mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-03 01:03:59 +00:00
Merge branch 'main' into feat/litellm_sambanova_usage
This commit is contained in:
jhpiedrahitao
commit
172a918fe3
66 changed files with 9320 additions and 9446 deletions
11
docs/_static/css/my_theme.css
vendored
11
docs/_static/css/my_theme.css
vendored
|
|
@ -16,3 +16,14 @@
|
|||
.hide-title h1 {
|
||||
display: none;
|
||||
}
|
||||
|
||||
h2, h3, h4 {
|
||||
font-weight: normal;
|
||||
}
|
||||
html[data-theme="dark"] .rst-content div[class^="highlight"] {
|
||||
background-color: #0b0b0b;
|
||||
}
|
||||
pre {
|
||||
white-space: pre-wrap !important;
|
||||
word-break: break-all;
|
||||
}
|
||||
|
|
|
|||
932
docs/_static/llama-stack-spec.html
vendored
932
docs/_static/llama-stack-spec.html
vendored
|
|
@ -3092,6 +3092,125 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/chat/completions": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletion"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Inference"
|
||||
],
|
||||
"description": "Generate an OpenAI-compatible chat completion for the given messages using the specified model.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenaiChatCompletionRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/completions": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenAICompletion"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Inference"
|
||||
],
|
||||
"description": "Generate an OpenAI-compatible completion for the given prompt using the specified model.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenaiCompletionRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/openai/v1/models": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenAIListModelsResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Models"
|
||||
],
|
||||
"description": "",
|
||||
"parameters": []
|
||||
}
|
||||
},
|
||||
"/v1/post-training/preference-optimize": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -8713,6 +8832,819 @@
|
|||
],
|
||||
"title": "LogEventRequest"
|
||||
},
|
||||
"OpenAIAssistantMessageParam": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"role": {
|
||||
"type": "string",
|
||||
"const": "assistant",
|
||||
"default": "assistant",
|
||||
"description": "Must be \"assistant\" to identify this as the model's response"
|
||||
},
|
||||
"content": {
|
||||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The content of the model's response"
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The name of the assistant message participant."
|
||||
},
|
||||
"tool_calls": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/ToolCall"
|
||||
},
|
||||
"description": "List of tool calls. Each tool call is a ToolCall object."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"role",
|
||||
"content"
|
||||
],
|
||||
"title": "OpenAIAssistantMessageParam",
|
||||
"description": "A message containing the model's (assistant) response in an OpenAI-compatible chat completion request."
|
||||
},
|
||||
"OpenAIDeveloperMessageParam": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"role": {
|
||||
"type": "string",
|
||||
"const": "developer",
|
||||
"default": "developer",
|
||||
"description": "Must be \"developer\" to identify this as a developer message"
|
||||
},
|
||||
"content": {
|
||||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The content of the developer message"
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The name of the developer message participant."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"role",
|
||||
"content"
|
||||
],
|
||||
"title": "OpenAIDeveloperMessageParam",
|
||||
"description": "A message from the developer in an OpenAI-compatible chat completion request."
|
||||
},
|
||||
"OpenAIMessageParam": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIUserMessageParam"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAISystemMessageParam"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIAssistantMessageParam"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIToolMessageParam"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIDeveloperMessageParam"
|
||||
}
|
||||
],
|
||||
"discriminator": {
|
||||
"propertyName": "role",
|
||||
"mapping": {
|
||||
"user": "#/components/schemas/OpenAIUserMessageParam",
|
||||
"system": "#/components/schemas/OpenAISystemMessageParam",
|
||||
"assistant": "#/components/schemas/OpenAIAssistantMessageParam",
|
||||
"tool": "#/components/schemas/OpenAIToolMessageParam",
|
||||
"developer": "#/components/schemas/OpenAIDeveloperMessageParam"
|
||||
}
|
||||
}
|
||||
},
|
||||
"OpenAISystemMessageParam": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"role": {
|
||||
"type": "string",
|
||||
"const": "system",
|
||||
"default": "system",
|
||||
"description": "Must be \"system\" to identify this as a system message"
|
||||
},
|
||||
"content": {
|
||||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions)."
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The name of the system message participant."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"role",
|
||||
"content"
|
||||
],
|
||||
"title": "OpenAISystemMessageParam",
|
||||
"description": "A system message providing instructions or context to the model."
|
||||
},
|
||||
"OpenAIToolMessageParam": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"role": {
|
||||
"type": "string",
|
||||
"const": "tool",
|
||||
"default": "tool",
|
||||
"description": "Must be \"tool\" to identify this as a tool response"
|
||||
},
|
||||
"tool_call_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier for the tool call this response is for"
|
||||
},
|
||||
"content": {
|
||||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The response content from the tool"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"role",
|
||||
"tool_call_id",
|
||||
"content"
|
||||
],
|
||||
"title": "OpenAIToolMessageParam",
|
||||
"description": "A message representing the result of a tool invocation in an OpenAI-compatible chat completion request."
|
||||
},
|
||||
"OpenAIUserMessageParam": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"role": {
|
||||
"type": "string",
|
||||
"const": "user",
|
||||
"default": "user",
|
||||
"description": "Must be \"user\" to identify this as a user message"
|
||||
},
|
||||
"content": {
|
||||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The content of the message, which can include text and other media"
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The name of the user message participant."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"role",
|
||||
"content"
|
||||
],
|
||||
"title": "OpenAIUserMessageParam",
|
||||
"description": "A message from the user in an OpenAI-compatible chat completion request."
|
||||
},
|
||||
"OpenaiChatCompletionRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint."
|
||||
},
|
||||
"messages": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAIMessageParam"
|
||||
},
|
||||
"description": "List of messages in the conversation"
|
||||
},
|
||||
"frequency_penalty": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The penalty for repeated tokens"
|
||||
},
|
||||
"function_call": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"description": "(Optional) The function call to use"
|
||||
},
|
||||
"functions": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"description": "(Optional) List of functions to use"
|
||||
},
|
||||
"logit_bias": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "number"
|
||||
},
|
||||
"description": "(Optional) The logit bias to use"
|
||||
},
|
||||
"logprobs": {
|
||||
"type": "boolean",
|
||||
"description": "(Optional) The log probabilities to use"
|
||||
},
|
||||
"max_completion_tokens": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The maximum number of tokens to generate"
|
||||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The maximum number of tokens to generate"
|
||||
},
|
||||
"n": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The number of completions to generate"
|
||||
},
|
||||
"parallel_tool_calls": {
|
||||
"type": "boolean",
|
||||
"description": "(Optional) Whether to parallelize tool calls"
|
||||
},
|
||||
"presence_penalty": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The penalty for repeated tokens"
|
||||
},
|
||||
"response_format": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "(Optional) The response format to use"
|
||||
},
|
||||
"seed": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The seed to use"
|
||||
},
|
||||
"stop": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"description": "(Optional) The stop tokens to use"
|
||||
},
|
||||
"stream": {
|
||||
"type": "boolean",
|
||||
"description": "(Optional) Whether to stream the response"
|
||||
},
|
||||
"stream_options": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "(Optional) The stream options to use"
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The temperature to use"
|
||||
},
|
||||
"tool_choice": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"description": "(Optional) The tool choice to use"
|
||||
},
|
||||
"tools": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"description": "(Optional) The tools to use"
|
||||
},
|
||||
"top_logprobs": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The top log probabilities to use"
|
||||
},
|
||||
"top_p": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The top p to use"
|
||||
},
|
||||
"user": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The user to use"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"model",
|
||||
"messages"
|
||||
],
|
||||
"title": "OpenaiChatCompletionRequest"
|
||||
},
|
||||
"OpenAIChatCompletion": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the chat completion"
|
||||
},
|
||||
"choices": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAIChoice"
|
||||
},
|
||||
"description": "List of choices"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "chat.completion",
|
||||
"default": "chat.completion",
|
||||
"description": "The object type, which will be \"chat.completion\""
|
||||
},
|
||||
"created": {
|
||||
"type": "integer",
|
||||
"description": "The Unix timestamp in seconds when the chat completion was created"
|
||||
},
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "The model that was used to generate the chat completion"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"choices",
|
||||
"object",
|
||||
"created",
|
||||
"model"
|
||||
],
|
||||
"title": "OpenAIChatCompletion",
|
||||
"description": "Response from an OpenAI-compatible chat completion request."
|
||||
},
|
||||
"OpenAIChoice": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"message": {
|
||||
"$ref": "#/components/schemas/OpenAIMessageParam",
|
||||
"description": "The message from the model"
|
||||
},
|
||||
"finish_reason": {
|
||||
"type": "string",
|
||||
"description": "The reason the model stopped generating"
|
||||
},
|
||||
"index": {
|
||||
"type": "integer"
|
||||
},
|
||||
"logprobs": {
|
||||
"$ref": "#/components/schemas/OpenAIChoiceLogprobs"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"message",
|
||||
"finish_reason",
|
||||
"index"
|
||||
],
|
||||
"title": "OpenAIChoice",
|
||||
"description": "A choice from an OpenAI-compatible chat completion response."
|
||||
},
|
||||
"OpenAIChoiceLogprobs": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"content": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAITokenLogProb"
|
||||
}
|
||||
},
|
||||
"refusal": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAITokenLogProb"
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"title": "OpenAIChoiceLogprobs",
|
||||
"description": "The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response."
|
||||
},
|
||||
"OpenAITokenLogProb": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"token": {
|
||||
"type": "string"
|
||||
},
|
||||
"bytes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"logprob": {
|
||||
"type": "number"
|
||||
},
|
||||
"top_logprobs": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAITopLogProb"
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"token",
|
||||
"logprob",
|
||||
"top_logprobs"
|
||||
],
|
||||
"title": "OpenAITokenLogProb",
|
||||
"description": "The log probability for a token from an OpenAI-compatible chat completion response."
|
||||
},
|
||||
"OpenAITopLogProb": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"token": {
|
||||
"type": "string"
|
||||
},
|
||||
"bytes": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"logprob": {
|
||||
"type": "number"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"token",
|
||||
"logprob"
|
||||
],
|
||||
"title": "OpenAITopLogProb",
|
||||
"description": "The top log probability for a token from an OpenAI-compatible chat completion response."
|
||||
},
|
||||
"OpenaiCompletionRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint."
|
||||
},
|
||||
"prompt": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "integer"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"description": "The prompt to generate a completion for"
|
||||
},
|
||||
"best_of": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The number of completions to generate"
|
||||
},
|
||||
"echo": {
|
||||
"type": "boolean",
|
||||
"description": "(Optional) Whether to echo the prompt"
|
||||
},
|
||||
"frequency_penalty": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The penalty for repeated tokens"
|
||||
},
|
||||
"logit_bias": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "number"
|
||||
},
|
||||
"description": "(Optional) The logit bias to use"
|
||||
},
|
||||
"logprobs": {
|
||||
"type": "boolean",
|
||||
"description": "(Optional) The log probabilities to use"
|
||||
},
|
||||
"max_tokens": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The maximum number of tokens to generate"
|
||||
},
|
||||
"n": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The number of completions to generate"
|
||||
},
|
||||
"presence_penalty": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The penalty for repeated tokens"
|
||||
},
|
||||
"seed": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) The seed to use"
|
||||
},
|
||||
"stop": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
],
|
||||
"description": "(Optional) The stop tokens to use"
|
||||
},
|
||||
"stream": {
|
||||
"type": "boolean",
|
||||
"description": "(Optional) Whether to stream the response"
|
||||
},
|
||||
"stream_options": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "(Optional) The stream options to use"
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The temperature to use"
|
||||
},
|
||||
"top_p": {
|
||||
"type": "number",
|
||||
"description": "(Optional) The top p to use"
|
||||
},
|
||||
"user": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The user to use"
|
||||
},
|
||||
"guided_choice": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"prompt_logprobs": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"model",
|
||||
"prompt"
|
||||
],
|
||||
"title": "OpenaiCompletionRequest"
|
||||
},
|
||||
"OpenAICompletion": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"choices": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAICompletionChoice"
|
||||
}
|
||||
},
|
||||
"created": {
|
||||
"type": "integer"
|
||||
},
|
||||
"model": {
|
||||
"type": "string"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "text_completion",
|
||||
"default": "text_completion"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"choices",
|
||||
"created",
|
||||
"model",
|
||||
"object"
|
||||
],
|
||||
"title": "OpenAICompletion",
|
||||
"description": "Response from an OpenAI-compatible completion request."
|
||||
},
|
||||
"OpenAICompletionChoice": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"finish_reason": {
|
||||
"type": "string"
|
||||
},
|
||||
"text": {
|
||||
"type": "string"
|
||||
},
|
||||
"index": {
|
||||
"type": "integer"
|
||||
},
|
||||
"logprobs": {
|
||||
"$ref": "#/components/schemas/OpenAIChoiceLogprobs"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"finish_reason",
|
||||
"text",
|
||||
"index"
|
||||
],
|
||||
"title": "OpenAICompletionChoice",
|
||||
"description": "A choice from an OpenAI-compatible completion response."
|
||||
},
|
||||
"OpenAIModel": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"type": "string"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "model",
|
||||
"default": "model"
|
||||
},
|
||||
"created": {
|
||||
"type": "integer"
|
||||
},
|
||||
"owned_by": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"id",
|
||||
"object",
|
||||
"created",
|
||||
"owned_by"
|
||||
],
|
||||
"title": "OpenAIModel",
|
||||
"description": "A model from OpenAI."
|
||||
},
|
||||
"OpenAIListModelsResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/OpenAIModel"
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"data"
|
||||
],
|
||||
"title": "OpenAIListModelsResponse"
|
||||
},
|
||||
"DPOAlignmentConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
|
|||
665
docs/_static/llama-stack-spec.yaml
vendored
665
docs/_static/llama-stack-spec.yaml
vendored
|
|
@ -2131,6 +2131,91 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/LogEventRequest'
|
||||
required: true
|
||||
/v1/openai/v1/chat/completions:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletion'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Inference
|
||||
description: >-
|
||||
Generate an OpenAI-compatible chat completion for the given messages using
|
||||
the specified model.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/OpenaiChatCompletionRequest'
|
||||
required: true
|
||||
/v1/openai/v1/completions:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/OpenAICompletion'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Inference
|
||||
description: >-
|
||||
Generate an OpenAI-compatible completion for the given prompt using the specified
|
||||
model.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/OpenaiCompletionRequest'
|
||||
required: true
|
||||
/v1/openai/v1/models:
|
||||
get:
|
||||
responses:
|
||||
'200':
|
||||
description: OK
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/OpenAIListModelsResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Models
|
||||
description: ''
|
||||
parameters: []
|
||||
/v1/post-training/preference-optimize:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -5980,6 +6065,586 @@ components:
|
|||
- event
|
||||
- ttl_seconds
|
||||
title: LogEventRequest
|
||||
OpenAIAssistantMessageParam:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: assistant
|
||||
default: assistant
|
||||
description: >-
|
||||
Must be "assistant" to identify this as the model's response
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: The content of the model's response
|
||||
name:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The name of the assistant message participant.
|
||||
tool_calls:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/ToolCall'
|
||||
description: >-
|
||||
List of tool calls. Each tool call is a ToolCall object.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
title: OpenAIAssistantMessageParam
|
||||
description: >-
|
||||
A message containing the model's (assistant) response in an OpenAI-compatible
|
||||
chat completion request.
|
||||
OpenAIDeveloperMessageParam:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: developer
|
||||
default: developer
|
||||
description: >-
|
||||
Must be "developer" to identify this as a developer message
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: The content of the developer message
|
||||
name:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The name of the developer message participant.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
title: OpenAIDeveloperMessageParam
|
||||
description: >-
|
||||
A message from the developer in an OpenAI-compatible chat completion request.
|
||||
OpenAIMessageParam:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIUserMessageParam'
|
||||
- $ref: '#/components/schemas/OpenAISystemMessageParam'
|
||||
- $ref: '#/components/schemas/OpenAIAssistantMessageParam'
|
||||
- $ref: '#/components/schemas/OpenAIToolMessageParam'
|
||||
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
|
||||
discriminator:
|
||||
propertyName: role
|
||||
mapping:
|
||||
user: '#/components/schemas/OpenAIUserMessageParam'
|
||||
system: '#/components/schemas/OpenAISystemMessageParam'
|
||||
assistant: '#/components/schemas/OpenAIAssistantMessageParam'
|
||||
tool: '#/components/schemas/OpenAIToolMessageParam'
|
||||
developer: '#/components/schemas/OpenAIDeveloperMessageParam'
|
||||
OpenAISystemMessageParam:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: system
|
||||
default: system
|
||||
description: >-
|
||||
Must be "system" to identify this as a system message
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
The content of the "system prompt". If multiple system messages are provided,
|
||||
they are concatenated. The underlying Llama Stack code may also add other
|
||||
system messages (for example, for formatting tool definitions).
|
||||
name:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The name of the system message participant.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
title: OpenAISystemMessageParam
|
||||
description: >-
|
||||
A system message providing instructions or context to the model.
|
||||
OpenAIToolMessageParam:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: tool
|
||||
default: tool
|
||||
description: >-
|
||||
Must be "tool" to identify this as a tool response
|
||||
tool_call_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier for the tool call this response is for
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: The response content from the tool
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- tool_call_id
|
||||
- content
|
||||
title: OpenAIToolMessageParam
|
||||
description: >-
|
||||
A message representing the result of a tool invocation in an OpenAI-compatible
|
||||
chat completion request.
|
||||
OpenAIUserMessageParam:
|
||||
type: object
|
||||
properties:
|
||||
role:
|
||||
type: string
|
||||
const: user
|
||||
default: user
|
||||
description: >-
|
||||
Must be "user" to identify this as a user message
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: >-
|
||||
The content of the message, which can include text and other media
|
||||
name:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) The name of the user message participant.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- role
|
||||
- content
|
||||
title: OpenAIUserMessageParam
|
||||
description: >-
|
||||
A message from the user in an OpenAI-compatible chat completion request.
|
||||
OpenaiChatCompletionRequest:
|
||||
type: object
|
||||
properties:
|
||||
model:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the model to use. The model must be registered with
|
||||
Llama Stack and available via the /models endpoint.
|
||||
messages:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAIMessageParam'
|
||||
description: List of messages in the conversation
|
||||
frequency_penalty:
|
||||
type: number
|
||||
description: >-
|
||||
(Optional) The penalty for repeated tokens
|
||||
function_call:
|
||||
oneOf:
|
||||
- type: string
|
||||
- type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) The function call to use
|
||||
functions:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) List of functions to use
|
||||
logit_bias:
|
||||
type: object
|
||||
additionalProperties:
|
||||
type: number
|
||||
description: (Optional) The logit bias to use
|
||||
logprobs:
|
||||
type: boolean
|
||||
description: (Optional) The log probabilities to use
|
||||
max_completion_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The maximum number of tokens to generate
|
||||
max_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The maximum number of tokens to generate
|
||||
n:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The number of completions to generate
|
||||
parallel_tool_calls:
|
||||
type: boolean
|
||||
description: >-
|
||||
(Optional) Whether to parallelize tool calls
|
||||
presence_penalty:
|
||||
type: number
|
||||
description: >-
|
||||
(Optional) The penalty for repeated tokens
|
||||
response_format:
|
||||
type: object
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: (Optional) The response format to use
|
||||
seed:
|
||||
type: integer
|
||||
description: (Optional) The seed to use
|
||||
stop:
|
||||
oneOf:
|
||||
- type: string
|
||||
- type: array
|
||||
items:
|
||||
type: string
|
||||
description: (Optional) The stop tokens to use
|
||||
stream:
|
||||
type: boolean
|
||||
description: >-
|
||||
(Optional) Whether to stream the response
|
||||
stream_options:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) The stream options to use
|
||||
temperature:
|
||||
type: number
|
||||
description: (Optional) The temperature to use
|
||||
tool_choice:
|
||||
oneOf:
|
||||
- type: string
|
||||
- type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) The tool choice to use
|
||||
tools:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) The tools to use
|
||||
top_logprobs:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The top log probabilities to use
|
||||
top_p:
|
||||
type: number
|
||||
description: (Optional) The top p to use
|
||||
user:
|
||||
type: string
|
||||
description: (Optional) The user to use
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model
|
||||
- messages
|
||||
title: OpenaiChatCompletionRequest
|
||||
OpenAIChatCompletion:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
description: The ID of the chat completion
|
||||
choices:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAIChoice'
|
||||
description: List of choices
|
||||
object:
|
||||
type: string
|
||||
const: chat.completion
|
||||
default: chat.completion
|
||||
description: >-
|
||||
The object type, which will be "chat.completion"
|
||||
created:
|
||||
type: integer
|
||||
description: >-
|
||||
The Unix timestamp in seconds when the chat completion was created
|
||||
model:
|
||||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
- choices
|
||||
- object
|
||||
- created
|
||||
- model
|
||||
title: OpenAIChatCompletion
|
||||
description: >-
|
||||
Response from an OpenAI-compatible chat completion request.
|
||||
OpenAIChoice:
|
||||
type: object
|
||||
properties:
|
||||
message:
|
||||
$ref: '#/components/schemas/OpenAIMessageParam'
|
||||
description: The message from the model
|
||||
finish_reason:
|
||||
type: string
|
||||
description: The reason the model stopped generating
|
||||
index:
|
||||
type: integer
|
||||
logprobs:
|
||||
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- message
|
||||
- finish_reason
|
||||
- index
|
||||
title: OpenAIChoice
|
||||
description: >-
|
||||
A choice from an OpenAI-compatible chat completion response.
|
||||
OpenAIChoiceLogprobs:
|
||||
type: object
|
||||
properties:
|
||||
content:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAITokenLogProb'
|
||||
refusal:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAITokenLogProb'
|
||||
additionalProperties: false
|
||||
title: OpenAIChoiceLogprobs
|
||||
description: >-
|
||||
The log probabilities for the tokens in the message from an OpenAI-compatible
|
||||
chat completion response.
|
||||
OpenAITokenLogProb:
|
||||
type: object
|
||||
properties:
|
||||
token:
|
||||
type: string
|
||||
bytes:
|
||||
type: array
|
||||
items:
|
||||
type: integer
|
||||
logprob:
|
||||
type: number
|
||||
top_logprobs:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAITopLogProb'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- token
|
||||
- logprob
|
||||
- top_logprobs
|
||||
title: OpenAITokenLogProb
|
||||
description: >-
|
||||
The log probability for a token from an OpenAI-compatible chat completion
|
||||
response.
|
||||
OpenAITopLogProb:
|
||||
type: object
|
||||
properties:
|
||||
token:
|
||||
type: string
|
||||
bytes:
|
||||
type: array
|
||||
items:
|
||||
type: integer
|
||||
logprob:
|
||||
type: number
|
||||
additionalProperties: false
|
||||
required:
|
||||
- token
|
||||
- logprob
|
||||
title: OpenAITopLogProb
|
||||
description: >-
|
||||
The top log probability for a token from an OpenAI-compatible chat completion
|
||||
response.
|
||||
OpenaiCompletionRequest:
|
||||
type: object
|
||||
properties:
|
||||
model:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the model to use. The model must be registered with
|
||||
Llama Stack and available via the /models endpoint.
|
||||
prompt:
|
||||
oneOf:
|
||||
- type: string
|
||||
- type: array
|
||||
items:
|
||||
type: string
|
||||
- type: array
|
||||
items:
|
||||
type: integer
|
||||
- type: array
|
||||
items:
|
||||
type: array
|
||||
items:
|
||||
type: integer
|
||||
description: The prompt to generate a completion for
|
||||
best_of:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The number of completions to generate
|
||||
echo:
|
||||
type: boolean
|
||||
description: (Optional) Whether to echo the prompt
|
||||
frequency_penalty:
|
||||
type: number
|
||||
description: >-
|
||||
(Optional) The penalty for repeated tokens
|
||||
logit_bias:
|
||||
type: object
|
||||
additionalProperties:
|
||||
type: number
|
||||
description: (Optional) The logit bias to use
|
||||
logprobs:
|
||||
type: boolean
|
||||
description: (Optional) The log probabilities to use
|
||||
max_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The maximum number of tokens to generate
|
||||
n:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) The number of completions to generate
|
||||
presence_penalty:
|
||||
type: number
|
||||
description: >-
|
||||
(Optional) The penalty for repeated tokens
|
||||
seed:
|
||||
type: integer
|
||||
description: (Optional) The seed to use
|
||||
stop:
|
||||
oneOf:
|
||||
- type: string
|
||||
- type: array
|
||||
items:
|
||||
type: string
|
||||
description: (Optional) The stop tokens to use
|
||||
stream:
|
||||
type: boolean
|
||||
description: >-
|
||||
(Optional) Whether to stream the response
|
||||
stream_options:
|
||||
type: object
|
||||
additionalProperties:
|
||||
oneOf:
|
||||
- type: 'null'
|
||||
- type: boolean
|
||||
- type: number
|
||||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) The stream options to use
|
||||
temperature:
|
||||
type: number
|
||||
description: (Optional) The temperature to use
|
||||
top_p:
|
||||
type: number
|
||||
description: (Optional) The top p to use
|
||||
user:
|
||||
type: string
|
||||
description: (Optional) The user to use
|
||||
guided_choice:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
prompt_logprobs:
|
||||
type: integer
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model
|
||||
- prompt
|
||||
title: OpenaiCompletionRequest
|
||||
OpenAICompletion:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
choices:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAICompletionChoice'
|
||||
created:
|
||||
type: integer
|
||||
model:
|
||||
type: string
|
||||
object:
|
||||
type: string
|
||||
const: text_completion
|
||||
default: text_completion
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
- choices
|
||||
- created
|
||||
- model
|
||||
- object
|
||||
title: OpenAICompletion
|
||||
description: >-
|
||||
Response from an OpenAI-compatible completion request.
|
||||
OpenAICompletionChoice:
|
||||
type: object
|
||||
properties:
|
||||
finish_reason:
|
||||
type: string
|
||||
text:
|
||||
type: string
|
||||
index:
|
||||
type: integer
|
||||
logprobs:
|
||||
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- finish_reason
|
||||
- text
|
||||
- index
|
||||
title: OpenAICompletionChoice
|
||||
description: >-
|
||||
A choice from an OpenAI-compatible completion response.
|
||||
OpenAIModel:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
object:
|
||||
type: string
|
||||
const: model
|
||||
default: model
|
||||
created:
|
||||
type: integer
|
||||
owned_by:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
- object
|
||||
- created
|
||||
- owned_by
|
||||
title: OpenAIModel
|
||||
description: A model from OpenAI.
|
||||
OpenAIListModelsResponse:
|
||||
type: object
|
||||
properties:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/OpenAIModel'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- data
|
||||
title: OpenAIListModelsResponse
|
||||
DPOAlignmentConfig:
|
||||
type: object
|
||||
properties:
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
The Llama Stack runtime configuration is specified as a YAML file. Here is a simplified version of an example configuration file for the Ollama distribution:
|
||||
|
||||
```{dropdown} Sample Configuration File
|
||||
```{dropdown} 👋 Click here for a Sample Configuration File
|
||||
|
||||
```yaml
|
||||
version: 2
|
||||
|
|
|
|||
|
|
@ -11,7 +11,12 @@ First, create a local Kubernetes cluster via Kind:
|
|||
kind create cluster --image kindest/node:v1.32.0 --name llama-stack-test
|
||||
```
|
||||
|
||||
First, create a Kubernetes PVC and Secret for downloading and storing Hugging Face model:
|
||||
First set your hugging face token as an environment variable.
|
||||
```
|
||||
export HF_TOKEN=$(echo -n "your-hf-token" | base64)
|
||||
```
|
||||
|
||||
Now create a Kubernetes PVC and Secret for downloading and storing Hugging Face model:
|
||||
|
||||
```
|
||||
cat <<EOF |kubectl apply -f -
|
||||
|
|
@ -33,7 +38,8 @@ metadata:
|
|||
name: hf-token-secret
|
||||
type: Opaque
|
||||
data:
|
||||
token: $(HF_TOKEN)
|
||||
token: $HF_TOKEN
|
||||
EOF
|
||||
```
|
||||
|
||||
|
||||
|
|
@ -120,7 +126,7 @@ providers:
|
|||
Once we have defined the run configuration for Llama Stack, we can build an image with that configuration and the server source code:
|
||||
|
||||
```
|
||||
cat >/tmp/test-vllm-llama-stack/Containerfile.llama-stack-run-k8s <<EOF
|
||||
tmp_dir=$(mktemp -d) && cat >$tmp_dir/Containerfile.llama-stack-run-k8s <<EOF
|
||||
FROM distribution-myenv:dev
|
||||
|
||||
RUN apt-get update && apt-get install -y git
|
||||
|
|
@ -128,7 +134,7 @@ RUN git clone https://github.com/meta-llama/llama-stack.git /app/llama-stack-sou
|
|||
|
||||
ADD ./vllm-llama-stack-run-k8s.yaml /app/config.yaml
|
||||
EOF
|
||||
podman build -f /tmp/test-vllm-llama-stack/Containerfile.llama-stack-run-k8s -t llama-stack-run-k8s /tmp/test-vllm-llama-stack
|
||||
podman build -f $tmp_dir/Containerfile.llama-stack-run-k8s -t llama-stack-run-k8s $tmp_dir
|
||||
```
|
||||
|
||||
### Deploying Llama Stack Server in Kubernetes
|
||||
|
|
|
|||
|
|
@ -1,88 +0,0 @@
|
|||
<!-- This file was auto-generated by distro_codegen.py, please edit source -->
|
||||
# NVIDIA Distribution
|
||||
|
||||
The `llamastack/distribution-nvidia` distribution consists of the following provider configurations.
|
||||
|
||||
| API | Provider(s) |
|
||||
|-----|-------------|
|
||||
| agents | `inline::meta-reference` |
|
||||
| datasetio | `inline::localfs` |
|
||||
| eval | `inline::meta-reference` |
|
||||
| inference | `remote::nvidia` |
|
||||
| post_training | `remote::nvidia` |
|
||||
| safety | `remote::nvidia` |
|
||||
| scoring | `inline::basic` |
|
||||
| telemetry | `inline::meta-reference` |
|
||||
| tool_runtime | `inline::rag-runtime` |
|
||||
| vector_io | `inline::faiss` |
|
||||
|
||||
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
- `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
|
||||
- `NVIDIA_USER_ID`: NVIDIA User ID (default: `llama-stack-user`)
|
||||
- `NVIDIA_DATASET_NAMESPACE`: NVIDIA Dataset Namespace (default: `default`)
|
||||
- `NVIDIA_ACCESS_POLICIES`: NVIDIA Access Policies (default: `{}`)
|
||||
- `NVIDIA_PROJECT_ID`: NVIDIA Project ID (default: `test-project`)
|
||||
- `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
|
||||
- `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)
|
||||
- `GUARDRAILS_SERVICE_URL`: URL for the NeMo Guardrails Service (default: `http://0.0.0.0:7331`)
|
||||
- `INFERENCE_MODEL`: Inference model (default: `Llama3.1-8B-Instruct`)
|
||||
- `SAFETY_MODEL`: Name of the model to use for safety (default: `meta/llama-3.1-8b-instruct`)
|
||||
|
||||
### Models
|
||||
|
||||
The following models are available by default:
|
||||
|
||||
- `meta/llama3-8b-instruct (aliases: meta-llama/Llama-3-8B-Instruct)`
|
||||
- `meta/llama3-70b-instruct (aliases: meta-llama/Llama-3-70B-Instruct)`
|
||||
- `meta/llama-3.1-8b-instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
|
||||
- `meta/llama-3.1-70b-instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
|
||||
- `meta/llama-3.1-405b-instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
|
||||
- `meta/llama-3.2-1b-instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
|
||||
- `meta/llama-3.2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
|
||||
- `meta/llama-3.2-11b-vision-instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
|
||||
- `meta/llama-3.2-90b-vision-instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
|
||||
- `nvidia/llama-3.2-nv-embedqa-1b-v2 `
|
||||
- `nvidia/nv-embedqa-e5-v5 `
|
||||
- `nvidia/nv-embedqa-mistral-7b-v2 `
|
||||
- `snowflake/arctic-embed-l `
|
||||
|
||||
|
||||
### Prerequisite: API Keys
|
||||
|
||||
Make sure you have access to a NVIDIA API Key. You can get one by visiting [https://build.nvidia.com/](https://build.nvidia.com/).
|
||||
|
||||
|
||||
## Running Llama Stack with NVIDIA
|
||||
|
||||
You can do this via Conda (build code) or Docker which has a pre-built image.
|
||||
|
||||
### Via Docker
|
||||
|
||||
This method allows you to get started quickly without having to build the distribution code.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=8321
|
||||
docker run \
|
||||
-it \
|
||||
--pull always \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-nvidia \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
```bash
|
||||
llama stack build --template nvidia --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port 8321 \
|
||||
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL
|
||||
```
|
||||
|
|
@ -1,3 +1,4 @@
|
|||
<!-- This file was auto-generated by distro_codegen.py, please edit source -->
|
||||
# NVIDIA Distribution
|
||||
|
||||
The `llamastack/distribution-nvidia` distribution consists of the following provider configurations.
|
||||
|
|
@ -5,24 +6,49 @@ The `llamastack/distribution-nvidia` distribution consists of the following prov
|
|||
| API | Provider(s) |
|
||||
|-----|-------------|
|
||||
| agents | `inline::meta-reference` |
|
||||
| datasetio | `inline::localfs` |
|
||||
| eval | `inline::meta-reference` |
|
||||
| inference | `remote::nvidia` |
|
||||
| memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
|
||||
| safety | `inline::llama-guard` |
|
||||
| post_training | `remote::nvidia` |
|
||||
| safety | `remote::nvidia` |
|
||||
| scoring | `inline::basic` |
|
||||
| telemetry | `inline::meta-reference` |
|
||||
| tool_runtime | `inline::rag-runtime` |
|
||||
| vector_io | `inline::faiss` |
|
||||
|
||||
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `8321`)
|
||||
- `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
|
||||
- `NVIDIA_USER_ID`: NVIDIA User ID (default: `llama-stack-user`)
|
||||
- `NVIDIA_DATASET_NAMESPACE`: NVIDIA Dataset Namespace (default: `default`)
|
||||
- `NVIDIA_ACCESS_POLICIES`: NVIDIA Access Policies (default: `{}`)
|
||||
- `NVIDIA_PROJECT_ID`: NVIDIA Project ID (default: `test-project`)
|
||||
- `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
|
||||
- `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)
|
||||
- `GUARDRAILS_SERVICE_URL`: URL for the NeMo Guardrails Service (default: `http://0.0.0.0:7331`)
|
||||
- `INFERENCE_MODEL`: Inference model (default: `Llama3.1-8B-Instruct`)
|
||||
- `SAFETY_MODEL`: Name of the model to use for safety (default: `meta/llama-3.1-8b-instruct`)
|
||||
|
||||
### Models
|
||||
|
||||
The following models are available by default:
|
||||
|
||||
- `${env.INFERENCE_MODEL} (None)`
|
||||
- `meta/llama3-8b-instruct (aliases: meta-llama/Llama-3-8B-Instruct)`
|
||||
- `meta/llama3-70b-instruct (aliases: meta-llama/Llama-3-70B-Instruct)`
|
||||
- `meta/llama-3.1-8b-instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
|
||||
- `meta/llama-3.1-70b-instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
|
||||
- `meta/llama-3.1-405b-instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
|
||||
- `meta/llama-3.2-1b-instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
|
||||
- `meta/llama-3.2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
|
||||
- `meta/llama-3.2-11b-vision-instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
|
||||
- `meta/llama-3.2-90b-vision-instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
|
||||
- `nvidia/llama-3.2-nv-embedqa-1b-v2 `
|
||||
- `nvidia/nv-embedqa-e5-v5 `
|
||||
- `nvidia/nv-embedqa-mistral-7b-v2 `
|
||||
- `snowflake/arctic-embed-l `
|
||||
|
||||
|
||||
### Prerequisite: API Keys
|
||||
|
|
@ -58,4 +84,5 @@ llama stack build --template nvidia --image-type conda
|
|||
llama stack run ./run.yaml \
|
||||
--port 8321 \
|
||||
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL
|
||||
```
|
||||
|
|
|
|||
|
|
@ -2,22 +2,22 @@
|
|||
|
||||
You can run a Llama Stack server in one of the following ways:
|
||||
|
||||
**As a Library**:
|
||||
## As a Library:
|
||||
|
||||
This is the simplest way to get started. Using Llama Stack as a library means you do not need to start a server. This is especially useful when you are not running inference locally and relying on an external inference service (eg. fireworks, together, groq, etc.) See [Using Llama Stack as a Library](importing_as_library)
|
||||
|
||||
|
||||
**Container**:
|
||||
## Container:
|
||||
|
||||
Another simple way to start interacting with Llama Stack is to just spin up a container (via Docker or Podman) which is pre-built with all the providers you need. We provide a number of pre-built images so you can start a Llama Stack server instantly. You can also build your own custom container. Which distribution to choose depends on the hardware you have. See [Selection of a Distribution](selection) for more details.
|
||||
|
||||
|
||||
**Conda**:
|
||||
## Conda:
|
||||
|
||||
If you have a custom or an advanced setup or you are developing on Llama Stack you can also build a custom Llama Stack server. Using `llama stack build` and `llama stack run` you can build/run a custom Llama Stack server containing the exact combination of providers you wish. We have also provided various templates to make getting started easier. See [Building a Custom Distribution](building_distro) for more details.
|
||||
|
||||
|
||||
**Kubernetes**:
|
||||
## Kubernetes:
|
||||
|
||||
If you have built a container image and want to deploy it in a Kubernetes cluster instead of starting the Llama Stack server locally. See [Kubernetes Deployment Guide](kubernetes_deployment) for more details.
|
||||
|
||||
|
|
|
|||
541
docs/source/getting_started/detailed_tutorial.md
Normal file
541
docs/source/getting_started/detailed_tutorial.md
Normal file
|
|
@ -0,0 +1,541 @@
|
|||
# Detailed Tutorial
|
||||
|
||||
In this guide, we'll walk through how you can use the Llama Stack (server and client SDK) to test a simple agent.
|
||||
A Llama Stack agent is a simple integrated system that can perform tasks by combining a Llama model for reasoning with
|
||||
tools (e.g., RAG, web search, code execution, etc.) for taking actions.
|
||||
In Llama Stack, we provide a server exposing multiple APIs. These APIs are backed by implementations from different providers.
|
||||
|
||||
Llama Stack is a stateful service with REST APIs to support seamless transition of AI applications across different environments. The server can be run in a variety of ways, including as a standalone binary, Docker container, or hosted service. You can build and test using a local server first and deploy to a hosted endpoint for production.
|
||||
|
||||
In this guide, we'll walk through how to build a RAG agent locally using Llama Stack with [Ollama](https://ollama.com/)
|
||||
as the inference [provider](../providers/index.md#inference) for a Llama Model.
|
||||
|
||||
## Step 1: Installation and Setup
|
||||
|
||||
Install Ollama by following the instructions on the [Ollama website](https://ollama.com/download), then
|
||||
download Llama 3.2 3B model, and then start the Ollama service.
|
||||
```bash
|
||||
ollama pull llama3.2:3b
|
||||
ollama run llama3.2:3b --keepalive 60m
|
||||
```
|
||||
|
||||
Install [uv](https://docs.astral.sh/uv/) to setup your virtual environment
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} macOS and Linux
|
||||
Use `curl` to download the script and execute it with `sh`:
|
||||
```console
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
```
|
||||
:::
|
||||
|
||||
:::{tab-item} Windows
|
||||
Use `irm` to download the script and execute it with `iex`:
|
||||
|
||||
```console
|
||||
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
|
||||
```
|
||||
:::
|
||||
::::
|
||||
|
||||
Setup your virtual environment.
|
||||
|
||||
```bash
|
||||
uv venv --python 3.10
|
||||
source .venv/bin/activate
|
||||
```
|
||||
## Step 2: Run Llama Stack
|
||||
Llama Stack is a server that exposes multiple APIs, you connect with it using the Llama Stack client SDK.
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} Using `venv`
|
||||
You can use Python to build and run the Llama Stack server, which is useful for testing and development.
|
||||
|
||||
Llama Stack uses a [YAML configuration file](../distributions/configuration.md) to specify the stack setup,
|
||||
which defines the providers and their settings.
|
||||
Now let's build and run the Llama Stack config for Ollama.
|
||||
|
||||
```bash
|
||||
INFERENCE_MODEL=llama3.2:3b llama stack build --template ollama --image-type venv --run
|
||||
```
|
||||
:::
|
||||
:::{tab-item} Using `conda`
|
||||
You can use Python to build and run the Llama Stack server, which is useful for testing and development.
|
||||
|
||||
Llama Stack uses a [YAML configuration file](../distributions/configuration.md) to specify the stack setup,
|
||||
which defines the providers and their settings.
|
||||
Now let's build and run the Llama Stack config for Ollama.
|
||||
|
||||
```bash
|
||||
INFERENCE_MODEL=llama3.2:3b llama stack build --template ollama --image-type conda --image-name llama3-3b-conda --run
|
||||
```
|
||||
:::
|
||||
:::{tab-item} Using a Container
|
||||
You can use a container image to run the Llama Stack server. We provide several container images for the server
|
||||
component that works with different inference providers out of the box. For this guide, we will use
|
||||
`llamastack/distribution-ollama` as the container image. If you'd like to build your own image or customize the
|
||||
configurations, please check out [this guide](../references/index.md).
|
||||
First lets setup some environment variables and create a local directory to mount into the container’s file system.
|
||||
```bash
|
||||
export INFERENCE_MODEL="llama3.2:3b"
|
||||
export LLAMA_STACK_PORT=8321
|
||||
mkdir -p ~/.llama
|
||||
```
|
||||
Then start the server using the container tool of your choice. For example, if you are running Docker you can use the
|
||||
following command:
|
||||
```bash
|
||||
docker run -it \
|
||||
--pull always \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
llamastack/distribution-ollama \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env OLLAMA_URL=http://host.docker.internal:11434
|
||||
```
|
||||
Note to start the container with Podman, you can do the same but replace `docker` at the start of the command with
|
||||
`podman`. If you are using `podman` older than `4.7.0`, please also replace `host.docker.internal` in the `OLLAMA_URL`
|
||||
with `host.containers.internal`.
|
||||
|
||||
The configuration YAML for the Ollama distribution is available at `distributions/ollama/run.yaml`.
|
||||
|
||||
```{tip}
|
||||
|
||||
Docker containers run in their own isolated network namespaces on Linux. To allow the container to communicate with services running on the host via `localhost`, you need `--network=host`. This makes the container use the host’s network directly so it can connect to Ollama running on `localhost:11434`.
|
||||
|
||||
Linux users having issues running the above command should instead try the following:
|
||||
```bash
|
||||
docker run -it \
|
||||
--pull always \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
--network=host \
|
||||
llamastack/distribution-ollama \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env OLLAMA_URL=http://localhost:11434
|
||||
```
|
||||
:::
|
||||
::::
|
||||
You will see output like below:
|
||||
```
|
||||
INFO: Application startup complete.
|
||||
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
|
||||
```
|
||||
|
||||
Now you can use the Llama Stack client to run inference and build agents!
|
||||
|
||||
You can reuse the server setup or use the [Llama Stack Client](https://github.com/meta-llama/llama-stack-client-python/).
|
||||
Note that the client package is already included in the `llama-stack` package.
|
||||
|
||||
## Step 3: Run Client CLI
|
||||
|
||||
Open a new terminal and navigate to the same directory you started the server from. Then set up a new or activate your
|
||||
existing server virtual environment.
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} Reuse Server `venv`
|
||||
```bash
|
||||
# The client is included in the llama-stack package so we just activate the server venv
|
||||
source .venv/bin/activate
|
||||
```
|
||||
:::
|
||||
|
||||
:::{tab-item} Install with `venv`
|
||||
```bash
|
||||
uv venv client --python 3.10
|
||||
source client/bin/activate
|
||||
pip install llama-stack-client
|
||||
```
|
||||
:::
|
||||
|
||||
:::{tab-item} Install with `conda`
|
||||
```bash
|
||||
yes | conda create -n stack-client python=3.10
|
||||
conda activate stack-client
|
||||
pip install llama-stack-client
|
||||
```
|
||||
:::
|
||||
::::
|
||||
|
||||
Now let's use the `llama-stack-client` [CLI](../references/llama_stack_client_cli_reference.md) to check the
|
||||
connectivity to the server.
|
||||
|
||||
```bash
|
||||
llama-stack-client configure --endpoint http://localhost:8321 --api-key none
|
||||
```
|
||||
You will see the below:
|
||||
```
|
||||
Done! You can now use the Llama Stack Client CLI with endpoint http://localhost:8321
|
||||
```
|
||||
|
||||
List the models
|
||||
```bash
|
||||
llama-stack-client models list
|
||||
Available Models
|
||||
|
||||
┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
|
||||
┃ model_type ┃ identifier ┃ provider_resource_id ┃ metadata ┃ provider_id ┃
|
||||
┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
|
||||
│ embedding │ all-MiniLM-L6-v2 │ all-minilm:latest │ {'embedding_dimension': 384.0} │ ollama │
|
||||
├─────────────────┼─────────────────────────────────────┼─────────────────────────────────────┼───────────────────────────────────────────┼─────────────────┤
|
||||
│ llm │ llama3.2:3b │ llama3.2:3b │ │ ollama │
|
||||
└─────────────────┴─────────────────────────────────────┴─────────────────────────────────────┴───────────────────────────────────────────┴─────────────────┘
|
||||
|
||||
Total models: 2
|
||||
|
||||
```
|
||||
You can test basic Llama inference completion using the CLI.
|
||||
|
||||
```bash
|
||||
llama-stack-client inference chat-completion --message "tell me a joke"
|
||||
```
|
||||
Sample output:
|
||||
```python
|
||||
ChatCompletionResponse(
|
||||
completion_message=CompletionMessage(
|
||||
content="Here's one:\n\nWhat do you call a fake noodle?\n\nAn impasta!",
|
||||
role="assistant",
|
||||
stop_reason="end_of_turn",
|
||||
tool_calls=[],
|
||||
),
|
||||
logprobs=None,
|
||||
metrics=[
|
||||
Metric(metric="prompt_tokens", value=14.0, unit=None),
|
||||
Metric(metric="completion_tokens", value=27.0, unit=None),
|
||||
Metric(metric="total_tokens", value=41.0, unit=None),
|
||||
],
|
||||
)
|
||||
```
|
||||
|
||||
## Step 4: Run the Demos
|
||||
|
||||
Note that these demos show the [Python Client SDK](../references/python_sdk_reference/index.md).
|
||||
Other SDKs are also available, please refer to the [Client SDK](../index.md#client-sdks) list for the complete options.
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} Basic Inference
|
||||
Now you can run inference using the Llama Stack client SDK.
|
||||
|
||||
### i. Create the Script
|
||||
|
||||
Create a file `inference.py` and add the following code:
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
|
||||
client = LlamaStackClient(base_url="http://localhost:8321")
|
||||
|
||||
# List available models
|
||||
models = client.models.list()
|
||||
|
||||
# Select the first LLM
|
||||
llm = next(m for m in models if m.model_type == "llm")
|
||||
model_id = llm.identifier
|
||||
|
||||
print("Model:", model_id)
|
||||
|
||||
response = client.inference.chat_completion(
|
||||
model_id=model_id,
|
||||
messages=[
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Write a haiku about coding"},
|
||||
],
|
||||
)
|
||||
print(response.completion_message.content)
|
||||
```
|
||||
|
||||
### ii. Run the Script
|
||||
Let's run the script using `uv`
|
||||
```bash
|
||||
uv run python inference.py
|
||||
```
|
||||
Which will output:
|
||||
```
|
||||
Model: llama3.2:3b
|
||||
Here is a haiku about coding:
|
||||
|
||||
Lines of code unfold
|
||||
Logic flows through digital night
|
||||
Beauty in the bits
|
||||
```
|
||||
:::
|
||||
|
||||
:::{tab-item} Build a Simple Agent
|
||||
Next we can move beyond simple inference and build an agent that can perform tasks using the Llama Stack server.
|
||||
### i. Create the Script
|
||||
Create a file `agent.py` and add the following code:
|
||||
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
from llama_stack_client import Agent, AgentEventLogger
|
||||
from rich.pretty import pprint
|
||||
import uuid
|
||||
|
||||
client = LlamaStackClient(base_url=f"http://localhost:8321")
|
||||
|
||||
models = client.models.list()
|
||||
llm = next(m for m in models if m.model_type == "llm")
|
||||
model_id = llm.identifier
|
||||
|
||||
agent = Agent(client, model=model_id, instructions="You are a helpful assistant.")
|
||||
|
||||
s_id = agent.create_session(session_name=f"s{uuid.uuid4().hex}")
|
||||
|
||||
print("Non-streaming ...")
|
||||
response = agent.create_turn(
|
||||
messages=[{"role": "user", "content": "Who are you?"}],
|
||||
session_id=s_id,
|
||||
stream=False,
|
||||
)
|
||||
print("agent>", response.output_message.content)
|
||||
|
||||
print("Streaming ...")
|
||||
stream = agent.create_turn(
|
||||
messages=[{"role": "user", "content": "Who are you?"}], session_id=s_id, stream=True
|
||||
)
|
||||
for event in stream:
|
||||
pprint(event)
|
||||
|
||||
print("Streaming with print helper...")
|
||||
stream = agent.create_turn(
|
||||
messages=[{"role": "user", "content": "Who are you?"}], session_id=s_id, stream=True
|
||||
)
|
||||
for event in AgentEventLogger().log(stream):
|
||||
event.print()
|
||||
```
|
||||
### ii. Run the Script
|
||||
Let's run the script using `uv`
|
||||
```bash
|
||||
uv run python agent.py
|
||||
```
|
||||
|
||||
```{dropdown} 👋 Click here to see the sample output
|
||||
Non-streaming ...
|
||||
agent> I'm an artificial intelligence designed to assist and communicate with users like you. I don't have a personal identity, but I'm here to provide information, answer questions, and help with tasks to the best of my abilities.
|
||||
|
||||
I can be used for a wide range of purposes, such as:
|
||||
|
||||
* Providing definitions and explanations
|
||||
* Offering suggestions and ideas
|
||||
* Helping with language translation
|
||||
* Assisting with writing and proofreading
|
||||
* Generating text or responses to questions
|
||||
* Playing simple games or chatting about topics of interest
|
||||
|
||||
I'm constantly learning and improving my abilities, so feel free to ask me anything, and I'll do my best to help!
|
||||
|
||||
Streaming ...
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepStartPayload(
|
||||
│ │ │ event_type='step_start',
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference',
|
||||
│ │ │ metadata={}
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepProgressPayload(
|
||||
│ │ │ delta=TextDelta(text='As', type='text'),
|
||||
│ │ │ event_type='step_progress',
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference'
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepProgressPayload(
|
||||
│ │ │ delta=TextDelta(text=' a', type='text'),
|
||||
│ │ │ event_type='step_progress',
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference'
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
...
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepCompletePayload(
|
||||
│ │ │ event_type='step_complete',
|
||||
│ │ │ step_details=InferenceStep(
|
||||
│ │ │ │ api_model_response=CompletionMessage(
|
||||
│ │ │ │ │ content='As a conversational AI, I don\'t have a personal identity in the classical sense. I exist as a program running on computer servers, designed to process and respond to text-based inputs.\n\nI\'m an instance of a type of artificial intelligence called a "language model," which is trained on vast amounts of text data to generate human-like responses. My primary function is to understand and respond to natural language inputs, like our conversation right now.\n\nThink of me as a virtual assistant, a chatbot, or a conversational interface – I\'m here to provide information, answer questions, and engage in conversation to the best of my abilities. I don\'t have feelings, emotions, or consciousness like humans do, but I\'m designed to simulate human-like interactions to make our conversations feel more natural and helpful.\n\nSo, that\'s me in a nutshell! What can I help you with today?',
|
||||
│ │ │ │ │ role='assistant',
|
||||
│ │ │ │ │ stop_reason='end_of_turn',
|
||||
│ │ │ │ │ tool_calls=[]
|
||||
│ │ │ │ ),
|
||||
│ │ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ │ step_type='inference',
|
||||
│ │ │ │ turn_id='8b360202-f7cb-4786-baa9-166a1b46e2ca',
|
||||
│ │ │ │ completed_at=datetime.datetime(2025, 4, 3, 1, 15, 21, 716174, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ started_at=datetime.datetime(2025, 4, 3, 1, 15, 14, 28823, tzinfo=TzInfo(UTC))
|
||||
│ │ │ ),
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference'
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseTurnCompletePayload(
|
||||
│ │ │ event_type='turn_complete',
|
||||
│ │ │ turn=Turn(
|
||||
│ │ │ │ input_messages=[UserMessage(content='Who are you?', role='user', context=None)],
|
||||
│ │ │ │ output_message=CompletionMessage(
|
||||
│ │ │ │ │ content='As a conversational AI, I don\'t have a personal identity in the classical sense. I exist as a program running on computer servers, designed to process and respond to text-based inputs.\n\nI\'m an instance of a type of artificial intelligence called a "language model," which is trained on vast amounts of text data to generate human-like responses. My primary function is to understand and respond to natural language inputs, like our conversation right now.\n\nThink of me as a virtual assistant, a chatbot, or a conversational interface – I\'m here to provide information, answer questions, and engage in conversation to the best of my abilities. I don\'t have feelings, emotions, or consciousness like humans do, but I\'m designed to simulate human-like interactions to make our conversations feel more natural and helpful.\n\nSo, that\'s me in a nutshell! What can I help you with today?',
|
||||
│ │ │ │ │ role='assistant',
|
||||
│ │ │ │ │ stop_reason='end_of_turn',
|
||||
│ │ │ │ │ tool_calls=[]
|
||||
│ │ │ │ ),
|
||||
│ │ │ │ session_id='abd4afea-4324-43f4-9513-cfe3970d92e8',
|
||||
│ │ │ │ started_at=datetime.datetime(2025, 4, 3, 1, 15, 14, 28722, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ steps=[
|
||||
│ │ │ │ │ InferenceStep(
|
||||
│ │ │ │ │ │ api_model_response=CompletionMessage(
|
||||
│ │ │ │ │ │ │ content='As a conversational AI, I don\'t have a personal identity in the classical sense. I exist as a program running on computer servers, designed to process and respond to text-based inputs.\n\nI\'m an instance of a type of artificial intelligence called a "language model," which is trained on vast amounts of text data to generate human-like responses. My primary function is to understand and respond to natural language inputs, like our conversation right now.\n\nThink of me as a virtual assistant, a chatbot, or a conversational interface – I\'m here to provide information, answer questions, and engage in conversation to the best of my abilities. I don\'t have feelings, emotions, or consciousness like humans do, but I\'m designed to simulate human-like interactions to make our conversations feel more natural and helpful.\n\nSo, that\'s me in a nutshell! What can I help you with today?',
|
||||
│ │ │ │ │ │ │ role='assistant',
|
||||
│ │ │ │ │ │ │ stop_reason='end_of_turn',
|
||||
│ │ │ │ │ │ │ tool_calls=[]
|
||||
│ │ │ │ │ │ ),
|
||||
│ │ │ │ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ │ │ │ step_type='inference',
|
||||
│ │ │ │ │ │ turn_id='8b360202-f7cb-4786-baa9-166a1b46e2ca',
|
||||
│ │ │ │ │ │ completed_at=datetime.datetime(2025, 4, 3, 1, 15, 21, 716174, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ │ │ started_at=datetime.datetime(2025, 4, 3, 1, 15, 14, 28823, tzinfo=TzInfo(UTC))
|
||||
│ │ │ │ │ )
|
||||
│ │ │ │ ],
|
||||
│ │ │ │ turn_id='8b360202-f7cb-4786-baa9-166a1b46e2ca',
|
||||
│ │ │ │ completed_at=datetime.datetime(2025, 4, 3, 1, 15, 21, 727364, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ output_attachments=[]
|
||||
│ │ │ )
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
|
||||
|
||||
Streaming with print helper...
|
||||
inference> Déjà vu!
|
||||
|
||||
As I mentioned earlier, I'm an artificial intelligence language model. I don't have a personal identity or consciousness like humans do. I exist solely to process and respond to text-based inputs, providing information and assistance on a wide range of topics.
|
||||
|
||||
I'm a computer program designed to simulate human-like conversations, using natural language processing (NLP) and machine learning algorithms to understand and generate responses. My purpose is to help users like you with their questions, provide information, and engage in conversation.
|
||||
|
||||
Think of me as a virtual companion, a helpful tool designed to make your interactions more efficient and enjoyable. I don't have personal opinions, emotions, or biases, but I'm here to provide accurate and informative responses to the best of my abilities.
|
||||
|
||||
So, who am I? I'm just a computer program designed to help you!
|
||||
```
|
||||
:::
|
||||
|
||||
:::{tab-item} Build a RAG Agent
|
||||
|
||||
For our last demo, we can build a RAG agent that can answer questions about the Torchtune project using the documents
|
||||
in a vector database.
|
||||
### i. Create the Script
|
||||
Create a file `rag_agent.py` and add the following code:
|
||||
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
from llama_stack_client import Agent, AgentEventLogger
|
||||
from llama_stack_client.types import Document
|
||||
import uuid
|
||||
from termcolor import cprint
|
||||
|
||||
client = LlamaStackClient(base_url="http://localhost:8321")
|
||||
|
||||
# Create a vector database instance
|
||||
embed_lm = next(m for m in client.models.list() if m.model_type == "embedding")
|
||||
embedding_model = embed_lm.identifier
|
||||
vector_db_id = f"v{uuid.uuid4().hex}"
|
||||
client.vector_dbs.register(
|
||||
vector_db_id=vector_db_id,
|
||||
embedding_model=embedding_model,
|
||||
)
|
||||
|
||||
# Create Documents
|
||||
urls = [
|
||||
"memory_optimizations.rst",
|
||||
"chat.rst",
|
||||
"llama3.rst",
|
||||
"datasets.rst",
|
||||
"qat_finetune.rst",
|
||||
"lora_finetune.rst",
|
||||
]
|
||||
documents = [
|
||||
Document(
|
||||
document_id=f"num-{i}",
|
||||
content=f"https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/{url}",
|
||||
mime_type="text/plain",
|
||||
metadata={},
|
||||
)
|
||||
for i, url in enumerate(urls)
|
||||
]
|
||||
|
||||
# Insert documents
|
||||
client.tool_runtime.rag_tool.insert(
|
||||
documents=documents,
|
||||
vector_db_id=vector_db_id,
|
||||
chunk_size_in_tokens=512,
|
||||
)
|
||||
|
||||
# Get the model being served
|
||||
llm = next(m for m in client.models.list() if m.model_type == "llm")
|
||||
model = llm.identifier
|
||||
|
||||
# Create the RAG agent
|
||||
rag_agent = Agent(
|
||||
client,
|
||||
model=model,
|
||||
instructions="You are a helpful assistant. Use the RAG tool to answer questions as needed.",
|
||||
tools=[
|
||||
{
|
||||
"name": "builtin::rag/knowledge_search",
|
||||
"args": {"vector_db_ids": [vector_db_id]},
|
||||
}
|
||||
],
|
||||
)
|
||||
|
||||
session_id = rag_agent.create_session(session_name=f"s{uuid.uuid4().hex}")
|
||||
|
||||
turns = ["what is torchtune", "tell me about dora"]
|
||||
|
||||
for t in turns:
|
||||
print("user>", t)
|
||||
stream = rag_agent.create_turn(
|
||||
messages=[{"role": "user", "content": t}], session_id=session_id, stream=True
|
||||
)
|
||||
for event in AgentEventLogger().log(stream):
|
||||
event.print()
|
||||
```
|
||||
### ii. Run the Script
|
||||
Let's run the script using `uv`
|
||||
```bash
|
||||
uv run python rag_agent.py
|
||||
```
|
||||
|
||||
```{dropdown} 👋 Click here to see the sample output
|
||||
user> what is torchtune
|
||||
inference> [knowledge_search(query='TorchTune')]
|
||||
tool_execution> Tool:knowledge_search Args:{'query': 'TorchTune'}
|
||||
tool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\nBEGIN of knowledge_search tool results.\n', type='text'), TextContentItem(text='Result 1:\nDocument_id:num-1\nContent: conversational data, :func:`~torchtune.datasets.chat_dataset` seems to be a good fit. ..., type='text'), TextContentItem(text='END of knowledge_search tool results.\n', type='text')]
|
||||
inference> Here is a high-level overview of the text:
|
||||
|
||||
**LoRA Finetuning with PyTorch Tune**
|
||||
|
||||
PyTorch Tune provides a recipe for LoRA (Low-Rank Adaptation) finetuning, which is a technique to adapt pre-trained models to new tasks. The recipe uses the `lora_finetune_distributed` command.
|
||||
...
|
||||
Overall, DORA is a powerful reinforcement learning algorithm that can learn complex tasks from human demonstrations. However, it requires careful consideration of the challenges and limitations to achieve optimal results.
|
||||
```
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
**You're Ready to Build Your Own Apps!**
|
||||
|
||||
Congrats! 🥳 Now you're ready to [build your own Llama Stack applications](../building_applications/index)! 🚀
|
||||
|
|
@ -1,414 +1,65 @@
|
|||
# Quick Start
|
||||
# Quickstart
|
||||
|
||||
Get started with Llama Stack in minutes!
|
||||
|
||||
Llama Stack is a stateful service with REST APIs to support seamless transition of AI applications across different environments. The server can be run in a variety of ways, including as a standalone binary, Docker container, or hosted service. You can build and test using a local server first and deploy to a hosted endpoint for production.
|
||||
Llama Stack is a stateful service with REST APIs to support the seamless transition of AI applications across different
|
||||
environments. You can build and test using a local server first and deploy to a hosted endpoint for production.
|
||||
|
||||
In this guide, we'll walk through how to build a RAG agent locally using Llama Stack with [Ollama](https://ollama.com/) to run inference on a Llama Model.
|
||||
|
||||
|
||||
### 1. Download a Llama model with Ollama
|
||||
In this guide, we'll walk through how to build a RAG application locally using Llama Stack with [Ollama](https://ollama.com/)
|
||||
as the inference [provider](../providers/index.md#inference) for a Llama Model.
|
||||
|
||||
#### Step 1: Install and setup
|
||||
1. Install [uv](https://docs.astral.sh/uv/)
|
||||
2. Run inference on a Llama model with [Ollama](https://ollama.com/download)
|
||||
```bash
|
||||
ollama pull llama3.2:3b-instruct-fp16
|
||||
ollama run llama3.2:3b --keepalive 60m
|
||||
```
|
||||
|
||||
This will instruct the Ollama service to download the Llama 3.2 3B Instruct model, which we'll use in the rest of this guide.
|
||||
|
||||
```{admonition} Note
|
||||
:class: tip
|
||||
|
||||
If you do not have ollama, you can install it from [here](https://ollama.com/download).
|
||||
```
|
||||
|
||||
### 2. Run Llama Stack locally
|
||||
|
||||
We use `uv` to setup a virtual environment and install the Llama Stack package.
|
||||
|
||||
:::{dropdown} [Click to Open] Instructions to setup uv
|
||||
|
||||
Install [uv](https://docs.astral.sh/uv/) to setup your virtual environment.
|
||||
|
||||
|
||||
#### For macOS and Linux:
|
||||
#### Step 2: Run the Llama Stack server
|
||||
We will use `uv` to run the Llama Stack server.
|
||||
```bash
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
```
|
||||
#### For Windows:
|
||||
Use `irm` to download the script and execute it with `iex`:
|
||||
```powershell
|
||||
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
|
||||
INFERENCE_MODEL=llama3.2:3b uv run --with llama-stack llama stack build --template ollama --image-type venv --run
|
||||
```
|
||||
#### Step 3: Run the demo
|
||||
Now open up a new terminal and copy the following script into a file named `demo_script.py`.
|
||||
|
||||
Setup venv
|
||||
```bash
|
||||
uv venv --python 3.10
|
||||
source .venv/bin/activate
|
||||
```
|
||||
:::
|
||||
|
||||
**Install the Llama Stack package**
|
||||
```bash
|
||||
uv pip install -U llama-stack
|
||||
```
|
||||
|
||||
**Build and Run the Llama Stack server for Ollama.**
|
||||
```bash
|
||||
INFERENCE_MODEL=llama3.2:3b llama stack build --template ollama --image-type venv --run
|
||||
```
|
||||
|
||||
You will see the output end like below:
|
||||
```
|
||||
...
|
||||
INFO: Application startup complete.
|
||||
INFO: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
|
||||
```
|
||||
|
||||
Now you can use the llama stack client to run inference and build agents!
|
||||
|
||||
### 3. Client CLI
|
||||
|
||||
Install the client package
|
||||
```bash
|
||||
pip install llama-stack-client
|
||||
```
|
||||
|
||||
:::{dropdown} OR reuse server setup
|
||||
Open a new terminal and navigate to the same directory you started the server from.
|
||||
|
||||
Setup venv (llama-stack already includes the llama-stack-client package)
|
||||
```bash
|
||||
source .venv/bin/activate
|
||||
```
|
||||
:::
|
||||
|
||||
#### 3.1 Configure the client to point to the local server
|
||||
```bash
|
||||
llama-stack-client configure --endpoint http://localhost:8321 --api-key none
|
||||
```
|
||||
You will see the below:
|
||||
```
|
||||
Done! You can now use the Llama Stack Client CLI with endpoint http://localhost:8321
|
||||
```
|
||||
|
||||
#### 3.2 List available models
|
||||
```
|
||||
llama-stack-client models list
|
||||
```
|
||||
|
||||
```
|
||||
Available Models
|
||||
|
||||
┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
|
||||
┃ model_type ┃ identifier ┃ provider_resource_id ┃ metadata ┃ provider_id ┃
|
||||
┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
|
||||
│ embedding │ all-MiniLM-L6-v2 │ all-minilm:latest │ {'embedding_dimension': 384.0} │ ollama │
|
||||
├─────────────────┼─────────────────────────────────────┼─────────────────────────────────────┼───────────────────────────────────────────┼─────────────────┤
|
||||
│ llm │ llama3.2:3b │ llama3.2:3b │ │ ollama │
|
||||
└─────────────────┴─────────────────────────────────────┴─────────────────────────────────────┴───────────────────────────────────────────┴─────────────────┘
|
||||
|
||||
Total models: 2
|
||||
|
||||
```
|
||||
|
||||
#### 3.3 Test basic inference
|
||||
```bash
|
||||
llama-stack-client inference chat-completion --message "tell me a joke"
|
||||
```
|
||||
Sample output:
|
||||
```python
|
||||
ChatCompletionResponse(
|
||||
completion_message=CompletionMessage(
|
||||
content="Here's one:\n\nWhat do you call a fake noodle?\n\nAn impasta!",
|
||||
role="assistant",
|
||||
stop_reason="end_of_turn",
|
||||
tool_calls=[],
|
||||
),
|
||||
logprobs=None,
|
||||
metrics=[
|
||||
Metric(metric="prompt_tokens", value=14.0, unit=None),
|
||||
Metric(metric="completion_tokens", value=27.0, unit=None),
|
||||
Metric(metric="total_tokens", value=41.0, unit=None),
|
||||
],
|
||||
)
|
||||
```
|
||||
from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient
|
||||
|
||||
### 4. Python SDK
|
||||
Install the python client
|
||||
```bash
|
||||
pip install llama-stack-client
|
||||
```
|
||||
:::{dropdown} OR reuse server setup
|
||||
Open a new terminal and navigate to the same directory you started the server from.
|
||||
vector_db_id = "my_demo_vector_db"
|
||||
client = LlamaStackClient(base_url="http://localhost:8321")
|
||||
|
||||
Setup venv (llama-stack already includes the llama-stack-client package)
|
||||
```bash
|
||||
source .venv/bin/activate
|
||||
```
|
||||
:::
|
||||
#### 4.1 Basic Inference
|
||||
Create a file `inference.py` and add the following code:
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
|
||||
client = LlamaStackClient(base_url=f"http://localhost:8321")
|
||||
|
||||
# List available models
|
||||
models = client.models.list()
|
||||
|
||||
# Select the first LLM
|
||||
llm = next(m for m in models if m.model_type == "llm")
|
||||
model_id = llm.identifier
|
||||
# Select the first LLM and first embedding models
|
||||
model_id = next(m for m in models if m.model_type == "llm").identifier
|
||||
embedding_model_id = (
|
||||
em := next(m for m in models if m.model_type == "embedding")
|
||||
).identifier
|
||||
embedding_dimension = em.metadata["embedding_dimension"]
|
||||
|
||||
print("Model:", model_id)
|
||||
|
||||
response = client.inference.chat_completion(
|
||||
model_id=model_id,
|
||||
messages=[
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Write a haiku about coding"},
|
||||
],
|
||||
)
|
||||
print(response.completion_message.content)
|
||||
```
|
||||
Run the script
|
||||
```bash
|
||||
python inference.py
|
||||
```
|
||||
Sample output:
|
||||
```
|
||||
Model: llama3.2:3b-instruct-fp16
|
||||
Here is a haiku about coding:
|
||||
|
||||
Lines of code unfold
|
||||
Logic flows through digital night
|
||||
Beauty in the bits
|
||||
```
|
||||
|
||||
#### 4.2. Basic Agent
|
||||
|
||||
Create a file `agent.py` and add the following code:
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
from llama_stack_client import Agent, AgentEventLogger
|
||||
from rich.pretty import pprint
|
||||
import uuid
|
||||
|
||||
client = LlamaStackClient(base_url=f"http://localhost:8321")
|
||||
|
||||
models = client.models.list()
|
||||
llm = next(m for m in models if m.model_type == "llm")
|
||||
model_id = llm.identifier
|
||||
|
||||
agent = Agent(client, model=model_id, instructions="You are a helpful assistant.")
|
||||
|
||||
s_id = agent.create_session(session_name=f"s{uuid.uuid4().hex}")
|
||||
|
||||
print("Non-streaming ...")
|
||||
response = agent.create_turn(
|
||||
messages=[{"role": "user", "content": "Who are you?"}],
|
||||
session_id=s_id,
|
||||
stream=False,
|
||||
)
|
||||
print("agent>", response.output_message.content)
|
||||
|
||||
print("Streaming ...")
|
||||
stream = agent.create_turn(
|
||||
messages=[{"role": "user", "content": "Who are you?"}], session_id=s_id, stream=True
|
||||
)
|
||||
for event in stream:
|
||||
pprint(event)
|
||||
|
||||
print("Streaming with print helper...")
|
||||
stream = agent.create_turn(
|
||||
messages=[{"role": "user", "content": "Who are you?"}], session_id=s_id, stream=True
|
||||
)
|
||||
for event in AgentEventLogger().log(stream):
|
||||
event.print()
|
||||
```
|
||||
|
||||
Run the script:
|
||||
```bash
|
||||
python agent.py
|
||||
```
|
||||
|
||||
:::{dropdown} `Sample output`
|
||||
```
|
||||
Non-streaming ...
|
||||
agent> I'm an artificial intelligence designed to assist and communicate with users like you. I don't have a personal identity, but I'm here to provide information, answer questions, and help with tasks to the best of my abilities.
|
||||
|
||||
I can be used for a wide range of purposes, such as:
|
||||
|
||||
* Providing definitions and explanations
|
||||
* Offering suggestions and ideas
|
||||
* Helping with language translation
|
||||
* Assisting with writing and proofreading
|
||||
* Generating text or responses to questions
|
||||
* Playing simple games or chatting about topics of interest
|
||||
|
||||
I'm constantly learning and improving my abilities, so feel free to ask me anything, and I'll do my best to help!
|
||||
|
||||
Streaming ...
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepStartPayload(
|
||||
│ │ │ event_type='step_start',
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference',
|
||||
│ │ │ metadata={}
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepProgressPayload(
|
||||
│ │ │ delta=TextDelta(text='As', type='text'),
|
||||
│ │ │ event_type='step_progress',
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference'
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepProgressPayload(
|
||||
│ │ │ delta=TextDelta(text=' a', type='text'),
|
||||
│ │ │ event_type='step_progress',
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference'
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
...
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseStepCompletePayload(
|
||||
│ │ │ event_type='step_complete',
|
||||
│ │ │ step_details=InferenceStep(
|
||||
│ │ │ │ api_model_response=CompletionMessage(
|
||||
│ │ │ │ │ content='As a conversational AI, I don\'t have a personal identity in the classical sense. I exist as a program running on computer servers, designed to process and respond to text-based inputs.\n\nI\'m an instance of a type of artificial intelligence called a "language model," which is trained on vast amounts of text data to generate human-like responses. My primary function is to understand and respond to natural language inputs, like our conversation right now.\n\nThink of me as a virtual assistant, a chatbot, or a conversational interface – I\'m here to provide information, answer questions, and engage in conversation to the best of my abilities. I don\'t have feelings, emotions, or consciousness like humans do, but I\'m designed to simulate human-like interactions to make our conversations feel more natural and helpful.\n\nSo, that\'s me in a nutshell! What can I help you with today?',
|
||||
│ │ │ │ │ role='assistant',
|
||||
│ │ │ │ │ stop_reason='end_of_turn',
|
||||
│ │ │ │ │ tool_calls=[]
|
||||
│ │ │ │ ),
|
||||
│ │ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ │ step_type='inference',
|
||||
│ │ │ │ turn_id='8b360202-f7cb-4786-baa9-166a1b46e2ca',
|
||||
│ │ │ │ completed_at=datetime.datetime(2025, 4, 3, 1, 15, 21, 716174, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ started_at=datetime.datetime(2025, 4, 3, 1, 15, 14, 28823, tzinfo=TzInfo(UTC))
|
||||
│ │ │ ),
|
||||
│ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ step_type='inference'
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
AgentTurnResponseStreamChunk(
|
||||
│ event=TurnResponseEvent(
|
||||
│ │ payload=AgentTurnResponseTurnCompletePayload(
|
||||
│ │ │ event_type='turn_complete',
|
||||
│ │ │ turn=Turn(
|
||||
│ │ │ │ input_messages=[UserMessage(content='Who are you?', role='user', context=None)],
|
||||
│ │ │ │ output_message=CompletionMessage(
|
||||
│ │ │ │ │ content='As a conversational AI, I don\'t have a personal identity in the classical sense. I exist as a program running on computer servers, designed to process and respond to text-based inputs.\n\nI\'m an instance of a type of artificial intelligence called a "language model," which is trained on vast amounts of text data to generate human-like responses. My primary function is to understand and respond to natural language inputs, like our conversation right now.\n\nThink of me as a virtual assistant, a chatbot, or a conversational interface – I\'m here to provide information, answer questions, and engage in conversation to the best of my abilities. I don\'t have feelings, emotions, or consciousness like humans do, but I\'m designed to simulate human-like interactions to make our conversations feel more natural and helpful.\n\nSo, that\'s me in a nutshell! What can I help you with today?',
|
||||
│ │ │ │ │ role='assistant',
|
||||
│ │ │ │ │ stop_reason='end_of_turn',
|
||||
│ │ │ │ │ tool_calls=[]
|
||||
│ │ │ │ ),
|
||||
│ │ │ │ session_id='abd4afea-4324-43f4-9513-cfe3970d92e8',
|
||||
│ │ │ │ started_at=datetime.datetime(2025, 4, 3, 1, 15, 14, 28722, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ steps=[
|
||||
│ │ │ │ │ InferenceStep(
|
||||
│ │ │ │ │ │ api_model_response=CompletionMessage(
|
||||
│ │ │ │ │ │ │ content='As a conversational AI, I don\'t have a personal identity in the classical sense. I exist as a program running on computer servers, designed to process and respond to text-based inputs.\n\nI\'m an instance of a type of artificial intelligence called a "language model," which is trained on vast amounts of text data to generate human-like responses. My primary function is to understand and respond to natural language inputs, like our conversation right now.\n\nThink of me as a virtual assistant, a chatbot, or a conversational interface – I\'m here to provide information, answer questions, and engage in conversation to the best of my abilities. I don\'t have feelings, emotions, or consciousness like humans do, but I\'m designed to simulate human-like interactions to make our conversations feel more natural and helpful.\n\nSo, that\'s me in a nutshell! What can I help you with today?',
|
||||
│ │ │ │ │ │ │ role='assistant',
|
||||
│ │ │ │ │ │ │ stop_reason='end_of_turn',
|
||||
│ │ │ │ │ │ │ tool_calls=[]
|
||||
│ │ │ │ │ │ ),
|
||||
│ │ │ │ │ │ step_id='69831607-fa75-424a-949b-e2049e3129d1',
|
||||
│ │ │ │ │ │ step_type='inference',
|
||||
│ │ │ │ │ │ turn_id='8b360202-f7cb-4786-baa9-166a1b46e2ca',
|
||||
│ │ │ │ │ │ completed_at=datetime.datetime(2025, 4, 3, 1, 15, 21, 716174, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ │ │ started_at=datetime.datetime(2025, 4, 3, 1, 15, 14, 28823, tzinfo=TzInfo(UTC))
|
||||
│ │ │ │ │ )
|
||||
│ │ │ │ ],
|
||||
│ │ │ │ turn_id='8b360202-f7cb-4786-baa9-166a1b46e2ca',
|
||||
│ │ │ │ completed_at=datetime.datetime(2025, 4, 3, 1, 15, 21, 727364, tzinfo=TzInfo(UTC)),
|
||||
│ │ │ │ output_attachments=[]
|
||||
│ │ │ )
|
||||
│ │ )
|
||||
│ )
|
||||
)
|
||||
|
||||
|
||||
Streaming with print helper...
|
||||
inference> Déjà vu!
|
||||
|
||||
As I mentioned earlier, I'm an artificial intelligence language model. I don't have a personal identity or consciousness like humans do. I exist solely to process and respond to text-based inputs, providing information and assistance on a wide range of topics.
|
||||
|
||||
I'm a computer program designed to simulate human-like conversations, using natural language processing (NLP) and machine learning algorithms to understand and generate responses. My purpose is to help users like you with their questions, provide information, and engage in conversation.
|
||||
|
||||
Think of me as a virtual companion, a helpful tool designed to make your interactions more efficient and enjoyable. I don't have personal opinions, emotions, or biases, but I'm here to provide accurate and informative responses to the best of my abilities.
|
||||
|
||||
So, who am I? I'm just a computer program designed to help you!
|
||||
|
||||
```
|
||||
:::
|
||||
|
||||
#### 4.3. RAG agent
|
||||
|
||||
Create a file `rag_agent.py` and add the following code:
|
||||
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
from llama_stack_client import Agent, AgentEventLogger
|
||||
from llama_stack_client.types import Document
|
||||
import uuid
|
||||
|
||||
client = LlamaStackClient(base_url=f"http://localhost:8321")
|
||||
|
||||
# Create a vector database instance
|
||||
embedlm = next(m for m in client.models.list() if m.model_type == "embedding")
|
||||
embedding_model = embedlm.identifier
|
||||
vector_db_id = f"v{uuid.uuid4().hex}"
|
||||
client.vector_dbs.register(
|
||||
_ = client.vector_dbs.register(
|
||||
vector_db_id=vector_db_id,
|
||||
embedding_model=embedding_model,
|
||||
embedding_model=embedding_model_id,
|
||||
embedding_dimension=embedding_dimension,
|
||||
provider_id="faiss",
|
||||
)
|
||||
source = "https://www.paulgraham.com/greatwork.html"
|
||||
print("rag_tool> Ingesting document:", source)
|
||||
document = RAGDocument(
|
||||
document_id="document_1",
|
||||
content=source,
|
||||
mime_type="text/html",
|
||||
metadata={},
|
||||
)
|
||||
|
||||
# Create Documents
|
||||
urls = [
|
||||
"memory_optimizations.rst",
|
||||
"chat.rst",
|
||||
"llama3.rst",
|
||||
"datasets.rst",
|
||||
"qat_finetune.rst",
|
||||
"lora_finetune.rst",
|
||||
]
|
||||
documents = [
|
||||
Document(
|
||||
document_id=f"num-{i}",
|
||||
content=f"https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/{url}",
|
||||
mime_type="text/plain",
|
||||
metadata={},
|
||||
)
|
||||
for i, url in enumerate(urls)
|
||||
]
|
||||
|
||||
# Insert documents
|
||||
client.tool_runtime.rag_tool.insert(
|
||||
documents=documents,
|
||||
documents=[document],
|
||||
vector_db_id=vector_db_id,
|
||||
chunk_size_in_tokens=512,
|
||||
chunk_size_in_tokens=50,
|
||||
)
|
||||
|
||||
# Get the model being served
|
||||
llm = next(m for m in client.models.list() if m.model_type == "llm")
|
||||
model = llm.identifier
|
||||
|
||||
# Create RAG agent
|
||||
ragagent = Agent(
|
||||
agent = Agent(
|
||||
client,
|
||||
model=model,
|
||||
instructions="You are a helpful assistant. Use the RAG tool to answer questions as needed.",
|
||||
model=model_id,
|
||||
instructions="You are a helpful assistant",
|
||||
tools=[
|
||||
{
|
||||
"name": "builtin::rag/knowledge_search",
|
||||
|
|
@ -417,39 +68,54 @@ ragagent = Agent(
|
|||
],
|
||||
)
|
||||
|
||||
s_id = ragagent.create_session(session_name=f"s{uuid.uuid4().hex}")
|
||||
prompt = "How do you do great work?"
|
||||
print("prompt>", prompt)
|
||||
|
||||
turns = ["what is torchtune", "tell me about dora"]
|
||||
response = agent.create_turn(
|
||||
messages=[{"role": "user", "content": prompt}],
|
||||
session_id=agent.create_session("rag_session"),
|
||||
stream=True,
|
||||
)
|
||||
|
||||
for t in turns:
|
||||
print("user>", t)
|
||||
stream = ragagent.create_turn(
|
||||
messages=[{"role": "user", "content": t}], session_id=s_id, stream=True
|
||||
)
|
||||
for event in AgentEventLogger().log(stream):
|
||||
event.print()
|
||||
for log in AgentEventLogger().log(response):
|
||||
log.print()
|
||||
```
|
||||
Run the script:
|
||||
We will use `uv` to run the script
|
||||
```
|
||||
python rag_agent.py
|
||||
uv run --with llama-stack-client demo_script.py
|
||||
```
|
||||
:::{dropdown} `Sample output`
|
||||
And you should see output like below.
|
||||
```
|
||||
user> what is torchtune
|
||||
inference> [knowledge_search(query='TorchTune')]
|
||||
tool_execution> Tool:knowledge_search Args:{'query': 'TorchTune'}
|
||||
tool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\nBEGIN of knowledge_search tool results.\n', type='text'), TextContentItem(text='Result 1:\nDocument_id:num-1\nContent: conversational data, :func:`~torchtune.datasets.chat_dataset` seems to be a good fit. ..., type='text'), TextContentItem(text='END of knowledge_search tool results.\n', type='text')]
|
||||
inference> Here is a high-level overview of the text:
|
||||
rag_tool> Ingesting document: https://www.paulgraham.com/greatwork.html
|
||||
|
||||
**LoRA Finetuning with PyTorch Tune**
|
||||
prompt> How do you do great work?
|
||||
|
||||
PyTorch Tune provides a recipe for LoRA (Low-Rank Adaptation) finetuning, which is a technique to adapt pre-trained models to new tasks. The recipe uses the `lora_finetune_distributed` command.
|
||||
...
|
||||
Overall, DORA is a powerful reinforcement learning algorithm that can learn complex tasks from human demonstrations. However, it requires careful consideration of the challenges and limitations to achieve optimal results.
|
||||
inference> [knowledge_search(query="What is the key to doing great work")]
|
||||
|
||||
tool_execution> Tool:knowledge_search Args:{'query': 'What is the key to doing great work'}
|
||||
|
||||
tool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\nBEGIN of knowledge_search tool results.\n', type='text'), TextContentItem(text="Result 1:\nDocument_id:docum\nContent: work. Doing great work means doing something important\nso well that you expand people's ideas of what's possible. But\nthere's no threshold for importance. It's a matter of degree, and\noften hard to judge at the time anyway.\n", type='text'), TextContentItem(text="Result 2:\nDocument_id:docum\nContent: work. Doing great work means doing something important\nso well that you expand people's ideas of what's possible. But\nthere's no threshold for importance. It's a matter of degree, and\noften hard to judge at the time anyway.\n", type='text'), TextContentItem(text="Result 3:\nDocument_id:docum\nContent: work. Doing great work means doing something important\nso well that you expand people's ideas of what's possible. But\nthere's no threshold for importance. It's a matter of degree, and\noften hard to judge at the time anyway.\n", type='text'), TextContentItem(text="Result 4:\nDocument_id:docum\nContent: work. Doing great work means doing something important\nso well that you expand people's ideas of what's possible. But\nthere's no threshold for importance. It's a matter of degree, and\noften hard to judge at the time anyway.\n", type='text'), TextContentItem(text="Result 5:\nDocument_id:docum\nContent: work. Doing great work means doing something important\nso well that you expand people's ideas of what's possible. But\nthere's no threshold for importance. It's a matter of degree, and\noften hard to judge at the time anyway.\n", type='text'), TextContentItem(text='END of knowledge_search tool results.\n', type='text')]
|
||||
|
||||
inference> Based on the search results, it seems that doing great work means doing something important so well that you expand people's ideas of what's possible. However, there is no clear threshold for importance, and it can be difficult to judge at the time.
|
||||
|
||||
To further clarify, I would suggest that doing great work involves:
|
||||
|
||||
* Completing tasks with high quality and attention to detail
|
||||
* Expanding on existing knowledge or ideas
|
||||
* Making a positive impact on others through your work
|
||||
* Striving for excellence and continuous improvement
|
||||
|
||||
Ultimately, great work is about making a meaningful contribution and leaving a lasting impression.
|
||||
```
|
||||
:::
|
||||
Congratulations! You've successfully built your first RAG application using Llama Stack! 🎉🥳
|
||||
|
||||
## Next Steps
|
||||
- Go through the [Getting Started Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb)
|
||||
- Checkout more [Notebooks on GitHub](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks)
|
||||
- See [References](../references/index.md) for more details about the llama CLI and Python SDK
|
||||
- For example applications and more detailed tutorials, visit our [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository.
|
||||
|
||||
Now you're ready to dive deeper into Llama Stack!
|
||||
- Explore the [Detailed Tutorial](./detailed_tutorial.md).
|
||||
- Try the [Getting Started Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb).
|
||||
- Browse more [Notebooks on GitHub](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks).
|
||||
- Learn about Llama Stack [Concepts](../concepts/index.md).
|
||||
- Discover how to [Build Llama Stacks](../distributions/index.md).
|
||||
- Refer to our [References](../references/index.md) for details on the Llama CLI and Python SDK.
|
||||
- Check out the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository for example applications and tutorials.
|
||||
|
|
|
|||
|
|
@ -1,3 +1,5 @@
|
|||
# Llama Stack
|
||||
Welcome to Llama Stack, the open-source framework for building generative AI applications.
|
||||
```{admonition} Llama 4 is here!
|
||||
:class: tip
|
||||
|
||||
|
|
@ -9,7 +11,6 @@ Check out [Getting Started with Llama 4](https://colab.research.google.com/githu
|
|||
Llama Stack {{ llama_stack_version }} is now available! See the {{ llama_stack_version_link }} for more details.
|
||||
```
|
||||
|
||||
# Llama Stack
|
||||
|
||||
## What is Llama Stack?
|
||||
|
||||
|
|
@ -98,8 +99,9 @@ A number of "adapters" are available for some popular Inference and Vector Store
|
|||
:maxdepth: 3
|
||||
|
||||
self
|
||||
introduction/index
|
||||
getting_started/index
|
||||
getting_started/detailed_tutorial
|
||||
introduction/index
|
||||
concepts/index
|
||||
providers/index
|
||||
distributions/index
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
# Providers Overview
|
||||
|
||||
The goal of Llama Stack is to build an ecosystem where users can easily swap out different implementations for the same API. Examples for these include:
|
||||
- LLM inference providers (e.g., Fireworks, Together, AWS Bedrock, Groq, Cerebras, SambaNova, vLLM, etc.),
|
||||
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, Milvus, FAISS, PGVector, etc.),
|
||||
- LLM inference providers (e.g., Ollama, Fireworks, Together, AWS Bedrock, Groq, Cerebras, SambaNova, vLLM, etc.),
|
||||
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, Milvus, FAISS, PGVector, SQLite-Vec, etc.),
|
||||
- Safety providers (e.g., Meta's Llama Guard, AWS Bedrock Guardrails, etc.)
|
||||
|
||||
Providers come in two flavors:
|
||||
|
|
|
|||
|
|
@ -442,6 +442,217 @@ class EmbeddingsResponse(BaseModel):
|
|||
embeddings: List[List[float]]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIUserMessageParam(BaseModel):
|
||||
"""A message from the user in an OpenAI-compatible chat completion request.
|
||||
|
||||
:param role: Must be "user" to identify this as a user message
|
||||
:param content: The content of the message, which can include text and other media
|
||||
:param name: (Optional) The name of the user message participant.
|
||||
"""
|
||||
|
||||
role: Literal["user"] = "user"
|
||||
content: InterleavedContent
|
||||
name: Optional[str] = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAISystemMessageParam(BaseModel):
|
||||
"""A system message providing instructions or context to the model.
|
||||
|
||||
:param role: Must be "system" to identify this as a system message
|
||||
:param content: The content of the "system prompt". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions).
|
||||
:param name: (Optional) The name of the system message participant.
|
||||
"""
|
||||
|
||||
role: Literal["system"] = "system"
|
||||
content: InterleavedContent
|
||||
name: Optional[str] = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIAssistantMessageParam(BaseModel):
|
||||
"""A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
|
||||
|
||||
:param role: Must be "assistant" to identify this as the model's response
|
||||
:param content: The content of the model's response
|
||||
:param name: (Optional) The name of the assistant message participant.
|
||||
:param tool_calls: List of tool calls. Each tool call is a ToolCall object.
|
||||
"""
|
||||
|
||||
role: Literal["assistant"] = "assistant"
|
||||
content: InterleavedContent
|
||||
name: Optional[str] = None
|
||||
tool_calls: Optional[List[ToolCall]] = Field(default_factory=list)
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIToolMessageParam(BaseModel):
|
||||
"""A message representing the result of a tool invocation in an OpenAI-compatible chat completion request.
|
||||
|
||||
:param role: Must be "tool" to identify this as a tool response
|
||||
:param tool_call_id: Unique identifier for the tool call this response is for
|
||||
:param content: The response content from the tool
|
||||
"""
|
||||
|
||||
role: Literal["tool"] = "tool"
|
||||
tool_call_id: str
|
||||
content: InterleavedContent
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIDeveloperMessageParam(BaseModel):
|
||||
"""A message from the developer in an OpenAI-compatible chat completion request.
|
||||
|
||||
:param role: Must be "developer" to identify this as a developer message
|
||||
:param content: The content of the developer message
|
||||
:param name: (Optional) The name of the developer message participant.
|
||||
"""
|
||||
|
||||
role: Literal["developer"] = "developer"
|
||||
content: InterleavedContent
|
||||
name: Optional[str] = None
|
||||
|
||||
|
||||
OpenAIMessageParam = Annotated[
|
||||
Union[
|
||||
OpenAIUserMessageParam,
|
||||
OpenAISystemMessageParam,
|
||||
OpenAIAssistantMessageParam,
|
||||
OpenAIToolMessageParam,
|
||||
OpenAIDeveloperMessageParam,
|
||||
],
|
||||
Field(discriminator="role"),
|
||||
]
|
||||
register_schema(OpenAIMessageParam, name="OpenAIMessageParam")
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAITopLogProb(BaseModel):
|
||||
"""The top log probability for a token from an OpenAI-compatible chat completion response.
|
||||
|
||||
:token: The token
|
||||
:bytes: (Optional) The bytes for the token
|
||||
:logprob: The log probability of the token
|
||||
"""
|
||||
|
||||
token: str
|
||||
bytes: Optional[List[int]] = None
|
||||
logprob: float
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAITokenLogProb(BaseModel):
|
||||
"""The log probability for a token from an OpenAI-compatible chat completion response.
|
||||
|
||||
:token: The token
|
||||
:bytes: (Optional) The bytes for the token
|
||||
:logprob: The log probability of the token
|
||||
:top_logprobs: The top log probabilities for the token
|
||||
"""
|
||||
|
||||
token: str
|
||||
bytes: Optional[List[int]] = None
|
||||
logprob: float
|
||||
top_logprobs: List[OpenAITopLogProb]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIChoiceLogprobs(BaseModel):
|
||||
"""The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response.
|
||||
|
||||
:content: (Optional) The log probabilities for the tokens in the message
|
||||
:refusal: (Optional) The log probabilities for the tokens in the message
|
||||
"""
|
||||
|
||||
content: Optional[List[OpenAITokenLogProb]] = None
|
||||
refusal: Optional[List[OpenAITokenLogProb]] = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIChoice(BaseModel):
|
||||
"""A choice from an OpenAI-compatible chat completion response.
|
||||
|
||||
:param message: The message from the model
|
||||
:param finish_reason: The reason the model stopped generating
|
||||
:index: The index of the choice
|
||||
:logprobs: (Optional) The log probabilities for the tokens in the message
|
||||
"""
|
||||
|
||||
message: OpenAIMessageParam
|
||||
finish_reason: str
|
||||
index: int
|
||||
logprobs: Optional[OpenAIChoiceLogprobs] = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIChatCompletion(BaseModel):
|
||||
"""Response from an OpenAI-compatible chat completion request.
|
||||
|
||||
:param id: The ID of the chat completion
|
||||
:param choices: List of choices
|
||||
:param object: The object type, which will be "chat.completion"
|
||||
:param created: The Unix timestamp in seconds when the chat completion was created
|
||||
:param model: The model that was used to generate the chat completion
|
||||
"""
|
||||
|
||||
id: str
|
||||
choices: List[OpenAIChoice]
|
||||
object: Literal["chat.completion"] = "chat.completion"
|
||||
created: int
|
||||
model: str
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAICompletionLogprobs(BaseModel):
|
||||
"""The log probabilities for the tokens in the message from an OpenAI-compatible completion response.
|
||||
|
||||
:text_offset: (Optional) The offset of the token in the text
|
||||
:token_logprobs: (Optional) The log probabilities for the tokens
|
||||
:tokens: (Optional) The tokens
|
||||
:top_logprobs: (Optional) The top log probabilities for the tokens
|
||||
"""
|
||||
|
||||
text_offset: Optional[List[int]] = None
|
||||
token_logprobs: Optional[List[float]] = None
|
||||
tokens: Optional[List[str]] = None
|
||||
top_logprobs: Optional[List[Dict[str, float]]] = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAICompletionChoice(BaseModel):
|
||||
"""A choice from an OpenAI-compatible completion response.
|
||||
|
||||
:finish_reason: The reason the model stopped generating
|
||||
:text: The text of the choice
|
||||
:index: The index of the choice
|
||||
:logprobs: (Optional) The log probabilities for the tokens in the choice
|
||||
"""
|
||||
|
||||
finish_reason: str
|
||||
text: str
|
||||
index: int
|
||||
logprobs: Optional[OpenAIChoiceLogprobs] = None
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAICompletion(BaseModel):
|
||||
"""Response from an OpenAI-compatible completion request.
|
||||
|
||||
:id: The ID of the completion
|
||||
:choices: List of choices
|
||||
:created: The Unix timestamp in seconds when the completion was created
|
||||
:model: The model that was used to generate the completion
|
||||
:object: The object type, which will be "text_completion"
|
||||
"""
|
||||
|
||||
id: str
|
||||
choices: List[OpenAICompletionChoice]
|
||||
created: int
|
||||
model: str
|
||||
object: Literal["text_completion"] = "text_completion"
|
||||
|
||||
|
||||
class ModelStore(Protocol):
|
||||
async def get_model(self, identifier: str) -> Model: ...
|
||||
|
||||
|
|
@ -564,3 +775,105 @@ class Inference(Protocol):
|
|||
:returns: An array of embeddings, one for each content. Each embedding is a list of floats. The dimensionality of the embedding is model-specific; you can check model metadata using /models/{model_id}
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/completions", method="POST")
|
||||
async def openai_completion(
|
||||
self,
|
||||
# Standard OpenAI completion parameters
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
# vLLM-specific parameters
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
"""Generate an OpenAI-compatible completion for the given prompt using the specified model.
|
||||
|
||||
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
|
||||
:param prompt: The prompt to generate a completion for
|
||||
:param best_of: (Optional) The number of completions to generate
|
||||
:param echo: (Optional) Whether to echo the prompt
|
||||
:param frequency_penalty: (Optional) The penalty for repeated tokens
|
||||
:param logit_bias: (Optional) The logit bias to use
|
||||
:param logprobs: (Optional) The log probabilities to use
|
||||
:param max_tokens: (Optional) The maximum number of tokens to generate
|
||||
:param n: (Optional) The number of completions to generate
|
||||
:param presence_penalty: (Optional) The penalty for repeated tokens
|
||||
:param seed: (Optional) The seed to use
|
||||
:param stop: (Optional) The stop tokens to use
|
||||
:param stream: (Optional) Whether to stream the response
|
||||
:param stream_options: (Optional) The stream options to use
|
||||
:param temperature: (Optional) The temperature to use
|
||||
:param top_p: (Optional) The top p to use
|
||||
:param user: (Optional) The user to use
|
||||
"""
|
||||
...
|
||||
|
||||
@webmethod(route="/openai/v1/chat/completions", method="POST")
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
"""Generate an OpenAI-compatible chat completion for the given messages using the specified model.
|
||||
|
||||
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
|
||||
:param messages: List of messages in the conversation
|
||||
:param frequency_penalty: (Optional) The penalty for repeated tokens
|
||||
:param function_call: (Optional) The function call to use
|
||||
:param functions: (Optional) List of functions to use
|
||||
:param logit_bias: (Optional) The logit bias to use
|
||||
:param logprobs: (Optional) The log probabilities to use
|
||||
:param max_completion_tokens: (Optional) The maximum number of tokens to generate
|
||||
:param max_tokens: (Optional) The maximum number of tokens to generate
|
||||
:param n: (Optional) The number of completions to generate
|
||||
:param parallel_tool_calls: (Optional) Whether to parallelize tool calls
|
||||
:param presence_penalty: (Optional) The penalty for repeated tokens
|
||||
:param response_format: (Optional) The response format to use
|
||||
:param seed: (Optional) The seed to use
|
||||
:param stop: (Optional) The stop tokens to use
|
||||
:param stream: (Optional) Whether to stream the response
|
||||
:param stream_options: (Optional) The stream options to use
|
||||
:param temperature: (Optional) The temperature to use
|
||||
:param tool_choice: (Optional) The tool choice to use
|
||||
:param tools: (Optional) The tools to use
|
||||
:param top_logprobs: (Optional) The top log probabilities to use
|
||||
:param top_p: (Optional) The top p to use
|
||||
:param user: (Optional) The user to use
|
||||
"""
|
||||
...
|
||||
|
|
|
|||
|
|
@ -56,12 +56,35 @@ class ListModelsResponse(BaseModel):
|
|||
data: List[Model]
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class OpenAIModel(BaseModel):
|
||||
"""A model from OpenAI.
|
||||
|
||||
:id: The ID of the model
|
||||
:object: The object type, which will be "model"
|
||||
:created: The Unix timestamp in seconds when the model was created
|
||||
:owned_by: The owner of the model
|
||||
"""
|
||||
|
||||
id: str
|
||||
object: Literal["model"] = "model"
|
||||
created: int
|
||||
owned_by: str
|
||||
|
||||
|
||||
class OpenAIListModelsResponse(BaseModel):
|
||||
data: List[OpenAIModel]
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
@trace_protocol
|
||||
class Models(Protocol):
|
||||
@webmethod(route="/models", method="GET")
|
||||
async def list_models(self) -> ListModelsResponse: ...
|
||||
|
||||
@webmethod(route="/openai/v1/models", method="GET")
|
||||
async def openai_list_models(self) -> OpenAIListModelsResponse: ...
|
||||
|
||||
@webmethod(route="/models/{model_id:path}", method="GET")
|
||||
async def get_model(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -35,6 +35,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.apis.models import Model, ModelType
|
||||
from llama_stack.apis.safety import RunShieldResponse, Safety
|
||||
from llama_stack.apis.scoring import (
|
||||
|
|
@ -419,6 +420,126 @@ class InferenceRouter(Inference):
|
|||
task_type=task_type,
|
||||
)
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
logger.debug(
|
||||
f"InferenceRouter.openai_completion: {model=}, {stream=}, {prompt=}",
|
||||
)
|
||||
model_obj = await self.routing_table.get_model(model)
|
||||
if model_obj is None:
|
||||
raise ValueError(f"Model '{model}' not found")
|
||||
if model_obj.model_type == ModelType.embedding:
|
||||
raise ValueError(f"Model '{model}' is an embedding model and does not support completions")
|
||||
|
||||
params = dict(
|
||||
model=model_obj.identifier,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
guided_choice=guided_choice,
|
||||
prompt_logprobs=prompt_logprobs,
|
||||
)
|
||||
|
||||
provider = self.routing_table.get_provider_impl(model_obj.identifier)
|
||||
return await provider.openai_completion(**params)
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
logger.debug(
|
||||
f"InferenceRouter.openai_chat_completion: {model=}, {stream=}, {messages=}",
|
||||
)
|
||||
model_obj = await self.routing_table.get_model(model)
|
||||
if model_obj is None:
|
||||
raise ValueError(f"Model '{model}' not found")
|
||||
if model_obj.model_type == ModelType.embedding:
|
||||
raise ValueError(f"Model '{model}' is an embedding model and does not support chat completions")
|
||||
|
||||
params = dict(
|
||||
model=model_obj.identifier,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
|
||||
provider = self.routing_table.get_provider_impl(model_obj.identifier)
|
||||
return await provider.openai_chat_completion(**params)
|
||||
|
||||
|
||||
class SafetyRouter(Safety):
|
||||
def __init__(
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
import time
|
||||
import uuid
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
|
|
@ -23,7 +24,7 @@ from llama_stack.apis.datasets import (
|
|||
RowsDataSource,
|
||||
URIDataSource,
|
||||
)
|
||||
from llama_stack.apis.models import ListModelsResponse, Model, Models, ModelType
|
||||
from llama_stack.apis.models import ListModelsResponse, Model, Models, ModelType, OpenAIListModelsResponse, OpenAIModel
|
||||
from llama_stack.apis.resource import ResourceType
|
||||
from llama_stack.apis.scoring_functions import (
|
||||
ListScoringFunctionsResponse,
|
||||
|
|
@ -254,6 +255,19 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
|
|||
async def list_models(self) -> ListModelsResponse:
|
||||
return ListModelsResponse(data=await self.get_all_with_type("model"))
|
||||
|
||||
async def openai_list_models(self) -> OpenAIListModelsResponse:
|
||||
models = await self.get_all_with_type("model")
|
||||
openai_models = [
|
||||
OpenAIModel(
|
||||
id=model.identifier,
|
||||
object="model",
|
||||
created=int(time.time()),
|
||||
owned_by="llama_stack",
|
||||
)
|
||||
for model in models
|
||||
]
|
||||
return OpenAIListModelsResponse(data=openai_models)
|
||||
|
||||
async def get_model(self, model_id: str) -> Model:
|
||||
model = await self.get_object_by_identifier("model", model_id)
|
||||
if model is None:
|
||||
|
|
|
|||
|
|
@ -96,7 +96,10 @@ async def register_resources(run_config: StackRunConfig, impls: Dict[Api, Any]):
|
|||
|
||||
method = getattr(impls[api], register_method)
|
||||
for obj in objects:
|
||||
await method(**obj.model_dump())
|
||||
# we want to maintain the type information in arguments to method.
|
||||
# instead of method(**obj.model_dump()), which may convert a typed attr to a dict,
|
||||
# we use model_dump() to find all the attrs and then getattr to get the still typed value.
|
||||
await method(**{k: getattr(obj, k) for k in obj.model_dump().keys()})
|
||||
|
||||
method = getattr(impls[api], list_method)
|
||||
response = await method()
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@ VIRTUAL_ENV=${VIRTUAL_ENV:-}
|
|||
set -euo pipefail
|
||||
|
||||
RED='\033[0;31m'
|
||||
GREEN='\033[0;32m'
|
||||
NC='\033[0m' # No Color
|
||||
|
||||
error_handler() {
|
||||
|
|
@ -73,7 +74,7 @@ done
|
|||
PYTHON_BINARY="python"
|
||||
case "$env_type" in
|
||||
"venv")
|
||||
if [ -n "$VIRTUAL_ENV" && "$VIRTUAL_ENV" == "$env_path_or_name" ]; then
|
||||
if [ -n "$VIRTUAL_ENV" ] && [ "$VIRTUAL_ENV" == "$env_path_or_name" ]; then
|
||||
echo -e "${GREEN}Virtual environment already activated${NC}" >&2
|
||||
else
|
||||
# Activate virtual environment
|
||||
|
|
|
|||
|
|
@ -9,6 +9,7 @@ import uuid
|
|||
import streamlit as st
|
||||
from llama_stack_client import Agent, AgentEventLogger, RAGDocument
|
||||
|
||||
from llama_stack.apis.common.content_types import ToolCallDelta
|
||||
from llama_stack.distribution.ui.modules.api import llama_stack_api
|
||||
from llama_stack.distribution.ui.modules.utils import data_url_from_file
|
||||
|
||||
|
|
@ -16,9 +17,16 @@ from llama_stack.distribution.ui.modules.utils import data_url_from_file
|
|||
def rag_chat_page():
|
||||
st.title("🦙 RAG")
|
||||
|
||||
def reset_agent_and_chat():
|
||||
st.session_state.clear()
|
||||
st.cache_resource.clear()
|
||||
|
||||
def should_disable_input():
|
||||
return "displayed_messages" in st.session_state and len(st.session_state.displayed_messages) > 0
|
||||
|
||||
with st.sidebar:
|
||||
# File/Directory Upload Section
|
||||
st.subheader("Upload Documents")
|
||||
st.subheader("Upload Documents", divider=True)
|
||||
uploaded_files = st.file_uploader(
|
||||
"Upload file(s) or directory",
|
||||
accept_multiple_files=True,
|
||||
|
|
@ -29,11 +37,11 @@ def rag_chat_page():
|
|||
st.success(f"Successfully uploaded {len(uploaded_files)} files")
|
||||
# Add memory bank name input field
|
||||
vector_db_name = st.text_input(
|
||||
"Vector Database Name",
|
||||
"Document Collection Name",
|
||||
value="rag_vector_db",
|
||||
help="Enter a unique identifier for this vector database",
|
||||
help="Enter a unique identifier for this document collection",
|
||||
)
|
||||
if st.button("Create Vector Database"):
|
||||
if st.button("Create Document Collection"):
|
||||
documents = [
|
||||
RAGDocument(
|
||||
document_id=uploaded_file.name,
|
||||
|
|
@ -64,26 +72,45 @@ def rag_chat_page():
|
|||
)
|
||||
st.success("Vector database created successfully!")
|
||||
|
||||
st.subheader("Configure Agent")
|
||||
st.subheader("RAG Parameters", divider=True)
|
||||
|
||||
rag_mode = st.radio(
|
||||
"RAG mode",
|
||||
["Direct", "Agent-based"],
|
||||
captions=[
|
||||
"RAG is performed by directly retrieving the information and augmenting the user query",
|
||||
"RAG is performed by an agent activating a dedicated knowledge search tool.",
|
||||
],
|
||||
on_change=reset_agent_and_chat,
|
||||
disabled=should_disable_input(),
|
||||
)
|
||||
|
||||
# select memory banks
|
||||
vector_dbs = llama_stack_api.client.vector_dbs.list()
|
||||
vector_dbs = [vector_db.identifier for vector_db in vector_dbs]
|
||||
selected_vector_dbs = st.multiselect(
|
||||
"Select Vector Databases",
|
||||
vector_dbs,
|
||||
label="Select Document Collections to use in RAG queries",
|
||||
options=vector_dbs,
|
||||
on_change=reset_agent_and_chat,
|
||||
disabled=should_disable_input(),
|
||||
)
|
||||
|
||||
st.subheader("Inference Parameters", divider=True)
|
||||
available_models = llama_stack_api.client.models.list()
|
||||
available_models = [model.identifier for model in available_models if model.model_type == "llm"]
|
||||
selected_model = st.selectbox(
|
||||
"Choose a model",
|
||||
available_models,
|
||||
label="Choose a model",
|
||||
options=available_models,
|
||||
index=0,
|
||||
on_change=reset_agent_and_chat,
|
||||
disabled=should_disable_input(),
|
||||
)
|
||||
system_prompt = st.text_area(
|
||||
"System Prompt",
|
||||
value="You are a helpful assistant. ",
|
||||
help="Initial instructions given to the AI to set its behavior and context",
|
||||
on_change=reset_agent_and_chat,
|
||||
disabled=should_disable_input(),
|
||||
)
|
||||
temperature = st.slider(
|
||||
"Temperature",
|
||||
|
|
@ -92,6 +119,8 @@ def rag_chat_page():
|
|||
value=0.0,
|
||||
step=0.1,
|
||||
help="Controls the randomness of the response. Higher values make the output more creative and unexpected, lower values make it more conservative and predictable",
|
||||
on_change=reset_agent_and_chat,
|
||||
disabled=should_disable_input(),
|
||||
)
|
||||
|
||||
top_p = st.slider(
|
||||
|
|
@ -100,19 +129,23 @@ def rag_chat_page():
|
|||
max_value=1.0,
|
||||
value=0.95,
|
||||
step=0.1,
|
||||
on_change=reset_agent_and_chat,
|
||||
disabled=should_disable_input(),
|
||||
)
|
||||
|
||||
# Add clear chat button to sidebar
|
||||
if st.button("Clear Chat", use_container_width=True):
|
||||
st.session_state.clear()
|
||||
st.cache_resource.clear()
|
||||
reset_agent_and_chat()
|
||||
st.rerun()
|
||||
|
||||
# Chat Interface
|
||||
if "messages" not in st.session_state:
|
||||
st.session_state.messages = []
|
||||
if "displayed_messages" not in st.session_state:
|
||||
st.session_state.displayed_messages = []
|
||||
|
||||
# Display chat history
|
||||
for message in st.session_state.messages:
|
||||
for message in st.session_state.displayed_messages:
|
||||
with st.chat_message(message["role"]):
|
||||
st.markdown(message["content"])
|
||||
|
||||
|
|
@ -144,22 +177,18 @@ def rag_chat_page():
|
|||
],
|
||||
)
|
||||
|
||||
agent = create_agent()
|
||||
if rag_mode == "Agent-based":
|
||||
agent = create_agent()
|
||||
if "agent_session_id" not in st.session_state:
|
||||
st.session_state["agent_session_id"] = agent.create_session(session_name=f"rag_demo_{uuid.uuid4()}")
|
||||
|
||||
if "agent_session_id" not in st.session_state:
|
||||
st.session_state["agent_session_id"] = agent.create_session(session_name=f"rag_demo_{uuid.uuid4()}")
|
||||
session_id = st.session_state["agent_session_id"]
|
||||
|
||||
session_id = st.session_state["agent_session_id"]
|
||||
|
||||
# Chat input
|
||||
if prompt := st.chat_input("Ask a question about your documents"):
|
||||
def agent_process_prompt(prompt):
|
||||
# Add user message to chat history
|
||||
st.session_state.messages.append({"role": "user", "content": prompt})
|
||||
|
||||
# Display user message
|
||||
with st.chat_message("user"):
|
||||
st.markdown(prompt)
|
||||
|
||||
# Send the prompt to the agent
|
||||
response = agent.create_turn(
|
||||
messages=[
|
||||
{
|
||||
|
|
@ -187,6 +216,79 @@ def rag_chat_page():
|
|||
message_placeholder.markdown(full_response)
|
||||
|
||||
st.session_state.messages.append({"role": "assistant", "content": full_response})
|
||||
st.session_state.displayed_messages.append({"role": "assistant", "content": full_response})
|
||||
|
||||
def direct_process_prompt(prompt):
|
||||
# Add the system prompt in the beginning of the conversation
|
||||
if len(st.session_state.messages) == 0:
|
||||
st.session_state.messages.append({"role": "system", "content": system_prompt})
|
||||
|
||||
# Query the vector DB
|
||||
rag_response = llama_stack_api.client.tool_runtime.rag_tool.query(
|
||||
content=prompt, vector_db_ids=list(selected_vector_dbs)
|
||||
)
|
||||
prompt_context = rag_response.content
|
||||
|
||||
with st.chat_message("assistant"):
|
||||
retrieval_message_placeholder = st.empty()
|
||||
message_placeholder = st.empty()
|
||||
full_response = ""
|
||||
retrieval_response = ""
|
||||
|
||||
# Display the retrieved content
|
||||
retrieval_response += str(prompt_context)
|
||||
retrieval_message_placeholder.info(retrieval_response)
|
||||
|
||||
# Construct the extended prompt
|
||||
extended_prompt = f"Please answer the following query using the context below.\n\nCONTEXT:\n{prompt_context}\n\nQUERY:\n{prompt}"
|
||||
|
||||
# Run inference directly
|
||||
st.session_state.messages.append({"role": "user", "content": extended_prompt})
|
||||
response = llama_stack_api.client.inference.chat_completion(
|
||||
messages=st.session_state.messages,
|
||||
model_id=selected_model,
|
||||
sampling_params={
|
||||
"strategy": strategy,
|
||||
},
|
||||
stream=True,
|
||||
)
|
||||
|
||||
# Display assistant response
|
||||
for chunk in response:
|
||||
response_delta = chunk.event.delta
|
||||
if isinstance(response_delta, ToolCallDelta):
|
||||
retrieval_response += response_delta.tool_call.replace("====", "").strip()
|
||||
retrieval_message_placeholder.info(retrieval_response)
|
||||
else:
|
||||
full_response += chunk.event.delta.text
|
||||
message_placeholder.markdown(full_response + "▌")
|
||||
message_placeholder.markdown(full_response)
|
||||
|
||||
response_dict = {"role": "assistant", "content": full_response, "stop_reason": "end_of_message"}
|
||||
st.session_state.messages.append(response_dict)
|
||||
st.session_state.displayed_messages.append(response_dict)
|
||||
|
||||
# Chat input
|
||||
if prompt := st.chat_input("Ask a question about your documents"):
|
||||
# Add user message to chat history
|
||||
st.session_state.displayed_messages.append({"role": "user", "content": prompt})
|
||||
|
||||
# Display user message
|
||||
with st.chat_message("user"):
|
||||
st.markdown(prompt)
|
||||
|
||||
# store the prompt to process it after page refresh
|
||||
st.session_state.prompt = prompt
|
||||
|
||||
# force page refresh to disable the settings widgets
|
||||
st.rerun()
|
||||
|
||||
if "prompt" in st.session_state and st.session_state.prompt is not None:
|
||||
if rag_mode == "Agent-based":
|
||||
agent_process_prompt(st.session_state.prompt)
|
||||
else: # rag_mode == "Direct"
|
||||
direct_process_prompt(st.session_state.prompt)
|
||||
st.session_state.prompt = None
|
||||
|
||||
|
||||
rag_chat_page()
|
||||
|
|
|
|||
|
|
@ -54,6 +54,10 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
ModelRegistryHelper,
|
||||
build_hf_repo_model_entry,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.prompt_adapter import (
|
||||
augment_content_with_response_format_prompt,
|
||||
chat_completion_request_to_messages,
|
||||
|
|
@ -79,6 +83,8 @@ def llama4_builder_fn(config: MetaReferenceInferenceConfig, model_id: str, llama
|
|||
|
||||
|
||||
class MetaReferenceInferenceImpl(
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
SentenceTransformerEmbeddingMixin,
|
||||
Inference,
|
||||
ModelsProtocolPrivate,
|
||||
|
|
|
|||
|
|
@ -23,6 +23,10 @@ from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
|
|||
from llama_stack.providers.utils.inference.embedding_mixin import (
|
||||
SentenceTransformerEmbeddingMixin,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
)
|
||||
|
||||
from .config import SentenceTransformersInferenceConfig
|
||||
|
||||
|
|
@ -30,6 +34,8 @@ log = logging.getLogger(__name__)
|
|||
|
||||
|
||||
class SentenceTransformersInferenceImpl(
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
SentenceTransformerEmbeddingMixin,
|
||||
Inference,
|
||||
ModelsProtocolPrivate,
|
||||
|
|
|
|||
|
|
@ -66,8 +66,10 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
ModelsProtocolPrivate,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompatCompletionChoice,
|
||||
OpenAICompatCompletionResponse,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
get_stop_reason,
|
||||
process_chat_completion_stream_response,
|
||||
)
|
||||
|
|
@ -172,7 +174,12 @@ def _convert_sampling_params(
|
|||
return vllm_sampling_params
|
||||
|
||||
|
||||
class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
|
||||
class VLLMInferenceImpl(
|
||||
Inference,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
ModelsProtocolPrivate,
|
||||
):
|
||||
"""
|
||||
vLLM-based inference model adapter for Llama Stack with support for multiple models.
|
||||
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ META_REFERENCE_DEPS = [
|
|||
"zmq",
|
||||
"lm-format-enforcer",
|
||||
"sentence-transformers",
|
||||
"torchao==0.5.0",
|
||||
"torchao==0.8.0",
|
||||
"fbgemm-gpu-genai==1.1.2",
|
||||
]
|
||||
|
||||
|
|
|
|||
|
|
@ -36,8 +36,10 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
ModelRegistryHelper,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompatCompletionChoice,
|
||||
OpenAICompatCompletionResponse,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
get_sampling_strategy_options,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
|
|
@ -51,7 +53,12 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
from .models import MODEL_ENTRIES
|
||||
|
||||
|
||||
class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
|
||||
class BedrockInferenceAdapter(
|
||||
ModelRegistryHelper,
|
||||
Inference,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
):
|
||||
def __init__(self, config: BedrockConfig) -> None:
|
||||
ModelRegistryHelper.__init__(self, MODEL_ENTRIES)
|
||||
self._config = config
|
||||
|
|
|
|||
|
|
@ -34,6 +34,8 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
ModelRegistryHelper,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
get_sampling_options,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
|
|
@ -49,7 +51,12 @@ from .config import CerebrasImplConfig
|
|||
from .models import MODEL_ENTRIES
|
||||
|
||||
|
||||
class CerebrasInferenceAdapter(ModelRegistryHelper, Inference):
|
||||
class CerebrasInferenceAdapter(
|
||||
ModelRegistryHelper,
|
||||
Inference,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
):
|
||||
def __init__(self, config: CerebrasImplConfig) -> None:
|
||||
ModelRegistryHelper.__init__(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -34,6 +34,8 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
build_hf_repo_model_entry,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
get_sampling_options,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
|
|
@ -56,7 +58,12 @@ model_entries = [
|
|||
]
|
||||
|
||||
|
||||
class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
|
||||
class DatabricksInferenceAdapter(
|
||||
ModelRegistryHelper,
|
||||
Inference,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
):
|
||||
def __init__(self, config: DatabricksImplConfig) -> None:
|
||||
ModelRegistryHelper.__init__(self, model_entries=model_entries)
|
||||
self.config = config
|
||||
|
|
|
|||
|
|
@ -4,9 +4,10 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import AsyncGenerator, List, Optional, Union
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
|
||||
|
||||
from fireworks.client import Fireworks
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
from llama_stack.apis.common.content_types import (
|
||||
InterleavedContent,
|
||||
|
|
@ -31,6 +32,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
|
|
@ -39,6 +41,7 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
convert_message_to_openai_dict,
|
||||
get_sampling_options,
|
||||
prepare_openai_completion_params,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
process_completion_response,
|
||||
|
|
@ -81,10 +84,16 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv
|
|||
)
|
||||
return provider_data.fireworks_api_key
|
||||
|
||||
def _get_base_url(self) -> str:
|
||||
return "https://api.fireworks.ai/inference/v1"
|
||||
|
||||
def _get_client(self) -> Fireworks:
|
||||
fireworks_api_key = self._get_api_key()
|
||||
return Fireworks(api_key=fireworks_api_key)
|
||||
|
||||
def _get_openai_client(self) -> AsyncOpenAI:
|
||||
return AsyncOpenAI(base_url=self._get_base_url(), api_key=self._get_api_key())
|
||||
|
||||
async def completion(
|
||||
self,
|
||||
model_id: str,
|
||||
|
|
@ -268,3 +277,101 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv
|
|||
|
||||
embeddings = [data.embedding for data in response.data]
|
||||
return EmbeddingsResponse(embeddings=embeddings)
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
model_obj = await self.model_store.get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
return await self._get_openai_client().completions.create(**params)
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
model_obj = await self.model_store.get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
return await self._get_openai_client().chat.completions.create(**params)
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
import logging
|
||||
import warnings
|
||||
from functools import lru_cache
|
||||
from typing import AsyncIterator, List, Optional, Union
|
||||
from typing import Any, AsyncIterator, Dict, List, Optional, Union
|
||||
|
||||
from openai import APIConnectionError, AsyncOpenAI, BadRequestError
|
||||
|
||||
|
|
@ -35,6 +35,7 @@ from llama_stack.apis.inference import (
|
|||
ToolConfig,
|
||||
ToolDefinition,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.models.llama.datatypes import ToolPromptFormat
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
|
|
@ -42,6 +43,7 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
convert_openai_chat_completion_choice,
|
||||
convert_openai_chat_completion_stream,
|
||||
prepare_openai_completion_params,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.prompt_adapter import content_has_media
|
||||
|
||||
|
|
@ -263,3 +265,111 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
|
|||
else:
|
||||
# we pass n=1 to get only one completion
|
||||
return convert_openai_chat_completion_choice(response.choices[0])
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
provider_model_id = self.get_provider_model_id(model)
|
||||
|
||||
params = await prepare_openai_completion_params(
|
||||
model=provider_model_id,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
|
||||
try:
|
||||
return await self._get_client(provider_model_id).completions.create(**params)
|
||||
except APIConnectionError as e:
|
||||
raise ConnectionError(f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}") from e
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
provider_model_id = self.get_provider_model_id(model)
|
||||
|
||||
params = await prepare_openai_completion_params(
|
||||
model=provider_model_id,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
|
||||
try:
|
||||
return await self._get_client(provider_model_id).chat.completions.create(**params)
|
||||
except APIConnectionError as e:
|
||||
raise ConnectionError(f"Failed to connect to NVIDIA NIM at {self._config.url}: {e}") from e
|
||||
|
|
|
|||
|
|
@ -5,10 +5,11 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
|
||||
from typing import Any, AsyncGenerator, List, Optional, Union
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
|
||||
|
||||
import httpx
|
||||
from ollama import AsyncClient
|
||||
from openai import AsyncOpenAI
|
||||
|
||||
from llama_stack.apis.common.content_types import (
|
||||
ImageContentItem,
|
||||
|
|
@ -38,6 +39,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.apis.models import Model, ModelType
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import ModelsProtocolPrivate
|
||||
|
|
@ -67,7 +69,10 @@ from .models import model_entries
|
|||
logger = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
||||
class OllamaInferenceAdapter(
|
||||
Inference,
|
||||
ModelsProtocolPrivate,
|
||||
):
|
||||
def __init__(self, url: str) -> None:
|
||||
self.register_helper = ModelRegistryHelper(model_entries)
|
||||
self.url = url
|
||||
|
|
@ -76,6 +81,10 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
def client(self) -> AsyncClient:
|
||||
return AsyncClient(host=self.url)
|
||||
|
||||
@property
|
||||
def openai_client(self) -> AsyncOpenAI:
|
||||
return AsyncOpenAI(base_url=f"{self.url}/v1", api_key="ollama")
|
||||
|
||||
async def initialize(self) -> None:
|
||||
logger.info(f"checking connectivity to Ollama at `{self.url}`...")
|
||||
try:
|
||||
|
|
@ -319,6 +328,115 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
|
||||
return model
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
if not isinstance(prompt, str):
|
||||
raise ValueError("Ollama does not support non-string prompts for completion")
|
||||
|
||||
model_obj = await self._get_model(model)
|
||||
params = {
|
||||
k: v
|
||||
for k, v in {
|
||||
"model": model_obj.provider_resource_id,
|
||||
"prompt": prompt,
|
||||
"best_of": best_of,
|
||||
"echo": echo,
|
||||
"frequency_penalty": frequency_penalty,
|
||||
"logit_bias": logit_bias,
|
||||
"logprobs": logprobs,
|
||||
"max_tokens": max_tokens,
|
||||
"n": n,
|
||||
"presence_penalty": presence_penalty,
|
||||
"seed": seed,
|
||||
"stop": stop,
|
||||
"stream": stream,
|
||||
"stream_options": stream_options,
|
||||
"temperature": temperature,
|
||||
"top_p": top_p,
|
||||
"user": user,
|
||||
}.items()
|
||||
if v is not None
|
||||
}
|
||||
return await self.openai_client.completions.create(**params) # type: ignore
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
model_obj = await self._get_model(model)
|
||||
params = {
|
||||
k: v
|
||||
for k, v in {
|
||||
"model": model_obj.provider_resource_id,
|
||||
"messages": messages,
|
||||
"frequency_penalty": frequency_penalty,
|
||||
"function_call": function_call,
|
||||
"functions": functions,
|
||||
"logit_bias": logit_bias,
|
||||
"logprobs": logprobs,
|
||||
"max_completion_tokens": max_completion_tokens,
|
||||
"max_tokens": max_tokens,
|
||||
"n": n,
|
||||
"parallel_tool_calls": parallel_tool_calls,
|
||||
"presence_penalty": presence_penalty,
|
||||
"response_format": response_format,
|
||||
"seed": seed,
|
||||
"stop": stop,
|
||||
"stream": stream,
|
||||
"stream_options": stream_options,
|
||||
"temperature": temperature,
|
||||
"tool_choice": tool_choice,
|
||||
"tools": tools,
|
||||
"top_logprobs": top_logprobs,
|
||||
"top_p": top_p,
|
||||
"user": user,
|
||||
}.items()
|
||||
if v is not None
|
||||
}
|
||||
return await self.openai_client.chat.completions.create(**params) # type: ignore
|
||||
|
||||
|
||||
async def convert_message_to_openai_dict_for_ollama(message: Message) -> List[dict]:
|
||||
async def _convert_content(content) -> dict:
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
|
||||
|
||||
from llama_stack_client import AsyncLlamaStackClient
|
||||
|
||||
|
|
@ -26,9 +26,11 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.apis.models import Model
|
||||
from llama_stack.distribution.library_client import convert_pydantic_to_json_value, convert_to_pydantic
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
|
||||
|
||||
from .config import PassthroughImplConfig
|
||||
|
||||
|
|
@ -201,6 +203,112 @@ class PassthroughInferenceAdapter(Inference):
|
|||
task_type=task_type,
|
||||
)
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
client = self._get_client()
|
||||
model_obj = await self.model_store.get_model(model)
|
||||
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
guided_choice=guided_choice,
|
||||
prompt_logprobs=prompt_logprobs,
|
||||
)
|
||||
|
||||
return await client.inference.openai_completion(**params)
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
client = self._get_client()
|
||||
model_obj = await self.model_store.get_model(model)
|
||||
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
|
||||
return await client.inference.openai_chat_completion(**params)
|
||||
|
||||
def cast_value_to_json_dict(self, request_params: Dict[str, Any]) -> Dict[str, Any]:
|
||||
json_params = {}
|
||||
for key, value in request_params.items():
|
||||
|
|
|
|||
|
|
@ -12,6 +12,8 @@ from llama_stack.apis.inference import * # noqa: F403
|
|||
# from llama_stack.providers.datatypes import ModelsProtocolPrivate
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
get_sampling_options,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
|
|
@ -38,7 +40,12 @@ RUNPOD_SUPPORTED_MODELS = {
|
|||
}
|
||||
|
||||
|
||||
class RunpodInferenceAdapter(ModelRegistryHelper, Inference):
|
||||
class RunpodInferenceAdapter(
|
||||
ModelRegistryHelper,
|
||||
Inference,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
):
|
||||
def __init__(self, config: RunpodImplConfig) -> None:
|
||||
ModelRegistryHelper.__init__(self, stack_to_provider_models_map=RUNPOD_SUPPORTED_MODELS)
|
||||
self.config = config
|
||||
|
|
|
|||
|
|
@ -40,8 +40,10 @@ from llama_stack.providers.utils.inference.model_registry import (
|
|||
build_hf_repo_model_entry,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompatCompletionChoice,
|
||||
OpenAICompatCompletionResponse,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
get_sampling_options,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
|
|
@ -69,7 +71,12 @@ def build_hf_repo_model_entries():
|
|||
]
|
||||
|
||||
|
||||
class _HfAdapter(Inference, ModelsProtocolPrivate):
|
||||
class _HfAdapter(
|
||||
Inference,
|
||||
OpenAIChatCompletionUnsupportedMixin,
|
||||
OpenAICompletionUnsupportedMixin,
|
||||
ModelsProtocolPrivate,
|
||||
):
|
||||
client: AsyncInferenceClient
|
||||
max_tokens: int
|
||||
model_id: str
|
||||
|
|
|
|||
|
|
@ -4,8 +4,9 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import AsyncGenerator, List, Optional, Union
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
|
||||
|
||||
from openai import AsyncOpenAI
|
||||
from together import AsyncTogether
|
||||
|
||||
from llama_stack.apis.common.content_types import (
|
||||
|
|
@ -30,12 +31,14 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
|
||||
from llama_stack.providers.utils.inference.openai_compat import (
|
||||
convert_message_to_openai_dict,
|
||||
get_sampling_options,
|
||||
prepare_openai_completion_params,
|
||||
process_chat_completion_response,
|
||||
process_chat_completion_stream_response,
|
||||
process_completion_response,
|
||||
|
|
@ -60,6 +63,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
|
|||
ModelRegistryHelper.__init__(self, MODEL_ENTRIES)
|
||||
self.config = config
|
||||
self._client = None
|
||||
self._openai_client = None
|
||||
|
||||
async def initialize(self) -> None:
|
||||
pass
|
||||
|
|
@ -110,6 +114,15 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
|
|||
self._client = AsyncTogether(api_key=together_api_key)
|
||||
return self._client
|
||||
|
||||
def _get_openai_client(self) -> AsyncOpenAI:
|
||||
if not self._openai_client:
|
||||
together_client = self._get_client().client
|
||||
self._openai_client = AsyncOpenAI(
|
||||
base_url=together_client.base_url,
|
||||
api_key=together_client.api_key,
|
||||
)
|
||||
return self._openai_client
|
||||
|
||||
async def _nonstream_completion(self, request: CompletionRequest) -> ChatCompletionResponse:
|
||||
params = await self._get_params(request)
|
||||
client = self._get_client()
|
||||
|
|
@ -243,3 +256,101 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
|
|||
)
|
||||
embeddings = [item.embedding for item in r.data]
|
||||
return EmbeddingsResponse(embeddings=embeddings)
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
model_obj = await self.model_store.get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
return await self._get_openai_client().completions.create(**params) # type: ignore
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
model_obj = await self.model_store.get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
return await self._get_openai_client().chat.completions.create(**params) # type: ignore
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
import json
|
||||
import logging
|
||||
from typing import Any, AsyncGenerator, List, Optional, Union
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
|
||||
|
||||
import httpx
|
||||
from openai import AsyncOpenAI
|
||||
|
|
@ -45,6 +45,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.apis.models import Model, ModelType
|
||||
from llama_stack.models.llama.datatypes import BuiltinTool, StopReason, ToolCall
|
||||
from llama_stack.models.llama.sku_list import all_registered_models
|
||||
|
|
@ -58,6 +59,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
|
|||
convert_message_to_openai_dict,
|
||||
convert_tool_call,
|
||||
get_sampling_options,
|
||||
prepare_openai_completion_params,
|
||||
process_chat_completion_stream_response,
|
||||
process_completion_response,
|
||||
process_completion_stream_response,
|
||||
|
|
@ -418,3 +420,109 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
|
||||
embeddings = [data.embedding for data in response.data]
|
||||
return EmbeddingsResponse(embeddings=embeddings)
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
model_obj = await self._get_model(model)
|
||||
|
||||
extra_body: Dict[str, Any] = {}
|
||||
if prompt_logprobs is not None and prompt_logprobs >= 0:
|
||||
extra_body["prompt_logprobs"] = prompt_logprobs
|
||||
if guided_choice:
|
||||
extra_body["guided_choice"] = guided_choice
|
||||
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
extra_body=extra_body,
|
||||
)
|
||||
return await self.client.completions.create(**params) # type: ignore
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
model_obj = await self._get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
return await self.client.chat.completions.create(**params) # type: ignore
|
||||
|
|
|
|||
|
|
@ -206,10 +206,6 @@ class NvidiaPostTrainingAdapter(ModelRegistryHelper):
|
|||
model: str,
|
||||
checkpoint_dir: Optional[str],
|
||||
algorithm_config: Optional[AlgorithmConfig] = None,
|
||||
extra_json: Optional[Dict[str, Any]] = None,
|
||||
params: Optional[Dict[str, Any]] = None,
|
||||
headers: Optional[Dict[str, Any]] = None,
|
||||
**kwargs,
|
||||
) -> NvidiaPostTrainingJob:
|
||||
"""
|
||||
Fine-tunes a model on a dataset.
|
||||
|
|
|
|||
|
|
@ -104,6 +104,15 @@ class NeMoGuardrails:
|
|||
self.threshold = threshold
|
||||
self.guardrails_service_url = config.guardrails_service_url
|
||||
|
||||
async def _guardrails_post(self, path: str, data: Any | None):
|
||||
"""Helper for making POST requests to the guardrails service."""
|
||||
headers = {
|
||||
"Accept": "application/json",
|
||||
}
|
||||
response = requests.post(url=f"{self.guardrails_service_url}{path}", headers=headers, json=data)
|
||||
response.raise_for_status()
|
||||
return response.json()
|
||||
|
||||
async def run(self, messages: List[Message]) -> RunShieldResponse:
|
||||
"""
|
||||
Queries the /v1/guardrails/checks endpoint of the NeMo guardrails deployed API.
|
||||
|
|
@ -118,9 +127,6 @@ class NeMoGuardrails:
|
|||
Raises:
|
||||
requests.HTTPError: If the POST request fails.
|
||||
"""
|
||||
headers = {
|
||||
"Accept": "application/json",
|
||||
}
|
||||
request_data = {
|
||||
"model": self.model,
|
||||
"messages": convert_pydantic_to_json_value(messages),
|
||||
|
|
@ -134,15 +140,11 @@ class NeMoGuardrails:
|
|||
"config_id": self.config_id,
|
||||
},
|
||||
}
|
||||
response = requests.post(
|
||||
url=f"{self.guardrails_service_url}/v1/guardrail/checks", headers=headers, json=request_data
|
||||
)
|
||||
response.raise_for_status()
|
||||
if "Content-Type" in response.headers and response.headers["Content-Type"].startswith("application/json"):
|
||||
response_json = response.json()
|
||||
if response_json["status"] == "blocked":
|
||||
response = await self._guardrails_post(path="/v1/guardrail/checks", data=request_data)
|
||||
|
||||
if response["status"] == "blocked":
|
||||
user_message = "Sorry I cannot do this."
|
||||
metadata = response_json["rails_status"]
|
||||
metadata = response["rails_status"]
|
||||
|
||||
return RunShieldResponse(
|
||||
violation=SafetyViolation(
|
||||
|
|
@ -151,4 +153,5 @@ class NeMoGuardrails:
|
|||
metadata=metadata,
|
||||
)
|
||||
)
|
||||
|
||||
return RunShieldResponse(violation=None)
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import AsyncGenerator, AsyncIterator, List, Optional, Union
|
||||
from typing import Any, AsyncGenerator, AsyncIterator, Dict, List, Optional, Union
|
||||
|
||||
import litellm
|
||||
|
||||
|
|
@ -30,6 +30,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAIMessageParam
|
||||
from llama_stack.apis.models.models import Model
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
|
|
@ -40,6 +41,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
|
|||
convert_openai_chat_completion_stream,
|
||||
convert_tooldef_to_openai_tool,
|
||||
get_sampling_options,
|
||||
prepare_openai_completion_params,
|
||||
)
|
||||
from llama_stack.providers.utils.inference.prompt_adapter import (
|
||||
interleaved_content_as_str,
|
||||
|
|
@ -245,3 +247,103 @@ class LiteLLMOpenAIMixin(
|
|||
|
||||
embeddings = [data["embedding"] for data in response["data"]]
|
||||
return EmbeddingsResponse(embeddings=embeddings)
|
||||
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
model_obj = await self._get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
prompt=prompt,
|
||||
best_of=best_of,
|
||||
echo=echo,
|
||||
frequency_penalty=frequency_penalty,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
presence_penalty=presence_penalty,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
guided_choice=guided_choice,
|
||||
prompt_logprobs=prompt_logprobs,
|
||||
)
|
||||
return litellm.text_completion(**params)
|
||||
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIMessageParam],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
model_obj = await self._get_model(model)
|
||||
params = await prepare_openai_completion_params(
|
||||
model=model_obj.provider_resource_id,
|
||||
messages=messages,
|
||||
frequency_penalty=frequency_penalty,
|
||||
function_call=function_call,
|
||||
functions=functions,
|
||||
logit_bias=logit_bias,
|
||||
logprobs=logprobs,
|
||||
max_completion_tokens=max_completion_tokens,
|
||||
max_tokens=max_tokens,
|
||||
n=n,
|
||||
parallel_tool_calls=parallel_tool_calls,
|
||||
presence_penalty=presence_penalty,
|
||||
response_format=response_format,
|
||||
seed=seed,
|
||||
stop=stop,
|
||||
stream=stream,
|
||||
stream_options=stream_options,
|
||||
temperature=temperature,
|
||||
tool_choice=tool_choice,
|
||||
tools=tools,
|
||||
top_logprobs=top_logprobs,
|
||||
top_p=top_p,
|
||||
user=user,
|
||||
)
|
||||
return litellm.completion(**params)
|
||||
|
|
|
|||
|
|
@ -5,8 +5,10 @@
|
|||
# the root directory of this source tree.
|
||||
import json
|
||||
import logging
|
||||
import time
|
||||
import uuid
|
||||
import warnings
|
||||
from typing import AsyncGenerator, Dict, Iterable, List, Optional, Union
|
||||
from typing import Any, AsyncGenerator, Dict, Iterable, List, Optional, Union
|
||||
|
||||
from openai import AsyncStream
|
||||
from openai.types.chat import (
|
||||
|
|
@ -83,6 +85,7 @@ from llama_stack.apis.inference import (
|
|||
TopPSamplingStrategy,
|
||||
UserMessage,
|
||||
)
|
||||
from llama_stack.apis.inference.inference import OpenAIChatCompletion, OpenAICompletion, OpenAICompletionChoice
|
||||
from llama_stack.models.llama.datatypes import (
|
||||
BuiltinTool,
|
||||
StopReason,
|
||||
|
|
@ -843,6 +846,31 @@ def _convert_openai_logprobs(
|
|||
]
|
||||
|
||||
|
||||
def _convert_openai_sampling_params(
|
||||
max_tokens: Optional[int] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
) -> SamplingParams:
|
||||
sampling_params = SamplingParams()
|
||||
|
||||
if max_tokens:
|
||||
sampling_params.max_tokens = max_tokens
|
||||
|
||||
# Map an explicit temperature of 0 to greedy sampling
|
||||
if temperature == 0:
|
||||
strategy = GreedySamplingStrategy()
|
||||
else:
|
||||
# OpenAI defaults to 1.0 for temperature and top_p if unset
|
||||
if temperature is None:
|
||||
temperature = 1.0
|
||||
if top_p is None:
|
||||
top_p = 1.0
|
||||
strategy = TopPSamplingStrategy(temperature=temperature, top_p=top_p)
|
||||
|
||||
sampling_params.strategy = strategy
|
||||
return sampling_params
|
||||
|
||||
|
||||
def convert_openai_chat_completion_choice(
|
||||
choice: OpenAIChoice,
|
||||
) -> ChatCompletionResponse:
|
||||
|
|
@ -1049,3 +1077,106 @@ async def convert_openai_chat_completion_stream(
|
|||
stop_reason=stop_reason,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
async def prepare_openai_completion_params(**params):
|
||||
completion_params = {k: v for k, v in params.items() if v is not None}
|
||||
return completion_params
|
||||
|
||||
|
||||
class OpenAICompletionUnsupportedMixin:
|
||||
async def openai_completion(
|
||||
self,
|
||||
model: str,
|
||||
prompt: Union[str, List[str], List[int], List[List[int]]],
|
||||
best_of: Optional[int] = None,
|
||||
echo: Optional[bool] = None,
|
||||
frequency_penalty: Optional[float] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
guided_choice: Optional[List[str]] = None,
|
||||
prompt_logprobs: Optional[int] = None,
|
||||
) -> OpenAICompletion:
|
||||
if stream:
|
||||
raise ValueError(f"{self.__class__.__name__} doesn't support streaming openai completions")
|
||||
|
||||
# This is a pretty hacky way to do emulate completions -
|
||||
# basically just de-batches them...
|
||||
prompts = [prompt] if not isinstance(prompt, list) else prompt
|
||||
|
||||
sampling_params = _convert_openai_sampling_params(
|
||||
max_tokens=max_tokens,
|
||||
temperature=temperature,
|
||||
top_p=top_p,
|
||||
)
|
||||
|
||||
choices = []
|
||||
# "n" is the number of completions to generate per prompt
|
||||
for _i in range(0, n):
|
||||
# and we may have multiple prompts, if batching was used
|
||||
|
||||
for prompt in prompts:
|
||||
result = self.completion(
|
||||
model_id=model,
|
||||
content=prompt,
|
||||
sampling_params=sampling_params,
|
||||
)
|
||||
|
||||
index = len(choices)
|
||||
text = result.content
|
||||
finish_reason = _convert_openai_finish_reason(result.stop_reason)
|
||||
|
||||
choice = OpenAICompletionChoice(
|
||||
index=index,
|
||||
text=text,
|
||||
finish_reason=finish_reason,
|
||||
)
|
||||
choices.append(choice)
|
||||
|
||||
return OpenAICompletion(
|
||||
id=f"cmpl-{uuid.uuid4()}",
|
||||
choices=choices,
|
||||
created=int(time.time()),
|
||||
model=model,
|
||||
object="text_completion",
|
||||
)
|
||||
|
||||
|
||||
class OpenAIChatCompletionUnsupportedMixin:
|
||||
async def openai_chat_completion(
|
||||
self,
|
||||
model: str,
|
||||
messages: List[OpenAIChatCompletionMessage],
|
||||
frequency_penalty: Optional[float] = None,
|
||||
function_call: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
functions: Optional[List[Dict[str, Any]]] = None,
|
||||
logit_bias: Optional[Dict[str, float]] = None,
|
||||
logprobs: Optional[bool] = None,
|
||||
max_completion_tokens: Optional[int] = None,
|
||||
max_tokens: Optional[int] = None,
|
||||
n: Optional[int] = None,
|
||||
parallel_tool_calls: Optional[bool] = None,
|
||||
presence_penalty: Optional[float] = None,
|
||||
response_format: Optional[Dict[str, str]] = None,
|
||||
seed: Optional[int] = None,
|
||||
stop: Optional[Union[str, List[str]]] = None,
|
||||
stream: Optional[bool] = None,
|
||||
stream_options: Optional[Dict[str, Any]] = None,
|
||||
temperature: Optional[float] = None,
|
||||
tool_choice: Optional[Union[str, Dict[str, Any]]] = None,
|
||||
tools: Optional[List[Dict[str, Any]]] = None,
|
||||
top_logprobs: Optional[int] = None,
|
||||
top_p: Optional[float] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> OpenAIChatCompletion:
|
||||
raise ValueError(f"{self.__class__.__name__} doesn't support openai chat completion")
|
||||
|
|
|
|||
|
|
@ -381,7 +381,7 @@
|
|||
"sentence-transformers",
|
||||
"sentencepiece",
|
||||
"torch",
|
||||
"torchao==0.5.0",
|
||||
"torchao==0.8.0",
|
||||
"torchvision",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
|
|
|
|||
|
|
@ -28,6 +28,7 @@ dependencies = [
|
|||
"jinja2>=3.1.6",
|
||||
"jsonschema",
|
||||
"llama-stack-client>=0.2.1",
|
||||
"openai>=1.66",
|
||||
"prompt-toolkit",
|
||||
"python-dotenv",
|
||||
"pydantic>=2",
|
||||
|
|
|
|||
|
|
@ -19,6 +19,7 @@ httpx==0.28.1
|
|||
huggingface-hub==0.29.0
|
||||
idna==3.10
|
||||
jinja2==3.1.6
|
||||
jiter==0.8.2
|
||||
jsonschema==4.23.0
|
||||
jsonschema-specifications==2024.10.1
|
||||
llama-stack-client==0.2.1
|
||||
|
|
@ -27,6 +28,7 @@ markdown-it-py==3.0.0
|
|||
markupsafe==3.0.2
|
||||
mdurl==0.1.2
|
||||
numpy==2.2.3
|
||||
openai==1.71.0
|
||||
packaging==24.2
|
||||
pandas==2.2.3
|
||||
pillow==11.1.0
|
||||
|
|
|
|||
216
tests/integration/inference/test_openai_completion.py
Normal file
216
tests/integration/inference/test_openai_completion.py
Normal file
|
|
@ -0,0 +1,216 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
|
||||
import pytest
|
||||
from openai import OpenAI
|
||||
|
||||
from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
|
||||
|
||||
from ..test_cases.test_case import TestCase
|
||||
|
||||
|
||||
def provider_from_model(client_with_models, model_id):
|
||||
models = {m.identifier: m for m in client_with_models.models.list()}
|
||||
models.update({m.provider_resource_id: m for m in client_with_models.models.list()})
|
||||
provider_id = models[model_id].provider_id
|
||||
providers = {p.provider_id: p for p in client_with_models.providers.list()}
|
||||
return providers[provider_id]
|
||||
|
||||
|
||||
def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id):
|
||||
if isinstance(client_with_models, LlamaStackAsLibraryClient):
|
||||
pytest.skip("OpenAI completions are not supported when testing with library client yet.")
|
||||
|
||||
provider = provider_from_model(client_with_models, model_id)
|
||||
if provider.provider_type in (
|
||||
"inline::meta-reference",
|
||||
"inline::sentence-transformers",
|
||||
"inline::vllm",
|
||||
"remote::bedrock",
|
||||
"remote::cerebras",
|
||||
"remote::databricks",
|
||||
# Technically Nvidia does support OpenAI completions, but none of their hosted models
|
||||
# support both completions and chat completions endpoint and all the Llama models are
|
||||
# just chat completions
|
||||
"remote::nvidia",
|
||||
"remote::runpod",
|
||||
"remote::sambanova",
|
||||
"remote::tgi",
|
||||
):
|
||||
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI completions.")
|
||||
|
||||
|
||||
def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, model_id):
|
||||
if isinstance(client_with_models, LlamaStackAsLibraryClient):
|
||||
pytest.skip("OpenAI chat completions are not supported when testing with library client yet.")
|
||||
|
||||
provider = provider_from_model(client_with_models, model_id)
|
||||
if provider.provider_type in (
|
||||
"inline::meta-reference",
|
||||
"inline::sentence-transformers",
|
||||
"inline::vllm",
|
||||
"remote::bedrock",
|
||||
"remote::cerebras",
|
||||
"remote::databricks",
|
||||
"remote::runpod",
|
||||
"remote::sambanova",
|
||||
"remote::tgi",
|
||||
):
|
||||
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI chat completions.")
|
||||
|
||||
|
||||
def skip_if_provider_isnt_vllm(client_with_models, model_id):
|
||||
provider = provider_from_model(client_with_models, model_id)
|
||||
if provider.provider_type != "remote::vllm":
|
||||
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support vllm extra_body parameters.")
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def openai_client(client_with_models):
|
||||
base_url = f"{client_with_models.base_url}/v1/openai/v1"
|
||||
return OpenAI(base_url=base_url, api_key="bar")
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"test_case",
|
||||
[
|
||||
"inference:completion:sanity",
|
||||
],
|
||||
)
|
||||
def test_openai_completion_non_streaming(openai_client, client_with_models, text_model_id, test_case):
|
||||
skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
|
||||
tc = TestCase(test_case)
|
||||
|
||||
# ollama needs more verbose prompting for some reason here...
|
||||
prompt = "Respond to this question and explain your answer. " + tc["content"]
|
||||
response = openai_client.completions.create(
|
||||
model=text_model_id,
|
||||
prompt=prompt,
|
||||
stream=False,
|
||||
)
|
||||
assert len(response.choices) > 0
|
||||
choice = response.choices[0]
|
||||
assert len(choice.text) > 10
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"test_case",
|
||||
[
|
||||
"inference:completion:sanity",
|
||||
],
|
||||
)
|
||||
def test_openai_completion_streaming(openai_client, client_with_models, text_model_id, test_case):
|
||||
skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
|
||||
tc = TestCase(test_case)
|
||||
|
||||
# ollama needs more verbose prompting for some reason here...
|
||||
prompt = "Respond to this question and explain your answer. " + tc["content"]
|
||||
response = openai_client.completions.create(
|
||||
model=text_model_id,
|
||||
prompt=prompt,
|
||||
stream=True,
|
||||
max_tokens=50,
|
||||
)
|
||||
streamed_content = [chunk.choices[0].text for chunk in response]
|
||||
content_str = "".join(streamed_content).lower().strip()
|
||||
assert len(content_str) > 10
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"prompt_logprobs",
|
||||
[
|
||||
1,
|
||||
0,
|
||||
],
|
||||
)
|
||||
def test_openai_completion_prompt_logprobs(openai_client, client_with_models, text_model_id, prompt_logprobs):
|
||||
skip_if_provider_isnt_vllm(client_with_models, text_model_id)
|
||||
|
||||
prompt = "Hello, world!"
|
||||
response = openai_client.completions.create(
|
||||
model=text_model_id,
|
||||
prompt=prompt,
|
||||
stream=False,
|
||||
extra_body={
|
||||
"prompt_logprobs": prompt_logprobs,
|
||||
},
|
||||
)
|
||||
assert len(response.choices) > 0
|
||||
choice = response.choices[0]
|
||||
assert len(choice.prompt_logprobs) > 0
|
||||
|
||||
|
||||
def test_openai_completion_guided_choice(openai_client, client_with_models, text_model_id):
|
||||
skip_if_provider_isnt_vllm(client_with_models, text_model_id)
|
||||
|
||||
prompt = "I am feeling really sad today."
|
||||
response = openai_client.completions.create(
|
||||
model=text_model_id,
|
||||
prompt=prompt,
|
||||
stream=False,
|
||||
extra_body={
|
||||
"guided_choice": ["joy", "sadness"],
|
||||
},
|
||||
)
|
||||
assert len(response.choices) > 0
|
||||
choice = response.choices[0]
|
||||
assert choice.text in ["joy", "sadness"]
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"test_case",
|
||||
[
|
||||
"inference:chat_completion:non_streaming_01",
|
||||
"inference:chat_completion:non_streaming_02",
|
||||
],
|
||||
)
|
||||
def test_openai_chat_completion_non_streaming(openai_client, client_with_models, text_model_id, test_case):
|
||||
skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
|
||||
tc = TestCase(test_case)
|
||||
question = tc["question"]
|
||||
expected = tc["expected"]
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=text_model_id,
|
||||
messages=[
|
||||
{
|
||||
"role": "user",
|
||||
"content": question,
|
||||
}
|
||||
],
|
||||
stream=False,
|
||||
)
|
||||
message_content = response.choices[0].message.content.lower().strip()
|
||||
assert len(message_content) > 0
|
||||
assert expected.lower() in message_content
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"test_case",
|
||||
[
|
||||
"inference:chat_completion:streaming_01",
|
||||
"inference:chat_completion:streaming_02",
|
||||
],
|
||||
)
|
||||
def test_openai_chat_completion_streaming(openai_client, client_with_models, text_model_id, test_case):
|
||||
skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
|
||||
tc = TestCase(test_case)
|
||||
question = tc["question"]
|
||||
expected = tc["expected"]
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=text_model_id,
|
||||
messages=[{"role": "user", "content": question}],
|
||||
stream=True,
|
||||
timeout=120, # Increase timeout to 2 minutes for large conversation history
|
||||
)
|
||||
streamed_content = []
|
||||
for chunk in response:
|
||||
if chunk.choices[0].delta.content:
|
||||
streamed_content.append(chunk.choices[0].delta.content.lower().strip())
|
||||
assert len(streamed_content) > 0
|
||||
assert expected.lower() in "".join(streamed_content)
|
||||
326
tests/unit/providers/nvidia/test_safety.py
Normal file
326
tests/unit/providers/nvidia/test_safety.py
Normal file
|
|
@ -0,0 +1,326 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import json
|
||||
import os
|
||||
import unittest
|
||||
from typing import Any
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from llama_stack.apis.inference.inference import CompletionMessage, UserMessage
|
||||
from llama_stack.apis.safety import RunShieldResponse, ViolationLevel
|
||||
from llama_stack.apis.shields import Shield
|
||||
from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig
|
||||
from llama_stack.providers.remote.safety.nvidia.nvidia import NVIDIASafetyAdapter
|
||||
|
||||
|
||||
class TestNVIDIASafetyAdapter(unittest.TestCase):
|
||||
def setUp(self):
|
||||
os.environ["NVIDIA_GUARDRAILS_URL"] = "http://nemo.test"
|
||||
|
||||
# Initialize the adapter
|
||||
self.config = NVIDIASafetyConfig(
|
||||
guardrails_service_url=os.environ["NVIDIA_GUARDRAILS_URL"],
|
||||
)
|
||||
self.adapter = NVIDIASafetyAdapter(config=self.config)
|
||||
self.shield_store = AsyncMock()
|
||||
self.adapter.shield_store = self.shield_store
|
||||
|
||||
# Mock the HTTP request methods
|
||||
self.guardrails_post_patcher = patch(
|
||||
"llama_stack.providers.remote.safety.nvidia.nvidia.NeMoGuardrails._guardrails_post"
|
||||
)
|
||||
self.mock_guardrails_post = self.guardrails_post_patcher.start()
|
||||
self.mock_guardrails_post.return_value = {"status": "allowed"}
|
||||
|
||||
def tearDown(self):
|
||||
"""Clean up after each test."""
|
||||
self.guardrails_post_patcher.stop()
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def inject_fixtures(self, run_async):
|
||||
self.run_async = run_async
|
||||
|
||||
def _assert_request(
|
||||
self,
|
||||
mock_call: MagicMock,
|
||||
expected_url: str,
|
||||
expected_headers: dict[str, str] | None = None,
|
||||
expected_json: dict[str, Any] | None = None,
|
||||
) -> None:
|
||||
"""
|
||||
Helper method to verify request details in mock API calls.
|
||||
|
||||
Args:
|
||||
mock_call: The MagicMock object that was called
|
||||
expected_url: The expected URL to which the request was made
|
||||
expected_headers: Optional dictionary of expected request headers
|
||||
expected_json: Optional dictionary of expected JSON payload
|
||||
"""
|
||||
call_args = mock_call.call_args
|
||||
|
||||
# Check URL
|
||||
assert call_args[0][0] == expected_url
|
||||
|
||||
# Check headers if provided
|
||||
if expected_headers:
|
||||
for key, value in expected_headers.items():
|
||||
assert call_args[1]["headers"][key] == value
|
||||
|
||||
# Check JSON if provided
|
||||
if expected_json:
|
||||
for key, value in expected_json.items():
|
||||
if isinstance(value, dict):
|
||||
for nested_key, nested_value in value.items():
|
||||
assert call_args[1]["json"][key][nested_key] == nested_value
|
||||
else:
|
||||
assert call_args[1]["json"][key] == value
|
||||
|
||||
def test_register_shield_with_valid_id(self):
|
||||
shield = Shield(
|
||||
provider_id="nvidia",
|
||||
type="shield",
|
||||
identifier="test-shield",
|
||||
provider_resource_id="test-model",
|
||||
)
|
||||
|
||||
# Register the shield
|
||||
self.run_async(self.adapter.register_shield(shield))
|
||||
|
||||
def test_register_shield_without_id(self):
|
||||
shield = Shield(
|
||||
provider_id="nvidia",
|
||||
type="shield",
|
||||
identifier="test-shield",
|
||||
provider_resource_id="",
|
||||
)
|
||||
|
||||
# Register the shield should raise a ValueError
|
||||
with self.assertRaises(ValueError):
|
||||
self.run_async(self.adapter.register_shield(shield))
|
||||
|
||||
def test_run_shield_allowed(self):
|
||||
# Set up the shield
|
||||
shield_id = "test-shield"
|
||||
shield = Shield(
|
||||
provider_id="nvidia",
|
||||
type="shield",
|
||||
identifier=shield_id,
|
||||
provider_resource_id="test-model",
|
||||
)
|
||||
self.shield_store.get_shield.return_value = shield
|
||||
|
||||
# Mock Guardrails API response
|
||||
self.mock_guardrails_post.return_value = {"status": "allowed"}
|
||||
|
||||
# Run the shield
|
||||
messages = [
|
||||
UserMessage(role="user", content="Hello, how are you?"),
|
||||
CompletionMessage(
|
||||
role="assistant",
|
||||
content="I'm doing well, thank you for asking!",
|
||||
stop_reason="end_of_message",
|
||||
tool_calls=[],
|
||||
),
|
||||
]
|
||||
result = self.run_async(self.adapter.run_shield(shield_id, messages))
|
||||
|
||||
# Verify the shield store was called
|
||||
self.shield_store.get_shield.assert_called_once_with(shield_id)
|
||||
|
||||
# Verify the Guardrails API was called correctly
|
||||
self.mock_guardrails_post.assert_called_once_with(
|
||||
path="/v1/guardrail/checks",
|
||||
data={
|
||||
"model": shield_id,
|
||||
"messages": [
|
||||
json.loads(messages[0].model_dump_json()),
|
||||
json.loads(messages[1].model_dump_json()),
|
||||
],
|
||||
"temperature": 1.0,
|
||||
"top_p": 1,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0,
|
||||
"max_tokens": 160,
|
||||
"stream": False,
|
||||
"guardrails": {
|
||||
"config_id": "self-check",
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
# Verify the result
|
||||
assert isinstance(result, RunShieldResponse)
|
||||
assert result.violation is None
|
||||
|
||||
def test_run_shield_blocked(self):
|
||||
# Set up the shield
|
||||
shield_id = "test-shield"
|
||||
shield = Shield(
|
||||
provider_id="nvidia",
|
||||
type="shield",
|
||||
identifier=shield_id,
|
||||
provider_resource_id="test-model",
|
||||
)
|
||||
self.shield_store.get_shield.return_value = shield
|
||||
|
||||
# Mock Guardrails API response
|
||||
self.mock_guardrails_post.return_value = {"status": "blocked", "rails_status": {"reason": "harmful_content"}}
|
||||
|
||||
# Run the shield
|
||||
messages = [
|
||||
UserMessage(role="user", content="Hello, how are you?"),
|
||||
CompletionMessage(
|
||||
role="assistant",
|
||||
content="I'm doing well, thank you for asking!",
|
||||
stop_reason="end_of_message",
|
||||
tool_calls=[],
|
||||
),
|
||||
]
|
||||
result = self.run_async(self.adapter.run_shield(shield_id, messages))
|
||||
|
||||
# Verify the shield store was called
|
||||
self.shield_store.get_shield.assert_called_once_with(shield_id)
|
||||
|
||||
# Verify the Guardrails API was called correctly
|
||||
self.mock_guardrails_post.assert_called_once_with(
|
||||
path="/v1/guardrail/checks",
|
||||
data={
|
||||
"model": shield_id,
|
||||
"messages": [
|
||||
json.loads(messages[0].model_dump_json()),
|
||||
json.loads(messages[1].model_dump_json()),
|
||||
],
|
||||
"temperature": 1.0,
|
||||
"top_p": 1,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0,
|
||||
"max_tokens": 160,
|
||||
"stream": False,
|
||||
"guardrails": {
|
||||
"config_id": "self-check",
|
||||
},
|
||||
},
|
||||
)
|
||||
|
||||
# Verify the result
|
||||
assert result.violation is not None
|
||||
assert isinstance(result, RunShieldResponse)
|
||||
assert result.violation.user_message == "Sorry I cannot do this."
|
||||
assert result.violation.violation_level == ViolationLevel.ERROR
|
||||
assert result.violation.metadata == {"reason": "harmful_content"}
|
||||
|
||||
def test_run_shield_not_found(self):
|
||||
# Set up shield store to return None
|
||||
shield_id = "non-existent-shield"
|
||||
self.shield_store.get_shield.return_value = None
|
||||
|
||||
messages = [
|
||||
UserMessage(role="user", content="Hello, how are you?"),
|
||||
]
|
||||
|
||||
with self.assertRaises(ValueError):
|
||||
self.run_async(self.adapter.run_shield(shield_id, messages))
|
||||
|
||||
# Verify the shield store was called
|
||||
self.shield_store.get_shield.assert_called_once_with(shield_id)
|
||||
|
||||
# Verify the Guardrails API was not called
|
||||
self.mock_guardrails_post.assert_not_called()
|
||||
|
||||
def test_run_shield_http_error(self):
|
||||
shield_id = "test-shield"
|
||||
shield = Shield(
|
||||
provider_id="nvidia",
|
||||
type="shield",
|
||||
identifier=shield_id,
|
||||
provider_resource_id="test-model",
|
||||
)
|
||||
self.shield_store.get_shield.return_value = shield
|
||||
|
||||
# Mock Guardrails API to raise an exception
|
||||
error_msg = "API Error: 500 Internal Server Error"
|
||||
self.mock_guardrails_post.side_effect = Exception(error_msg)
|
||||
|
||||
# Running the shield should raise an exception
|
||||
messages = [
|
||||
UserMessage(role="user", content="Hello, how are you?"),
|
||||
CompletionMessage(
|
||||
role="assistant",
|
||||
content="I'm doing well, thank you for asking!",
|
||||
stop_reason="end_of_message",
|
||||
tool_calls=[],
|
||||
),
|
||||
]
|
||||
with self.assertRaises(Exception) as context:
|
||||
self.run_async(self.adapter.run_shield(shield_id, messages))
|
||||
|
||||
# Verify the shield store was called
|
||||
self.shield_store.get_shield.assert_called_once_with(shield_id)
|
||||
|
||||
# Verify the Guardrails API was called correctly
|
||||
self.mock_guardrails_post.assert_called_once_with(
|
||||
path="/v1/guardrail/checks",
|
||||
data={
|
||||
"model": shield_id,
|
||||
"messages": [
|
||||
json.loads(messages[0].model_dump_json()),
|
||||
json.loads(messages[1].model_dump_json()),
|
||||
],
|
||||
"temperature": 1.0,
|
||||
"top_p": 1,
|
||||
"frequency_penalty": 0,
|
||||
"presence_penalty": 0,
|
||||
"max_tokens": 160,
|
||||
"stream": False,
|
||||
"guardrails": {
|
||||
"config_id": "self-check",
|
||||
},
|
||||
},
|
||||
)
|
||||
# Verify the exception message
|
||||
assert error_msg in str(context.exception)
|
||||
|
||||
def test_init_nemo_guardrails(self):
|
||||
from llama_stack.providers.remote.safety.nvidia.nvidia import NeMoGuardrails
|
||||
|
||||
test_config_id = "test-custom-config-id"
|
||||
config = NVIDIASafetyConfig(
|
||||
guardrails_service_url=os.environ["NVIDIA_GUARDRAILS_URL"],
|
||||
config_id=test_config_id,
|
||||
)
|
||||
# Initialize with default parameters
|
||||
test_model = "test-model"
|
||||
guardrails = NeMoGuardrails(config, test_model)
|
||||
|
||||
# Verify the attributes are set correctly
|
||||
assert guardrails.config_id == test_config_id
|
||||
assert guardrails.model == test_model
|
||||
assert guardrails.threshold == 0.9 # Default value
|
||||
assert guardrails.temperature == 1.0 # Default value
|
||||
assert guardrails.guardrails_service_url == os.environ["NVIDIA_GUARDRAILS_URL"]
|
||||
|
||||
# Initialize with custom parameters
|
||||
guardrails = NeMoGuardrails(config, test_model, threshold=0.8, temperature=0.7)
|
||||
|
||||
# Verify the attributes are set correctly
|
||||
assert guardrails.config_id == test_config_id
|
||||
assert guardrails.model == test_model
|
||||
assert guardrails.threshold == 0.8
|
||||
assert guardrails.temperature == 0.7
|
||||
assert guardrails.guardrails_service_url == os.environ["NVIDIA_GUARDRAILS_URL"]
|
||||
|
||||
def test_init_nemo_guardrails_invalid_temperature(self):
|
||||
from llama_stack.providers.remote.safety.nvidia.nvidia import NeMoGuardrails
|
||||
|
||||
config = NVIDIASafetyConfig(
|
||||
guardrails_service_url=os.environ["NVIDIA_GUARDRAILS_URL"],
|
||||
config_id="test-custom-config-id",
|
||||
)
|
||||
with self.assertRaises(ValueError):
|
||||
NeMoGuardrails(config, "test-model", temperature=0)
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
# Test Results Report
|
||||
|
||||
*Generated on: 2025-04-08 21:14:02*
|
||||
*Generated on: 2025-04-10 16:48:18*
|
||||
|
||||
*This report was generated by running `python tests/verifications/generate_report.py`*
|
||||
|
||||
|
|
@ -15,74 +15,118 @@
|
|||
|
||||
| Provider | Pass Rate | Tests Passed | Total Tests |
|
||||
| --- | --- | --- | --- |
|
||||
| Together | 67.7% | 21 | 31 |
|
||||
| Fireworks | 90.3% | 28 | 31 |
|
||||
| Openai | 100.0% | 22 | 22 |
|
||||
| Together | 64.7% | 22 | 34 |
|
||||
| Fireworks | 82.4% | 28 | 34 |
|
||||
| Openai | 100.0% | 24 | 24 |
|
||||
|
||||
|
||||
|
||||
## Together
|
||||
|
||||
*Tests run on: 2025-04-08 16:19:59*
|
||||
*Tests run on: 2025-04-10 16:46:35*
|
||||
|
||||
```bash
|
||||
pytest tests/verifications/openai/test_chat_completion.py --provider=together -v
|
||||
# Run all tests for this provider:
|
||||
pytest tests/verifications/openai_api/test_chat_completion.py --provider=together -v
|
||||
|
||||
# Example: Run only the 'earth' case of test_chat_non_streaming_basic:
|
||||
pytest tests/verifications/openai_api/test_chat_completion.py --provider=together -k "test_chat_non_streaming_basic and earth"
|
||||
```
|
||||
|
||||
| Test | Llama-3.3-70B-Instruct | Llama-4-Maverick-17B-128E-Instruct | Llama-4-Scout-17B-16E-Instruct |
|
||||
|
||||
**Model Key (Together)**
|
||||
|
||||
| Display Name | Full Model ID |
|
||||
| --- | --- |
|
||||
| Llama-3.3-70B-Instruct | `meta-llama/Llama-3.3-70B-Instruct-Turbo` |
|
||||
| Llama-4-Maverick-Instruct | `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` |
|
||||
| Llama-4-Scout-Instruct | `meta-llama/Llama-4-Scout-17B-16E-Instruct` |
|
||||
|
||||
|
||||
| Test | Llama-3.3-70B-Instruct | Llama-4-Maverick-Instruct | Llama-4-Scout-Instruct |
|
||||
| --- | --- | --- | --- |
|
||||
| test_chat_non_streaming_basic (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (case 1) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_image (case 0) | ⚪ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (case 1) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_tool_calling (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (case 0) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_basic (case 1) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_image (case 0) | ⚪ | ❌ | ❌ |
|
||||
| test_chat_streaming_structured_output (case 0) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_structured_output (case 1) | ✅ | ❌ | ❌ |
|
||||
| test_chat_non_streaming_basic (earth) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (saturn) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_image | ⚪ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (calendar) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (math) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_tool_calling | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (earth) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_basic (saturn) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_image | ⚪ | ❌ | ❌ |
|
||||
| test_chat_streaming_structured_output (calendar) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_structured_output (math) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_tool_calling | ✅ | ❌ | ❌ |
|
||||
|
||||
## Fireworks
|
||||
|
||||
*Tests run on: 2025-04-08 16:18:28*
|
||||
*Tests run on: 2025-04-10 16:44:44*
|
||||
|
||||
```bash
|
||||
pytest tests/verifications/openai/test_chat_completion.py --provider=fireworks -v
|
||||
# Run all tests for this provider:
|
||||
pytest tests/verifications/openai_api/test_chat_completion.py --provider=fireworks -v
|
||||
|
||||
# Example: Run only the 'earth' case of test_chat_non_streaming_basic:
|
||||
pytest tests/verifications/openai_api/test_chat_completion.py --provider=fireworks -k "test_chat_non_streaming_basic and earth"
|
||||
```
|
||||
|
||||
| Test | Llama-3.3-70B-Instruct | Llama-4-Maverick-17B-128E-Instruct | Llama-4-Scout-17B-16E-Instruct |
|
||||
|
||||
**Model Key (Fireworks)**
|
||||
|
||||
| Display Name | Full Model ID |
|
||||
| --- | --- |
|
||||
| Llama-3.3-70B-Instruct | `accounts/fireworks/models/llama-v3p3-70b-instruct` |
|
||||
| Llama-4-Maverick-Instruct | `accounts/fireworks/models/llama4-maverick-instruct-basic` |
|
||||
| Llama-4-Scout-Instruct | `accounts/fireworks/models/llama4-scout-instruct-basic` |
|
||||
|
||||
|
||||
| Test | Llama-3.3-70B-Instruct | Llama-4-Maverick-Instruct | Llama-4-Scout-Instruct |
|
||||
| --- | --- | --- | --- |
|
||||
| test_chat_non_streaming_basic (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (case 1) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_image (case 0) | ⚪ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (case 1) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_tool_calling (case 0) | ✅ | ❌ | ❌ |
|
||||
| test_chat_streaming_basic (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (case 1) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_image (case 0) | ⚪ | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (case 0) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (case 1) | ❌ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (earth) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (saturn) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_image | ⚪ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (calendar) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (math) | ✅ | ✅ | ✅ |
|
||||
| test_chat_non_streaming_tool_calling | ❌ | ❌ | ❌ |
|
||||
| test_chat_streaming_basic (earth) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (saturn) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_image | ⚪ | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (calendar) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (math) | ✅ | ✅ | ✅ |
|
||||
| test_chat_streaming_tool_calling | ❌ | ❌ | ❌ |
|
||||
|
||||
## Openai
|
||||
|
||||
*Tests run on: 2025-04-08 16:22:02*
|
||||
*Tests run on: 2025-04-10 16:47:28*
|
||||
|
||||
```bash
|
||||
pytest tests/verifications/openai/test_chat_completion.py --provider=openai -v
|
||||
# Run all tests for this provider:
|
||||
pytest tests/verifications/openai_api/test_chat_completion.py --provider=openai -v
|
||||
|
||||
# Example: Run only the 'earth' case of test_chat_non_streaming_basic:
|
||||
pytest tests/verifications/openai_api/test_chat_completion.py --provider=openai -k "test_chat_non_streaming_basic and earth"
|
||||
```
|
||||
|
||||
|
||||
**Model Key (Openai)**
|
||||
|
||||
| Display Name | Full Model ID |
|
||||
| --- | --- |
|
||||
| gpt-4o | `gpt-4o` |
|
||||
| gpt-4o-mini | `gpt-4o-mini` |
|
||||
|
||||
|
||||
| Test | gpt-4o | gpt-4o-mini |
|
||||
| --- | --- | --- |
|
||||
| test_chat_non_streaming_basic (case 0) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (case 1) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_image (case 0) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (case 0) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (case 1) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_tool_calling (case 0) | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (case 0) | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (case 1) | ✅ | ✅ |
|
||||
| test_chat_streaming_image (case 0) | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (case 0) | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (case 1) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (earth) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_basic (saturn) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_image | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (calendar) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_structured_output (math) | ✅ | ✅ |
|
||||
| test_chat_non_streaming_tool_calling | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (earth) | ✅ | ✅ |
|
||||
| test_chat_streaming_basic (saturn) | ✅ | ✅ |
|
||||
| test_chat_streaming_image | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (calendar) | ✅ | ✅ |
|
||||
| test_chat_streaming_structured_output (math) | ✅ | ✅ |
|
||||
| test_chat_streaming_tool_calling | ✅ | ✅ |
|
||||
|
|
|
|||
10
tests/verifications/conf/cerebras.yaml
Normal file
10
tests/verifications/conf/cerebras.yaml
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
base_url: https://api.cerebras.ai/v1
|
||||
api_key_var: CEREBRAS_API_KEY
|
||||
models:
|
||||
- llama-3.3-70b
|
||||
model_display_names:
|
||||
llama-3.3-70b: Llama-3.3-70B-Instruct
|
||||
test_exclusions:
|
||||
llama-3.3-70b:
|
||||
- test_chat_non_streaming_image
|
||||
- test_chat_streaming_image
|
||||
14
tests/verifications/conf/fireworks.yaml
Normal file
14
tests/verifications/conf/fireworks.yaml
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
base_url: https://api.fireworks.ai/inference/v1
|
||||
api_key_var: FIREWORKS_API_KEY
|
||||
models:
|
||||
- accounts/fireworks/models/llama-v3p3-70b-instruct
|
||||
- accounts/fireworks/models/llama4-scout-instruct-basic
|
||||
- accounts/fireworks/models/llama4-maverick-instruct-basic
|
||||
model_display_names:
|
||||
accounts/fireworks/models/llama-v3p3-70b-instruct: Llama-3.3-70B-Instruct
|
||||
accounts/fireworks/models/llama4-scout-instruct-basic: Llama-4-Scout-Instruct
|
||||
accounts/fireworks/models/llama4-maverick-instruct-basic: Llama-4-Maverick-Instruct
|
||||
test_exclusions:
|
||||
accounts/fireworks/models/llama-v3p3-70b-instruct:
|
||||
- test_chat_non_streaming_image
|
||||
- test_chat_streaming_image
|
||||
14
tests/verifications/conf/groq.yaml
Normal file
14
tests/verifications/conf/groq.yaml
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
base_url: https://api.groq.com/openai/v1
|
||||
api_key_var: GROQ_API_KEY
|
||||
models:
|
||||
- llama-3.3-70b-versatile
|
||||
- llama-4-scout-17b-16e-instruct
|
||||
- llama-4-maverick-17b-128e-instruct
|
||||
model_display_names:
|
||||
llama-3.3-70b-versatile: Llama-3.3-70B-Instruct
|
||||
llama-4-scout-17b-16e-instruct: Llama-4-Scout-Instruct
|
||||
llama-4-maverick-17b-128e-instruct: Llama-4-Maverick-Instruct
|
||||
test_exclusions:
|
||||
llama-3.3-70b-versatile:
|
||||
- test_chat_non_streaming_image
|
||||
- test_chat_streaming_image
|
||||
9
tests/verifications/conf/openai.yaml
Normal file
9
tests/verifications/conf/openai.yaml
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
base_url: https://api.openai.com/v1
|
||||
api_key_var: OPENAI_API_KEY
|
||||
models:
|
||||
- gpt-4o
|
||||
- gpt-4o-mini
|
||||
model_display_names:
|
||||
gpt-4o: gpt-4o
|
||||
gpt-4o-mini: gpt-4o-mini
|
||||
test_exclusions: {}
|
||||
14
tests/verifications/conf/together.yaml
Normal file
14
tests/verifications/conf/together.yaml
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
base_url: https://api.together.xyz/v1
|
||||
api_key_var: TOGETHER_API_KEY
|
||||
models:
|
||||
- meta-llama/Llama-3.3-70B-Instruct-Turbo
|
||||
- meta-llama/Llama-4-Scout-17B-16E-Instruct
|
||||
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
|
||||
model_display_names:
|
||||
meta-llama/Llama-3.3-70B-Instruct-Turbo: Llama-3.3-70B-Instruct
|
||||
meta-llama/Llama-4-Scout-17B-16E-Instruct: Llama-4-Scout-Instruct
|
||||
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8: Llama-4-Maverick-Instruct
|
||||
test_exclusions:
|
||||
meta-llama/Llama-3.3-70B-Instruct-Turbo:
|
||||
- test_chat_non_streaming_image
|
||||
- test_chat_streaming_image
|
||||
|
|
@ -4,6 +4,10 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import re
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
def pytest_addoption(parser):
|
||||
parser.addoption(
|
||||
|
|
@ -14,7 +18,7 @@ def pytest_addoption(parser):
|
|||
parser.addoption(
|
||||
"--api-key",
|
||||
action="store",
|
||||
help="API key",
|
||||
help="API key to use for the provider",
|
||||
)
|
||||
parser.addoption(
|
||||
"--provider",
|
||||
|
|
@ -24,5 +28,64 @@ def pytest_addoption(parser):
|
|||
|
||||
|
||||
pytest_plugins = [
|
||||
"tests.verifications.openai.fixtures.fixtures",
|
||||
"pytest_jsonreport",
|
||||
"tests.verifications.openai_api.fixtures.fixtures",
|
||||
"tests.verifications.openai_api.fixtures.load",
|
||||
]
|
||||
|
||||
|
||||
@pytest.hookimpl(optionalhook=True)
|
||||
def pytest_json_runtest_metadata(item, call):
|
||||
"""Add model and case_id to pytest-json report metadata."""
|
||||
metadata = {}
|
||||
nodeid = item.nodeid
|
||||
|
||||
# 1. Extract model from callspec if available
|
||||
model = item.callspec.params.get("model") if hasattr(item, "callspec") else None
|
||||
if model:
|
||||
metadata["model"] = model
|
||||
else:
|
||||
# Fallback: Try parsing from nodeid (less reliable)
|
||||
match_model = re.search(r"\[(.*?)-", nodeid)
|
||||
if match_model:
|
||||
model = match_model.group(1) # Store model even if found via fallback
|
||||
metadata["model"] = model
|
||||
else:
|
||||
print(f"Warning: Could not determine model for test {nodeid}")
|
||||
model = None # Ensure model is None if not found
|
||||
|
||||
# 2. Extract case_id using the known model string if possible
|
||||
if model:
|
||||
# Construct a regex pattern to find the case_id *after* the model name and a hyphen.
|
||||
# Escape the model name in case it contains regex special characters.
|
||||
pattern = re.escape(model) + r"-(.*?)\]$"
|
||||
match_case = re.search(pattern, nodeid)
|
||||
if match_case:
|
||||
case_id = match_case.group(1)
|
||||
metadata["case_id"] = case_id
|
||||
else:
|
||||
# Fallback if the pattern didn't match (e.g., nodeid format unexpected)
|
||||
# Try the old less specific regex as a last resort.
|
||||
match_case_fallback = re.search(r"-(.*?)\]$", nodeid)
|
||||
if match_case_fallback:
|
||||
case_id = match_case_fallback.group(1)
|
||||
metadata["case_id"] = case_id
|
||||
print(f"Warning: Used fallback regex to parse case_id from nodeid {nodeid}")
|
||||
else:
|
||||
print(f"Warning: Could not parse case_id from nodeid {nodeid} even with fallback.")
|
||||
if "case" in (item.callspec.params if hasattr(item, "callspec") else {}):
|
||||
metadata["case_id"] = "parsing_failed"
|
||||
elif "case" in (item.callspec.params if hasattr(item, "callspec") else {}):
|
||||
# Cannot reliably parse case_id without model, but we know it's a case test.
|
||||
# Try the generic fallback regex.
|
||||
match_case_fallback = re.search(r"-(.*?)\]$", nodeid)
|
||||
if match_case_fallback:
|
||||
case_id = match_case_fallback.group(1)
|
||||
metadata["case_id"] = case_id
|
||||
print(f"Warning: Used fallback regex to parse case_id from nodeid {nodeid} (model unknown)")
|
||||
else:
|
||||
print(f"Warning: Could not parse case_id from nodeid {nodeid} (model unknown)")
|
||||
metadata["case_id"] = "parsing_failed_no_model"
|
||||
# else: Not a test with a model or case param we need to handle.
|
||||
|
||||
return metadata
|
||||
|
|
|
|||
|
|
@ -4,27 +4,48 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
# /// script
|
||||
# requires-python = ">=3.10"
|
||||
# dependencies = [
|
||||
# "pytest-json-report",
|
||||
# "pyyaml",
|
||||
# ]
|
||||
# ///
|
||||
"""
|
||||
Test Report Generator
|
||||
|
||||
Requirements:
|
||||
pip install pytest-json-report
|
||||
Description:
|
||||
This script runs pytest tests (specifically designed for OpenAI API compatibility checks)
|
||||
for different providers, aggregates the results from JSON reports, and generates
|
||||
a markdown summary report (REPORT.md).
|
||||
|
||||
It automatically cleans up old test result files, keeping only the latest
|
||||
per provider.
|
||||
|
||||
|
||||
Configuration:
|
||||
- Provider details (models, display names) are loaded from `tests/verifications/config.yaml`.
|
||||
- Test cases are defined in YAML files within `tests/verifications/openai_api/fixtures/test_cases/`.
|
||||
- Test results are stored in `tests/verifications/test_results/`.
|
||||
|
||||
Usage:
|
||||
# Generate a report using existing test results
|
||||
# Generate a report using the latest existing test results
|
||||
python tests/verifications/generate_report.py
|
||||
|
||||
# Run tests and generate a report
|
||||
# Run tests for all configured providers and generate a report
|
||||
python tests/verifications/generate_report.py --run-tests
|
||||
|
||||
# Run tests for specific providers
|
||||
# Run tests only for specific providers (space-separated)
|
||||
python tests/verifications/generate_report.py --run-tests --providers fireworks openai
|
||||
|
||||
# Run tests matching a keyword expression (uses pytest -k)
|
||||
python tests/verifications/generate_report.py --run-tests --providers fireworks --k "streaming"
|
||||
|
||||
# Run a specific test case for a provider
|
||||
python tests/verifications/generate_report.py --run-tests --providers fireworks --k "test_chat_streaming_basic and basic_earth"
|
||||
|
||||
# Save the report to a custom location
|
||||
python tests/verifications/generate_report.py --output custom_report.md
|
||||
|
||||
# Clean up old test result files
|
||||
python tests/verifications/generate_report.py --cleanup
|
||||
"""
|
||||
|
||||
import argparse
|
||||
|
|
@ -35,6 +56,9 @@ import subprocess
|
|||
import time
|
||||
from collections import defaultdict
|
||||
from pathlib import Path
|
||||
from typing import Any, DefaultDict, Dict, Set, Tuple
|
||||
|
||||
from tests.verifications.openai_api.fixtures.fixtures import _load_all_verification_configs
|
||||
|
||||
# Define the root directory for test results
|
||||
RESULTS_DIR = Path(__file__).parent / "test_results"
|
||||
|
|
@ -43,47 +67,52 @@ RESULTS_DIR.mkdir(exist_ok=True)
|
|||
# Maximum number of test result files to keep per provider
|
||||
MAX_RESULTS_PER_PROVIDER = 1
|
||||
|
||||
# Custom order of providers
|
||||
PROVIDER_ORDER = ["together", "fireworks", "groq", "cerebras", "openai"]
|
||||
|
||||
# Dictionary to store providers and their models (will be populated dynamically)
|
||||
PROVIDERS = defaultdict(set)
|
||||
|
||||
# Tests will be dynamically extracted from results
|
||||
ALL_TESTS = set()
|
||||
VERIFICATION_CONFIG = _load_all_verification_configs()
|
||||
|
||||
|
||||
def run_tests(provider):
|
||||
def run_tests(provider, keyword=None):
|
||||
"""Run pytest for a specific provider and save results"""
|
||||
print(f"Running tests for provider: {provider}")
|
||||
|
||||
timestamp = int(time.time())
|
||||
result_file = RESULTS_DIR / f"{provider}_{timestamp}.json"
|
||||
temp_json_file = RESULTS_DIR / f"temp_{provider}_{timestamp}.json"
|
||||
# Use a constant filename for the final result and temp file
|
||||
result_file = RESULTS_DIR / f"{provider}.json"
|
||||
temp_json_file = RESULTS_DIR / f"temp_{provider}.json"
|
||||
|
||||
# Determine project root directory relative to this script
|
||||
project_root = Path(__file__).parent.parent.parent
|
||||
|
||||
# Run pytest with JSON output
|
||||
cmd = [
|
||||
"python",
|
||||
"-m",
|
||||
"pytest",
|
||||
"tests/verifications/openai/test_chat_completion.py",
|
||||
"tests/verifications/openai_api/test_chat_completion.py",
|
||||
f"--provider={provider}",
|
||||
"-v",
|
||||
"--json-report",
|
||||
f"--json-report-file={temp_json_file}",
|
||||
]
|
||||
|
||||
# Append -k argument if provided
|
||||
if keyword:
|
||||
cmd.extend(["-k", keyword])
|
||||
|
||||
try:
|
||||
result = subprocess.run(cmd, capture_output=True, text=True)
|
||||
# Run subprocess with cwd set to project root
|
||||
result = subprocess.run(cmd, capture_output=True, text=True, cwd=project_root)
|
||||
print(f"Pytest exit code: {result.returncode}")
|
||||
|
||||
# Check if the JSON file was created
|
||||
if temp_json_file.exists():
|
||||
# Read the JSON file and save it to our results format
|
||||
with open(temp_json_file, "r") as f:
|
||||
test_results = json.load(f)
|
||||
|
||||
# Save results to our own format with a trailing newline
|
||||
test_results["run_timestamp"] = timestamp
|
||||
|
||||
# Save results to the final (overwritten) file
|
||||
with open(result_file, "w") as f:
|
||||
json.dump(test_results, f, indent=2)
|
||||
f.write("\n") # Add a trailing newline for precommit
|
||||
|
|
@ -103,18 +132,40 @@ def run_tests(provider):
|
|||
return None
|
||||
|
||||
|
||||
def parse_results(result_file):
|
||||
"""Parse the test results file and extract pass/fail by model and test"""
|
||||
def parse_results(
|
||||
result_file,
|
||||
) -> Tuple[DefaultDict[str, DefaultDict[str, Dict[str, bool]]], DefaultDict[str, Set[str]], Set[str], str]:
|
||||
"""Parse a single test results file.
|
||||
|
||||
Returns:
|
||||
Tuple containing:
|
||||
- parsed_results: DefaultDict[provider, DefaultDict[model, Dict[test_name, pass_status]]]
|
||||
- providers_in_file: DefaultDict[provider, Set[model]] found in this file.
|
||||
- tests_in_file: Set[test_name] found in this file.
|
||||
- run_timestamp: Timestamp when the test was run
|
||||
"""
|
||||
if not os.path.exists(result_file):
|
||||
print(f"Results file does not exist: {result_file}")
|
||||
return {}
|
||||
# Return empty defaultdicts/set matching the type hint
|
||||
return defaultdict(lambda: defaultdict(dict)), defaultdict(set), set(), ""
|
||||
|
||||
with open(result_file, "r") as f:
|
||||
results = json.load(f)
|
||||
|
||||
# Initialize results dictionary
|
||||
parsed_results = defaultdict(lambda: defaultdict(dict))
|
||||
provider = os.path.basename(result_file).split("_")[0]
|
||||
# Initialize results dictionary with specific types
|
||||
parsed_results: DefaultDict[str, DefaultDict[str, Dict[str, bool]]] = defaultdict(lambda: defaultdict(dict))
|
||||
providers_in_file: DefaultDict[str, Set[str]] = defaultdict(set)
|
||||
tests_in_file: Set[str] = set()
|
||||
# Extract provider from filename (e.g., "openai.json" -> "openai")
|
||||
provider: str = result_file.stem
|
||||
|
||||
# Extract run timestamp from the JSON data
|
||||
run_timestamp_unix = results.get("run_timestamp")
|
||||
run_timestamp_str = (
|
||||
time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(run_timestamp_unix))
|
||||
if run_timestamp_unix is not None
|
||||
else "Unknown"
|
||||
)
|
||||
|
||||
# Debug: Print summary of test results
|
||||
print(f"Test results summary for {provider}:")
|
||||
|
|
@ -127,195 +178,131 @@ def parse_results(result_file):
|
|||
# Extract test results
|
||||
if "tests" not in results or not results["tests"]:
|
||||
print(f"No test results found in {result_file}")
|
||||
return parsed_results
|
||||
# Return empty defaultdicts/set matching the type hint
|
||||
return defaultdict(lambda: defaultdict(dict)), defaultdict(set), set(), ""
|
||||
|
||||
# Map for normalizing model names
|
||||
model_name_map = {
|
||||
"Llama-3.3-8B-Instruct": "Llama-3.3-8B-Instruct",
|
||||
"Llama-3.3-70B-Instruct": "Llama-3.3-70B-Instruct",
|
||||
"Llama-3.2-11B-Vision-Instruct": "Llama-3.2-11B-Vision-Instruct",
|
||||
"Llama-4-Scout-17B-16E": "Llama-4-Scout-17B-16E-Instruct",
|
||||
"Llama-4-Scout-17B-16E-Instruct": "Llama-4-Scout-17B-16E-Instruct",
|
||||
"Llama-4-Maverick-17B-128E": "Llama-4-Maverick-17B-128E-Instruct",
|
||||
"Llama-4-Maverick-17B-128E-Instruct": "Llama-4-Maverick-17B-128E-Instruct",
|
||||
"gpt-4o": "gpt-4o",
|
||||
"gpt-4o-mini": "gpt-4o-mini",
|
||||
}
|
||||
|
||||
# Keep track of all models found for this provider
|
||||
provider_models = set()
|
||||
|
||||
# Track all unique test cases for each base test
|
||||
test_case_counts = defaultdict(int)
|
||||
|
||||
# First pass: count the number of cases for each test
|
||||
# Process the tests
|
||||
for test in results["tests"]:
|
||||
test_id = test.get("nodeid", "")
|
||||
|
||||
if "call" in test:
|
||||
test_name = test_id.split("::")[1].split("[")[0]
|
||||
input_output_match = re.search(r"\[input_output(\d+)-", test_id)
|
||||
if input_output_match:
|
||||
test_case_counts[test_name] += 1
|
||||
if not (call_phase := test.get("call")):
|
||||
continue
|
||||
call_outcome = call_phase.get("outcome")
|
||||
if call_outcome not in ("passed", "failed"):
|
||||
continue
|
||||
|
||||
# Second pass: process the tests with case numbers only for tests with multiple cases
|
||||
for test in results["tests"]:
|
||||
test_id = test.get("nodeid", "")
|
||||
outcome = test.get("outcome", "")
|
||||
# --- Extract data from metadata ---
|
||||
metadata = test.get("metadata", {})
|
||||
model = metadata.get("model")
|
||||
case_id = metadata.get("case_id") # String ID (if provided)
|
||||
case_index = metadata.get("case_index") # Integer index (if no ID provided)
|
||||
|
||||
# Only process tests that have been executed (not setup errors)
|
||||
if "call" in test:
|
||||
# Regular test that actually ran
|
||||
test_name = test_id.split("::")[1].split("[")[0]
|
||||
# Check if we have a model and at least one case identifier
|
||||
if not model or (case_id is None and case_index is None):
|
||||
print(
|
||||
f"Warning: Missing 'model' or case identifier ('case_id'/'case_index') metadata for test: {test_id}. Skipping."
|
||||
)
|
||||
continue
|
||||
|
||||
# Extract input_output parameter to differentiate between test cases
|
||||
input_output_match = re.search(r"\[input_output(\d+)-", test_id)
|
||||
input_output_index = input_output_match.group(1) if input_output_match else ""
|
||||
try:
|
||||
test_name_base = test_id.split("::")[1].split("[")[0]
|
||||
except (IndexError, ValueError) as e:
|
||||
print(f"Warning: Could not parse base test name for {test_id}. Error: {e}. Skipping.")
|
||||
continue
|
||||
|
||||
# Create a more detailed test name with case number only if there are multiple cases
|
||||
detailed_test_name = test_name
|
||||
if input_output_index and test_case_counts[test_name] > 1:
|
||||
detailed_test_name = f"{test_name} (case {input_output_index})"
|
||||
# Construct detailed test name using ID or index
|
||||
if case_id is not None:
|
||||
detailed_test_name = f"{test_name_base} ({case_id})"
|
||||
elif case_index == 0:
|
||||
# If case_id is missing and index is 0, assume single case, use base name only
|
||||
detailed_test_name = test_name_base
|
||||
elif case_index is not None: # case_index > 0
|
||||
# Use case_index for naming if case_id wasn't provided and index > 0
|
||||
detailed_test_name = f"{test_name_base} (case{case_index})"
|
||||
else:
|
||||
# This case should be prevented by the earlier check, but handle defensively
|
||||
print(f"Error: No case identifier found for test {test_id} after initial check. Skipping.")
|
||||
continue
|
||||
|
||||
# Track all unique test names
|
||||
ALL_TESTS.add(detailed_test_name)
|
||||
# Populate collections for this file
|
||||
tests_in_file.add(detailed_test_name)
|
||||
providers_in_file[provider].add(model)
|
||||
|
||||
# Extract model name from test_id using a more robust pattern
|
||||
model_match = re.search(r"\[input_output\d+-([^\]]+)\]", test_id)
|
||||
if model_match:
|
||||
raw_model = model_match.group(1)
|
||||
model = model_name_map.get(raw_model, raw_model)
|
||||
if call_outcome == "passed":
|
||||
parsed_results[provider][model][detailed_test_name] = True
|
||||
elif call_outcome == "failed":
|
||||
parsed_results[provider][model][detailed_test_name] = False
|
||||
|
||||
# Add to set of known models for this provider
|
||||
provider_models.add(model)
|
||||
# Final Summary Warning (Optional)
|
||||
if not parsed_results.get(provider):
|
||||
print(f"Warning: No valid test results parsed for provider {provider} from file {result_file}")
|
||||
|
||||
# Also update the global PROVIDERS dictionary
|
||||
PROVIDERS[provider].add(model)
|
||||
|
||||
# Store the result
|
||||
if outcome == "passed":
|
||||
parsed_results[provider][model][detailed_test_name] = True
|
||||
else:
|
||||
parsed_results[provider][model][detailed_test_name] = False
|
||||
|
||||
print(f"Parsed test result: {detailed_test_name} for model {model}: {outcome}")
|
||||
elif outcome == "error" and "setup" in test and test.get("setup", {}).get("outcome") == "failed":
|
||||
# This is a setup failure, which likely means a configuration issue
|
||||
# Extract the base test name and model name
|
||||
parts = test_id.split("::")
|
||||
if len(parts) > 1:
|
||||
test_name = parts[1].split("[")[0]
|
||||
|
||||
# Extract input_output parameter to differentiate between test cases
|
||||
input_output_match = re.search(r"\[input_output(\d+)-", test_id)
|
||||
input_output_index = input_output_match.group(1) if input_output_match else ""
|
||||
|
||||
# Create a more detailed test name with case number only if there are multiple cases
|
||||
detailed_test_name = test_name
|
||||
if input_output_index and test_case_counts[test_name] > 1:
|
||||
detailed_test_name = f"{test_name} (case {input_output_index})"
|
||||
|
||||
if detailed_test_name in ALL_TESTS:
|
||||
# Use a more robust pattern for model extraction
|
||||
model_match = re.search(r"\[input_output\d+-([^\]]+)\]", test_id)
|
||||
if model_match:
|
||||
raw_model = model_match.group(1)
|
||||
model = model_name_map.get(raw_model, raw_model)
|
||||
|
||||
# Add to set of known models for this provider
|
||||
provider_models.add(model)
|
||||
|
||||
# Also update the global PROVIDERS dictionary
|
||||
PROVIDERS[provider].add(model)
|
||||
|
||||
# Mark setup failures as false (failed)
|
||||
parsed_results[provider][model][detailed_test_name] = False
|
||||
print(f"Parsed setup failure: {detailed_test_name} for model {model}")
|
||||
|
||||
# Debug: Print parsed results
|
||||
if not parsed_results[provider]:
|
||||
print(f"Warning: No test results parsed for provider {provider}")
|
||||
else:
|
||||
for model, tests in parsed_results[provider].items():
|
||||
print(f"Model {model}: {len(tests)} test results")
|
||||
|
||||
return parsed_results
|
||||
return parsed_results, providers_in_file, tests_in_file, run_timestamp_str
|
||||
|
||||
|
||||
def cleanup_old_results():
|
||||
"""Clean up old test result files, keeping only the newest N per provider"""
|
||||
for provider in PROVIDERS.keys():
|
||||
# Get all result files for this provider
|
||||
provider_files = list(RESULTS_DIR.glob(f"{provider}_*.json"))
|
||||
|
||||
# Sort by timestamp (newest first)
|
||||
provider_files.sort(key=lambda x: int(x.stem.split("_")[1]), reverse=True)
|
||||
|
||||
# Remove old files beyond the max to keep
|
||||
if len(provider_files) > MAX_RESULTS_PER_PROVIDER:
|
||||
for old_file in provider_files[MAX_RESULTS_PER_PROVIDER:]:
|
||||
try:
|
||||
old_file.unlink()
|
||||
print(f"Removed old result file: {old_file}")
|
||||
except Exception as e:
|
||||
print(f"Error removing file {old_file}: {e}")
|
||||
|
||||
|
||||
def get_latest_results_by_provider():
|
||||
"""Get the latest test result file for each provider"""
|
||||
def get_all_result_files_by_provider():
|
||||
"""Get all test result files, keyed by provider."""
|
||||
provider_results = {}
|
||||
|
||||
# Get all result files
|
||||
result_files = list(RESULTS_DIR.glob("*.json"))
|
||||
|
||||
# Extract all provider names from filenames
|
||||
all_providers = set()
|
||||
for file in result_files:
|
||||
# File format is provider_timestamp.json
|
||||
parts = file.stem.split("_")
|
||||
if len(parts) >= 2:
|
||||
all_providers.add(parts[0])
|
||||
|
||||
# Group by provider
|
||||
for provider in all_providers:
|
||||
provider_files = [f for f in result_files if f.name.startswith(f"{provider}_")]
|
||||
|
||||
# Sort by timestamp (newest first)
|
||||
provider_files.sort(key=lambda x: int(x.stem.split("_")[1]), reverse=True)
|
||||
|
||||
if provider_files:
|
||||
provider_results[provider] = provider_files[0]
|
||||
provider = file.stem
|
||||
if provider:
|
||||
provider_results[provider] = file
|
||||
|
||||
return provider_results
|
||||
|
||||
|
||||
def generate_report(results_dict, output_file=None):
|
||||
"""Generate the markdown report"""
|
||||
def generate_report(
|
||||
results_dict: Dict[str, Any],
|
||||
providers: Dict[str, Set[str]],
|
||||
all_tests: Set[str],
|
||||
provider_timestamps: Dict[str, str],
|
||||
output_file=None,
|
||||
):
|
||||
"""Generate the markdown report.
|
||||
|
||||
Args:
|
||||
results_dict: Aggregated results [provider][model][test_name] -> status.
|
||||
providers: Dict of all providers and their models {provider: {models}}.
|
||||
all_tests: Set of all test names found.
|
||||
provider_timestamps: Dict of provider to timestamp when tests were run
|
||||
output_file: Optional path to save the report.
|
||||
"""
|
||||
if output_file is None:
|
||||
# Default to creating the report in the same directory as this script
|
||||
output_file = Path(__file__).parent / "REPORT.md"
|
||||
else:
|
||||
output_file = Path(output_file)
|
||||
|
||||
# Get the timestamp from result files
|
||||
provider_timestamps = {}
|
||||
provider_results = get_latest_results_by_provider()
|
||||
for provider, result_file in provider_results.items():
|
||||
# Extract timestamp from filename (format: provider_timestamp.json)
|
||||
try:
|
||||
timestamp_str = result_file.stem.split("_")[1]
|
||||
timestamp = int(timestamp_str)
|
||||
formatted_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(timestamp))
|
||||
provider_timestamps[provider] = formatted_time
|
||||
except (IndexError, ValueError):
|
||||
provider_timestamps[provider] = "Unknown"
|
||||
# Convert provider model sets to sorted lists (use passed-in providers dict)
|
||||
providers_sorted = {prov: sorted(models) for prov, models in providers.items()}
|
||||
|
||||
# Convert provider model sets to sorted lists
|
||||
for provider in PROVIDERS:
|
||||
PROVIDERS[provider] = sorted(PROVIDERS[provider])
|
||||
# Sort tests alphabetically (use passed-in all_tests set)
|
||||
sorted_tests = sorted(all_tests)
|
||||
|
||||
# Sort tests alphabetically
|
||||
sorted_tests = sorted(ALL_TESTS)
|
||||
# Calculate counts for each base test name
|
||||
base_test_case_counts: DefaultDict[str, int] = defaultdict(int)
|
||||
base_test_name_map: Dict[str, str] = {}
|
||||
for test_name in sorted_tests:
|
||||
match = re.match(r"^(.*?)( \([^)]+\))?$", test_name)
|
||||
if match:
|
||||
base_name = match.group(1).strip()
|
||||
base_test_case_counts[base_name] += 1
|
||||
base_test_name_map[test_name] = base_name
|
||||
else:
|
||||
# Should not happen with current naming, but handle defensively
|
||||
base_test_case_counts[test_name] += 1
|
||||
base_test_name_map[test_name] = test_name
|
||||
|
||||
if not sorted_tests:
|
||||
print("Warning: No test results found to generate a report.")
|
||||
# Optionally create an empty report or return early
|
||||
with open(output_file, "w") as f:
|
||||
f.write("# Test Results Report\n\nNo test results found.\n")
|
||||
print(f"Generated empty report: {output_file}")
|
||||
return
|
||||
|
||||
report = ["# Test Results Report\n"]
|
||||
report.append(f"*Generated on: {time.strftime('%Y-%m-%d %H:%M:%S')}*\n")
|
||||
|
|
@ -336,19 +323,15 @@ def generate_report(results_dict, output_file=None):
|
|||
# Add a summary section
|
||||
report.append("## Summary\n")
|
||||
|
||||
# Count total tests and passes
|
||||
# Count total tests and passes (use passed-in providers and all_tests)
|
||||
total_tests = 0
|
||||
passed_tests = 0
|
||||
provider_totals = {}
|
||||
|
||||
# Prepare summary data
|
||||
for provider in PROVIDERS.keys():
|
||||
for provider, models in providers_sorted.items():
|
||||
provider_passed = 0
|
||||
provider_total = 0
|
||||
|
||||
if provider in results_dict:
|
||||
provider_models = PROVIDERS[provider]
|
||||
for model in provider_models:
|
||||
for model in models:
|
||||
if model in results_dict[provider]:
|
||||
model_results = results_dict[provider][model]
|
||||
for test in sorted_tests:
|
||||
|
|
@ -358,33 +341,26 @@ def generate_report(results_dict, output_file=None):
|
|||
if model_results[test]:
|
||||
provider_passed += 1
|
||||
passed_tests += 1
|
||||
|
||||
provider_totals[provider] = (provider_passed, provider_total)
|
||||
|
||||
# Add summary table
|
||||
# Add summary table (use passed-in providers dict)
|
||||
report.append("| Provider | Pass Rate | Tests Passed | Total Tests |")
|
||||
report.append("| --- | --- | --- | --- |")
|
||||
|
||||
# Use the custom order for summary table
|
||||
for provider in [p for p in PROVIDER_ORDER if p in PROVIDERS]:
|
||||
for provider in [p for p in PROVIDER_ORDER if p in providers]: # Check against keys of passed-in dict
|
||||
passed, total = provider_totals.get(provider, (0, 0))
|
||||
pass_rate = f"{(passed / total * 100):.1f}%" if total > 0 else "N/A"
|
||||
report.append(f"| {provider.capitalize()} | {pass_rate} | {passed} | {total} |")
|
||||
|
||||
# Add providers not in the custom order
|
||||
for provider in [p for p in PROVIDERS if p not in PROVIDER_ORDER]:
|
||||
for provider in [p for p in providers if p not in PROVIDER_ORDER]: # Check against keys of passed-in dict
|
||||
passed, total = provider_totals.get(provider, (0, 0))
|
||||
pass_rate = f"{(passed / total * 100):.1f}%" if total > 0 else "N/A"
|
||||
report.append(f"| {provider.capitalize()} | {pass_rate} | {passed} | {total} |")
|
||||
|
||||
report.append("\n")
|
||||
|
||||
# Process each provider in the custom order, then any additional providers
|
||||
for provider in sorted(
|
||||
PROVIDERS.keys(), key=lambda p: (PROVIDER_ORDER.index(p) if p in PROVIDER_ORDER else float("inf"), p)
|
||||
providers_sorted.keys(), key=lambda p: (PROVIDER_ORDER.index(p) if p in PROVIDER_ORDER else float("inf"), p)
|
||||
):
|
||||
if not PROVIDERS[provider]:
|
||||
# Skip providers with no models
|
||||
provider_models = providers_sorted[provider] # Use sorted models
|
||||
if not provider_models:
|
||||
continue
|
||||
|
||||
report.append(f"\n## {provider.capitalize()}\n")
|
||||
|
|
@ -394,34 +370,70 @@ def generate_report(results_dict, output_file=None):
|
|||
report.append(f"*Tests run on: {provider_timestamps[provider]}*\n")
|
||||
|
||||
# Add test command for reproducing results
|
||||
test_cmd = f"pytest tests/verifications/openai/test_chat_completion.py --provider={provider} -v"
|
||||
report.append(f"```bash\n{test_cmd}\n```\n")
|
||||
test_cmd_all = f"pytest tests/verifications/openai_api/test_chat_completion.py --provider={provider} -v"
|
||||
report.append(f"```bash\n# Run all tests for this provider:\n{test_cmd_all}\n")
|
||||
|
||||
# Get the relevant models for this provider
|
||||
provider_models = PROVIDERS[provider]
|
||||
# Find an example test with a case ID
|
||||
example_base_test_name = None
|
||||
example_case_id = None
|
||||
# Get first test as fallback base, handle empty list
|
||||
first_test_name = sorted_tests[0] if sorted_tests else "unknown_test"
|
||||
|
||||
# Create table header with models as columns
|
||||
header = "| Test | " + " | ".join(provider_models) + " |"
|
||||
match = re.match(r"^(.*?) \((.*?)\)$", first_test_name)
|
||||
if match:
|
||||
example_base_test_name = match.group(1).strip()
|
||||
example_case_id = match.group(2).strip()
|
||||
else:
|
||||
example_base_test_name = first_test_name
|
||||
|
||||
base_name = base_test_name_map.get(first_test_name, first_test_name) # Get base name
|
||||
case_count = base_test_case_counts.get(base_name, 1) # Get count
|
||||
filter_str = f"{example_base_test_name} and {example_case_id}" if case_count > 1 else example_base_test_name
|
||||
|
||||
test_cmd_specific_case = (
|
||||
f'pytest tests/verifications/openai_api/test_chat_completion.py --provider={provider} -k "{filter_str}"'
|
||||
)
|
||||
report.append(
|
||||
f"# Example: Run only the '{example_case_id}' case of {example_base_test_name}:\n{test_cmd_specific_case}\n```\n"
|
||||
)
|
||||
|
||||
# Get display names (use passed-in providers dict)
|
||||
provider_config = VERIFICATION_CONFIG.get("providers", {}).get(provider, {})
|
||||
display_name_map = provider_config.get("model_display_names", {})
|
||||
|
||||
# Add Model Key Table (use provider_models)
|
||||
report.append(f"\n**Model Key ({provider.capitalize()})**\n")
|
||||
provider_key_lines = ["| Display Name | Full Model ID |", "| --- | --- |"]
|
||||
for model_id in provider_models:
|
||||
display_name = display_name_map.get(model_id, model_id)
|
||||
provider_key_lines.append(f"| {display_name} | `{model_id}` |")
|
||||
report.extend(provider_key_lines)
|
||||
report.append("\n")
|
||||
|
||||
# Create results table header (use provider_models)
|
||||
display_names = [display_name_map.get(m, m) for m in provider_models]
|
||||
header = "| Test | " + " | ".join(display_names) + " |"
|
||||
separator = "| --- | " + " | ".join(["---"] * len(provider_models)) + " |"
|
||||
|
||||
report.append(header)
|
||||
report.append(separator)
|
||||
|
||||
# Get results for this provider
|
||||
provider_results = results_dict.get(provider, {})
|
||||
# Get results for this provider from results_dict
|
||||
provider_results_data = results_dict.get(provider, {})
|
||||
|
||||
# Add rows for each test
|
||||
# Add rows for each test (use sorted_tests)
|
||||
for test in sorted_tests:
|
||||
row = f"| {test} |"
|
||||
# Determine display name based on case count
|
||||
base_name = base_test_name_map.get(test, test) # Get base name
|
||||
case_count = base_test_case_counts.get(base_name, 1) # Get count
|
||||
display_test_name = base_name if case_count == 1 else test # Choose display name
|
||||
row = f"| {display_test_name} |" # Use display name
|
||||
|
||||
# Add results for each model in this test
|
||||
for model in provider_models:
|
||||
if model in provider_results and test in provider_results[model]:
|
||||
result = pass_icon if provider_results[model][test] else fail_icon
|
||||
for model_id in provider_models:
|
||||
if model_id in provider_results_data and test in provider_results_data[model_id]:
|
||||
result = pass_icon if provider_results_data[model_id][test] else fail_icon
|
||||
else:
|
||||
result = na_icon
|
||||
row += f" {result} |"
|
||||
|
||||
report.append(row)
|
||||
|
||||
# Write to file
|
||||
|
|
@ -442,9 +454,14 @@ def main():
|
|||
help="Specify providers to test (comma-separated or space-separated, default: all)",
|
||||
)
|
||||
parser.add_argument("--output", type=str, help="Output file location (default: tests/verifications/REPORT.md)")
|
||||
parser.add_argument("--k", type=str, help="Keyword expression to filter tests (passed to pytest -k)")
|
||||
args = parser.parse_args()
|
||||
|
||||
all_results = {}
|
||||
# Initialize collections to aggregate results in main
|
||||
aggregated_providers = defaultdict(set)
|
||||
aggregated_tests = set()
|
||||
provider_timestamps = {}
|
||||
|
||||
if args.run_tests:
|
||||
# Get list of available providers from command line or use detected providers
|
||||
|
|
@ -463,22 +480,31 @@ def main():
|
|||
|
||||
for provider in test_providers:
|
||||
provider = provider.strip() # Remove any whitespace
|
||||
result_file = run_tests(provider)
|
||||
result_file = run_tests(provider, keyword=args.k)
|
||||
if result_file:
|
||||
provider_results = parse_results(result_file)
|
||||
all_results.update(provider_results)
|
||||
# Parse and aggregate results
|
||||
parsed_results, providers_in_file, tests_in_file, run_timestamp = parse_results(result_file)
|
||||
all_results.update(parsed_results)
|
||||
for prov, models in providers_in_file.items():
|
||||
aggregated_providers[prov].update(models)
|
||||
if run_timestamp:
|
||||
provider_timestamps[prov] = run_timestamp
|
||||
aggregated_tests.update(tests_in_file)
|
||||
else:
|
||||
# Use existing results
|
||||
provider_result_files = get_latest_results_by_provider()
|
||||
provider_result_files = get_all_result_files_by_provider()
|
||||
|
||||
for result_file in provider_result_files.values():
|
||||
provider_results = parse_results(result_file)
|
||||
all_results.update(provider_results)
|
||||
# Parse and aggregate results
|
||||
parsed_results, providers_in_file, tests_in_file, run_timestamp = parse_results(result_file)
|
||||
all_results.update(parsed_results)
|
||||
for prov, models in providers_in_file.items():
|
||||
aggregated_providers[prov].update(models)
|
||||
if run_timestamp:
|
||||
provider_timestamps[prov] = run_timestamp
|
||||
aggregated_tests.update(tests_in_file)
|
||||
|
||||
# Generate the report
|
||||
generate_report(all_results, args.output)
|
||||
|
||||
cleanup_old_results()
|
||||
generate_report(all_results, aggregated_providers, aggregated_tests, provider_timestamps, args.output)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
|
|
|||
|
|
@ -1,97 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import os
|
||||
|
||||
import pytest
|
||||
from openai import OpenAI
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def providers_model_mapping():
|
||||
"""
|
||||
Mapping from model names used in test cases to provider's model names.
|
||||
"""
|
||||
return {
|
||||
"fireworks": {
|
||||
"Llama-3.3-70B-Instruct": "accounts/fireworks/models/llama-v3p1-70b-instruct",
|
||||
"Llama-3.2-11B-Vision-Instruct": "accounts/fireworks/models/llama-v3p2-11b-vision-instruct",
|
||||
"Llama-4-Scout-17B-16E-Instruct": "accounts/fireworks/models/llama4-scout-instruct-basic",
|
||||
"Llama-4-Maverick-17B-128E-Instruct": "accounts/fireworks/models/llama4-maverick-instruct-basic",
|
||||
},
|
||||
"together": {
|
||||
"Llama-3.3-70B-Instruct": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
||||
"Llama-3.2-11B-Vision-Instruct": "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
|
||||
"Llama-4-Scout-17B-16E-Instruct": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
|
||||
"Llama-4-Maverick-17B-128E-Instruct": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
},
|
||||
"groq": {
|
||||
"Llama-3.3-70B-Instruct": "llama-3.3-70b-versatile",
|
||||
"Llama-3.2-11B-Vision-Instruct": "llama-3.2-11b-vision-preview",
|
||||
"Llama-4-Scout-17B-16E-Instruct": "llama-4-scout-17b-16e-instruct",
|
||||
"Llama-4-Maverick-17B-128E-Instruct": "llama-4-maverick-17b-128e-instruct",
|
||||
},
|
||||
"cerebras": {
|
||||
"Llama-3.3-70B-Instruct": "llama-3.3-70b",
|
||||
},
|
||||
"openai": {
|
||||
"gpt-4o": "gpt-4o",
|
||||
"gpt-4o-mini": "gpt-4o-mini",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def provider_metadata():
|
||||
return {
|
||||
"fireworks": ("https://api.fireworks.ai/inference/v1", "FIREWORKS_API_KEY"),
|
||||
"together": ("https://api.together.xyz/v1", "TOGETHER_API_KEY"),
|
||||
"groq": ("https://api.groq.com/openai/v1", "GROQ_API_KEY"),
|
||||
"cerebras": ("https://api.cerebras.ai/v1", "CEREBRAS_API_KEY"),
|
||||
"openai": ("https://api.openai.com/v1", "OPENAI_API_KEY"),
|
||||
}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def provider(request, provider_metadata):
|
||||
provider = request.config.getoption("--provider")
|
||||
base_url = request.config.getoption("--base-url")
|
||||
|
||||
if provider and base_url and provider_metadata[provider][0] != base_url:
|
||||
raise ValueError(f"Provider {provider} is not supported for base URL {base_url}")
|
||||
|
||||
if not provider:
|
||||
if not base_url:
|
||||
raise ValueError("Provider and base URL are not provided")
|
||||
for provider, metadata in provider_metadata.items():
|
||||
if metadata[0] == base_url:
|
||||
provider = provider
|
||||
break
|
||||
|
||||
return provider
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def base_url(request, provider, provider_metadata):
|
||||
return request.config.getoption("--base-url") or provider_metadata[provider][0]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def api_key(request, provider, provider_metadata):
|
||||
return request.config.getoption("--api-key") or os.getenv(provider_metadata[provider][1])
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def model_mapping(provider, providers_model_mapping):
|
||||
return providers_model_mapping[provider]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def openai_client(base_url, api_key):
|
||||
return OpenAI(
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
)
|
||||
|
|
@ -1,202 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
from pydantic import BaseModel
|
||||
|
||||
from tests.verifications.openai.fixtures.load import load_test_cases
|
||||
|
||||
chat_completion_test_cases = load_test_cases("chat_completion")
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def correct_model_name(model, provider, providers_model_mapping):
|
||||
"""Return the provider-specific model name based on the generic model name."""
|
||||
mapping = providers_model_mapping[provider]
|
||||
if model not in mapping:
|
||||
pytest.skip(f"Provider {provider} does not support model {model}")
|
||||
return mapping[model]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", chat_completion_test_cases["test_chat_basic"]["test_params"]["model"])
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_chat_basic"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_non_streaming_basic(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
stream=False,
|
||||
)
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
assert input_output["output"].lower() in response.choices[0].message.content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", chat_completion_test_cases["test_chat_basic"]["test_params"]["model"])
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_chat_basic"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_streaming_basic(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
stream=True,
|
||||
)
|
||||
content = ""
|
||||
for chunk in response:
|
||||
content += chunk.choices[0].delta.content or ""
|
||||
|
||||
# TODO: add detailed type validation
|
||||
|
||||
assert input_output["output"].lower() in content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", chat_completion_test_cases["test_chat_image"]["test_params"]["model"])
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_chat_image"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_non_streaming_image(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
stream=False,
|
||||
)
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
assert input_output["output"].lower() in response.choices[0].message.content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", chat_completion_test_cases["test_chat_image"]["test_params"]["model"])
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_chat_image"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_streaming_image(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
stream=True,
|
||||
)
|
||||
content = ""
|
||||
for chunk in response:
|
||||
content += chunk.choices[0].delta.content or ""
|
||||
|
||||
# TODO: add detailed type validation
|
||||
|
||||
assert input_output["output"].lower() in content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"model",
|
||||
chat_completion_test_cases["test_chat_structured_output"]["test_params"]["model"],
|
||||
)
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_chat_structured_output"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_non_streaming_structured_output(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
response_format=input_output["input"]["response_format"],
|
||||
stream=False,
|
||||
)
|
||||
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
maybe_json_content = response.choices[0].message.content
|
||||
|
||||
validate_structured_output(maybe_json_content, input_output["output"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"model",
|
||||
chat_completion_test_cases["test_chat_structured_output"]["test_params"]["model"],
|
||||
)
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_chat_structured_output"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_streaming_structured_output(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
response_format=input_output["input"]["response_format"],
|
||||
stream=True,
|
||||
)
|
||||
maybe_json_content = ""
|
||||
for chunk in response:
|
||||
maybe_json_content += chunk.choices[0].delta.content or ""
|
||||
validate_structured_output(maybe_json_content, input_output["output"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"model",
|
||||
chat_completion_test_cases["test_tool_calling"]["test_params"]["model"],
|
||||
)
|
||||
@pytest.mark.parametrize(
|
||||
"input_output",
|
||||
chat_completion_test_cases["test_tool_calling"]["test_params"]["input_output"],
|
||||
)
|
||||
def test_chat_non_streaming_tool_calling(openai_client, input_output, correct_model_name):
|
||||
response = openai_client.chat.completions.create(
|
||||
model=correct_model_name,
|
||||
messages=input_output["input"]["messages"],
|
||||
tools=input_output["input"]["tools"],
|
||||
stream=False,
|
||||
)
|
||||
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
assert len(response.choices[0].message.tool_calls) > 0
|
||||
assert input_output["output"] == "get_weather_tool_call"
|
||||
assert response.choices[0].message.tool_calls[0].function.name == "get_weather"
|
||||
# TODO: add detailed type validation
|
||||
|
||||
|
||||
def get_structured_output(maybe_json_content: str, schema_name: str) -> Any | None:
|
||||
if schema_name == "valid_calendar_event":
|
||||
|
||||
class CalendarEvent(BaseModel):
|
||||
name: str
|
||||
date: str
|
||||
participants: list[str]
|
||||
|
||||
try:
|
||||
calendar_event = CalendarEvent.model_validate_json(maybe_json_content)
|
||||
return calendar_event
|
||||
except Exception:
|
||||
return None
|
||||
elif schema_name == "valid_math_reasoning":
|
||||
|
||||
class Step(BaseModel):
|
||||
explanation: str
|
||||
output: str
|
||||
|
||||
class MathReasoning(BaseModel):
|
||||
steps: list[Step]
|
||||
final_answer: str
|
||||
|
||||
try:
|
||||
math_reasoning = MathReasoning.model_validate_json(maybe_json_content)
|
||||
return math_reasoning
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def validate_structured_output(maybe_json_content: str, schema_name: str) -> None:
|
||||
structured_output = get_structured_output(maybe_json_content, schema_name)
|
||||
assert structured_output is not None
|
||||
if schema_name == "valid_calendar_event":
|
||||
assert structured_output.name is not None
|
||||
assert structured_output.date is not None
|
||||
assert len(structured_output.participants) == 2
|
||||
elif schema_name == "valid_math_reasoning":
|
||||
assert len(structured_output.final_answer) > 0
|
||||
105
tests/verifications/openai_api/fixtures/fixtures.py
Normal file
105
tests/verifications/openai_api/fixtures/fixtures.py
Normal file
|
|
@ -0,0 +1,105 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
import yaml
|
||||
from openai import OpenAI
|
||||
|
||||
|
||||
# --- Helper Function to Load Config ---
|
||||
def _load_all_verification_configs():
|
||||
"""Load and aggregate verification configs from the conf/ directory."""
|
||||
# Note: Path is relative to *this* file (fixtures.py)
|
||||
conf_dir = Path(__file__).parent.parent.parent / "conf"
|
||||
if not conf_dir.is_dir():
|
||||
# Use pytest.fail if called during test collection, otherwise raise error
|
||||
# For simplicity here, we'll raise an error, assuming direct calls
|
||||
# are less likely or can handle it.
|
||||
raise FileNotFoundError(f"Verification config directory not found at {conf_dir}")
|
||||
|
||||
all_provider_configs = {}
|
||||
yaml_files = list(conf_dir.glob("*.yaml"))
|
||||
if not yaml_files:
|
||||
raise FileNotFoundError(f"No YAML configuration files found in {conf_dir}")
|
||||
|
||||
for config_path in yaml_files:
|
||||
provider_name = config_path.stem
|
||||
try:
|
||||
with open(config_path, "r") as f:
|
||||
provider_config = yaml.safe_load(f)
|
||||
if provider_config:
|
||||
all_provider_configs[provider_name] = provider_config
|
||||
else:
|
||||
# Log warning if possible, or just skip empty files silently
|
||||
print(f"Warning: Config file {config_path} is empty or invalid.")
|
||||
except Exception as e:
|
||||
raise IOError(f"Error loading config file {config_path}: {e}") from e
|
||||
|
||||
return {"providers": all_provider_configs}
|
||||
|
||||
|
||||
# --- End Helper Function ---
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def verification_config():
|
||||
"""Pytest fixture to provide the loaded verification config."""
|
||||
try:
|
||||
return _load_all_verification_configs()
|
||||
except (FileNotFoundError, IOError) as e:
|
||||
pytest.fail(str(e)) # Fail test collection if config loading fails
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def provider(request, verification_config):
|
||||
provider = request.config.getoption("--provider")
|
||||
base_url = request.config.getoption("--base-url")
|
||||
|
||||
if provider and base_url and verification_config["providers"][provider]["base_url"] != base_url:
|
||||
raise ValueError(f"Provider {provider} is not supported for base URL {base_url}")
|
||||
|
||||
if not provider:
|
||||
if not base_url:
|
||||
raise ValueError("Provider and base URL are not provided")
|
||||
for provider, metadata in verification_config["providers"].items():
|
||||
if metadata["base_url"] == base_url:
|
||||
provider = provider
|
||||
break
|
||||
|
||||
return provider
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def base_url(request, provider, verification_config):
|
||||
return request.config.getoption("--base-url") or verification_config["providers"][provider]["base_url"]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def api_key(request, provider, verification_config):
|
||||
provider_conf = verification_config.get("providers", {}).get(provider, {})
|
||||
api_key_env_var = provider_conf.get("api_key_var")
|
||||
|
||||
key_from_option = request.config.getoption("--api-key")
|
||||
key_from_env = os.getenv(api_key_env_var) if api_key_env_var else None
|
||||
|
||||
final_key = key_from_option or key_from_env
|
||||
return final_key
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def model_mapping(provider, providers_model_mapping):
|
||||
return providers_model_mapping[provider]
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def openai_client(base_url, api_key):
|
||||
return OpenAI(
|
||||
base_url=base_url,
|
||||
api_key=api_key,
|
||||
)
|
||||
|
|
@ -1,31 +1,24 @@
|
|||
test_chat_basic:
|
||||
test_name: test_chat_basic
|
||||
test_params:
|
||||
input_output:
|
||||
- input:
|
||||
case:
|
||||
- case_id: "earth"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet do humans live on?
|
||||
role: user
|
||||
output: Earth
|
||||
- input:
|
||||
- case_id: "saturn"
|
||||
input:
|
||||
messages:
|
||||
- content: Which planet has rings around it with a name starting with letter
|
||||
S?
|
||||
role: user
|
||||
output: Saturn
|
||||
model:
|
||||
- Llama-3.3-8B-Instruct
|
||||
- Llama-3.3-70B-Instruct
|
||||
- Llama-4-Scout-17B-16E
|
||||
- Llama-4-Scout-17B-16E-Instruct
|
||||
- Llama-4-Maverick-17B-128E
|
||||
- Llama-4-Maverick-17B-128E-Instruct
|
||||
- gpt-4o
|
||||
- gpt-4o-mini
|
||||
test_chat_image:
|
||||
test_name: test_chat_image
|
||||
test_params:
|
||||
input_output:
|
||||
case:
|
||||
- input:
|
||||
messages:
|
||||
- content:
|
||||
|
|
@ -36,18 +29,12 @@ test_chat_image:
|
|||
type: image_url
|
||||
role: user
|
||||
output: llama
|
||||
model:
|
||||
- Llama-4-Scout-17B-16E
|
||||
- Llama-4-Scout-17B-16E-Instruct
|
||||
- Llama-4-Maverick-17B-128E
|
||||
- Llama-4-Maverick-17B-128E-Instruct
|
||||
- gpt-4o
|
||||
- gpt-4o-mini
|
||||
test_chat_structured_output:
|
||||
test_name: test_chat_structured_output
|
||||
test_params:
|
||||
input_output:
|
||||
- input:
|
||||
case:
|
||||
- case_id: "calendar"
|
||||
input:
|
||||
messages:
|
||||
- content: Extract the event information.
|
||||
role: system
|
||||
|
|
@ -77,7 +64,8 @@ test_chat_structured_output:
|
|||
type: object
|
||||
type: json_schema
|
||||
output: valid_calendar_event
|
||||
- input:
|
||||
- case_id: "math"
|
||||
input:
|
||||
messages:
|
||||
- content: You are a helpful math tutor. Guide the user through the solution
|
||||
step by step.
|
||||
|
|
@ -118,19 +106,10 @@ test_chat_structured_output:
|
|||
type: object
|
||||
type: json_schema
|
||||
output: valid_math_reasoning
|
||||
model:
|
||||
- Llama-3.3-8B-Instruct
|
||||
- Llama-3.3-70B-Instruct
|
||||
- Llama-4-Scout-17B-16E
|
||||
- Llama-4-Scout-17B-16E-Instruct
|
||||
- Llama-4-Maverick-17B-128E
|
||||
- Llama-4-Maverick-17B-128E-Instruct
|
||||
- gpt-4o
|
||||
- gpt-4o-mini
|
||||
test_tool_calling:
|
||||
test_name: test_tool_calling
|
||||
test_params:
|
||||
input_output:
|
||||
case:
|
||||
- input:
|
||||
messages:
|
||||
- content: You are a helpful assistant that can use tools to get information.
|
||||
|
|
@ -152,11 +131,3 @@ test_tool_calling:
|
|||
type: object
|
||||
type: function
|
||||
output: get_weather_tool_call
|
||||
model:
|
||||
- Llama-3.3-70B-Instruct
|
||||
- Llama-4-Scout-17B-16E
|
||||
- Llama-4-Scout-17B-16E-Instruct
|
||||
- Llama-4-Maverick-17B-128E
|
||||
- Llama-4-Maverick-17B-128E-Instruct
|
||||
- gpt-4o
|
||||
- gpt-4o-mini
|
||||
326
tests/verifications/openai_api/test_chat_completion.py
Normal file
326
tests/verifications/openai_api/test_chat_completion.py
Normal file
|
|
@ -0,0 +1,326 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import json
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
import pytest
|
||||
from pydantic import BaseModel
|
||||
|
||||
from tests.verifications.openai_api.fixtures.fixtures import _load_all_verification_configs
|
||||
from tests.verifications.openai_api.fixtures.load import load_test_cases
|
||||
|
||||
chat_completion_test_cases = load_test_cases("chat_completion")
|
||||
|
||||
|
||||
def case_id_generator(case):
|
||||
"""Generate a test ID from the case's 'case_id' field, or use a default."""
|
||||
case_id = case.get("case_id")
|
||||
if isinstance(case_id, (str, int)):
|
||||
return re.sub(r"\\W|^(?=\\d)", "_", str(case_id))
|
||||
return None
|
||||
|
||||
|
||||
def pytest_generate_tests(metafunc):
|
||||
"""Dynamically parametrize tests based on the selected provider and config."""
|
||||
if "model" in metafunc.fixturenames:
|
||||
provider = metafunc.config.getoption("provider")
|
||||
if not provider:
|
||||
print("Warning: --provider not specified. Skipping model parametrization.")
|
||||
metafunc.parametrize("model", [])
|
||||
return
|
||||
|
||||
try:
|
||||
config_data = _load_all_verification_configs()
|
||||
except (FileNotFoundError, IOError) as e:
|
||||
print(f"ERROR loading verification configs: {e}")
|
||||
config_data = {"providers": {}}
|
||||
|
||||
provider_config = config_data.get("providers", {}).get(provider)
|
||||
if provider_config:
|
||||
models = provider_config.get("models", [])
|
||||
if models:
|
||||
metafunc.parametrize("model", models)
|
||||
else:
|
||||
print(f"Warning: No models found for provider '{provider}' in config.")
|
||||
metafunc.parametrize("model", []) # Parametrize empty if no models found
|
||||
else:
|
||||
print(f"Warning: Provider '{provider}' not found in config. No models parametrized.")
|
||||
metafunc.parametrize("model", []) # Parametrize empty if provider not found
|
||||
|
||||
|
||||
def should_skip_test(verification_config, provider, model, test_name_base):
|
||||
"""Check if a test should be skipped based on config exclusions."""
|
||||
provider_config = verification_config.get("providers", {}).get(provider)
|
||||
if not provider_config:
|
||||
return False # No config for provider, don't skip
|
||||
|
||||
exclusions = provider_config.get("test_exclusions", {}).get(model, [])
|
||||
return test_name_base in exclusions
|
||||
|
||||
|
||||
# Helper to get the base test name from the request object
|
||||
def get_base_test_name(request):
|
||||
return request.node.originalname
|
||||
|
||||
|
||||
# --- Test Functions ---
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_chat_basic"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_non_streaming_basic(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
stream=False,
|
||||
)
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
assert case["output"].lower() in response.choices[0].message.content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_chat_basic"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_streaming_basic(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
stream=True,
|
||||
)
|
||||
content = ""
|
||||
for chunk in response:
|
||||
content += chunk.choices[0].delta.content or ""
|
||||
|
||||
# TODO: add detailed type validation
|
||||
|
||||
assert case["output"].lower() in content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_chat_image"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_non_streaming_image(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
stream=False,
|
||||
)
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
assert case["output"].lower() in response.choices[0].message.content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_chat_image"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_streaming_image(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
stream=True,
|
||||
)
|
||||
content = ""
|
||||
for chunk in response:
|
||||
content += chunk.choices[0].delta.content or ""
|
||||
|
||||
# TODO: add detailed type validation
|
||||
|
||||
assert case["output"].lower() in content.lower()
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_chat_structured_output"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_non_streaming_structured_output(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
response_format=case["input"]["response_format"],
|
||||
stream=False,
|
||||
)
|
||||
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
maybe_json_content = response.choices[0].message.content
|
||||
|
||||
validate_structured_output(maybe_json_content, case["output"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_chat_structured_output"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_streaming_structured_output(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
response_format=case["input"]["response_format"],
|
||||
stream=True,
|
||||
)
|
||||
maybe_json_content = ""
|
||||
for chunk in response:
|
||||
maybe_json_content += chunk.choices[0].delta.content or ""
|
||||
validate_structured_output(maybe_json_content, case["output"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_tool_calling"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_non_streaming_tool_calling(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
response = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
tools=case["input"]["tools"],
|
||||
stream=False,
|
||||
)
|
||||
|
||||
assert response.choices[0].message.role == "assistant"
|
||||
assert len(response.choices[0].message.tool_calls) > 0
|
||||
assert case["output"] == "get_weather_tool_call"
|
||||
assert response.choices[0].message.tool_calls[0].function.name == "get_weather"
|
||||
# TODO: add detailed type validation
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"case",
|
||||
chat_completion_test_cases["test_tool_calling"]["test_params"]["case"],
|
||||
ids=case_id_generator,
|
||||
)
|
||||
def test_chat_streaming_tool_calling(request, openai_client, model, provider, verification_config, case):
|
||||
test_name_base = get_base_test_name(request)
|
||||
if should_skip_test(verification_config, provider, model, test_name_base):
|
||||
pytest.skip(f"Skipping {test_name_base} for model {model} on provider {provider} based on config.")
|
||||
|
||||
stream = openai_client.chat.completions.create(
|
||||
model=model,
|
||||
messages=case["input"]["messages"],
|
||||
tools=case["input"]["tools"],
|
||||
stream=True,
|
||||
)
|
||||
|
||||
# Accumulate partial tool_calls here
|
||||
tool_calls_buffer = {}
|
||||
current_id = None
|
||||
# Process streaming chunks
|
||||
for chunk in stream:
|
||||
choice = chunk.choices[0]
|
||||
delta = choice.delta
|
||||
|
||||
if delta.tool_calls is None:
|
||||
continue
|
||||
|
||||
for tool_call_delta in delta.tool_calls:
|
||||
if tool_call_delta.id:
|
||||
current_id = tool_call_delta.id
|
||||
call_id = current_id
|
||||
func_delta = tool_call_delta.function
|
||||
|
||||
if call_id not in tool_calls_buffer:
|
||||
tool_calls_buffer[call_id] = {
|
||||
"id": call_id,
|
||||
"type": tool_call_delta.type,
|
||||
"name": func_delta.name,
|
||||
"arguments": "",
|
||||
}
|
||||
|
||||
if func_delta.arguments:
|
||||
tool_calls_buffer[call_id]["arguments"] += func_delta.arguments
|
||||
|
||||
assert len(tool_calls_buffer) == 1
|
||||
for call in tool_calls_buffer.values():
|
||||
assert len(call["id"]) > 0
|
||||
assert call["name"] == "get_weather"
|
||||
|
||||
args_dict = json.loads(call["arguments"])
|
||||
assert "san francisco" in args_dict["location"].lower()
|
||||
|
||||
|
||||
# --- Helper functions (structured output validation) ---
|
||||
|
||||
|
||||
def get_structured_output(maybe_json_content: str, schema_name: str) -> Any | None:
|
||||
if schema_name == "valid_calendar_event":
|
||||
|
||||
class CalendarEvent(BaseModel):
|
||||
name: str
|
||||
date: str
|
||||
participants: list[str]
|
||||
|
||||
try:
|
||||
calendar_event = CalendarEvent.model_validate_json(maybe_json_content)
|
||||
return calendar_event
|
||||
except Exception:
|
||||
return None
|
||||
elif schema_name == "valid_math_reasoning":
|
||||
|
||||
class Step(BaseModel):
|
||||
explanation: str
|
||||
output: str
|
||||
|
||||
class MathReasoning(BaseModel):
|
||||
steps: list[Step]
|
||||
final_answer: str
|
||||
|
||||
try:
|
||||
math_reasoning = MathReasoning.model_validate_json(maybe_json_content)
|
||||
return math_reasoning
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def validate_structured_output(maybe_json_content: str, schema_name: str) -> None:
|
||||
structured_output = get_structured_output(maybe_json_content, schema_name)
|
||||
assert structured_output is not None
|
||||
if schema_name == "valid_calendar_event":
|
||||
assert structured_output.name is not None
|
||||
assert structured_output.date is not None
|
||||
assert len(structured_output.participants) == 2
|
||||
elif schema_name == "valid_math_reasoning":
|
||||
assert len(structured_output.final_answer) > 0
|
||||
1483
tests/verifications/test_results/fireworks.json
Normal file
1483
tests/verifications/test_results/fireworks.json
Normal file
File diff suppressed because it is too large
Load diff
File diff suppressed because it is too large
Load diff
945
tests/verifications/test_results/openai.json
Normal file
945
tests/verifications/test_results/openai.json
Normal file
|
|
@ -0,0 +1,945 @@
|
|||
{
|
||||
"created": 1744328898.0248861,
|
||||
"duration": 47.561042070388794,
|
||||
"exitcode": 0,
|
||||
"root": "/Users/erichuang/projects/llama-stack",
|
||||
"environment": {},
|
||||
"summary": {
|
||||
"passed": 24,
|
||||
"total": 24,
|
||||
"collected": 24
|
||||
},
|
||||
"collectors": [
|
||||
{
|
||||
"nodeid": "",
|
||||
"outcome": "passed",
|
||||
"result": [
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py",
|
||||
"type": "Module"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py",
|
||||
"outcome": "passed",
|
||||
"result": [
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-earth]",
|
||||
"type": "Function",
|
||||
"lineno": 73
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-saturn]",
|
||||
"type": "Function",
|
||||
"lineno": 73
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-earth]",
|
||||
"type": "Function",
|
||||
"lineno": 73
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
|
||||
"type": "Function",
|
||||
"lineno": 73
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-earth]",
|
||||
"type": "Function",
|
||||
"lineno": 92
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-saturn]",
|
||||
"type": "Function",
|
||||
"lineno": 92
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-earth]",
|
||||
"type": "Function",
|
||||
"lineno": 92
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-saturn]",
|
||||
"type": "Function",
|
||||
"lineno": 92
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 116
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-mini-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 116
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 135
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-mini-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 135
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-calendar]",
|
||||
"type": "Function",
|
||||
"lineno": 159
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-math]",
|
||||
"type": "Function",
|
||||
"lineno": 159
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
|
||||
"type": "Function",
|
||||
"lineno": 159
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
|
||||
"type": "Function",
|
||||
"lineno": 159
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-calendar]",
|
||||
"type": "Function",
|
||||
"lineno": 182
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-math]",
|
||||
"type": "Function",
|
||||
"lineno": 182
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
|
||||
"type": "Function",
|
||||
"lineno": 182
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-math]",
|
||||
"type": "Function",
|
||||
"lineno": 182
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 204
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 204
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 228
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
|
||||
"type": "Function",
|
||||
"lineno": 228
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"tests": [
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-earth]",
|
||||
"lineno": 73,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_basic[gpt-4o-earth]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-earth",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "earth"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.0694252080284059,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.5709165419684723,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0007626248989254236,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-saturn]",
|
||||
"lineno": 73,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_basic[gpt-4o-saturn]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-saturn",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "saturn"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.010281750001013279,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.6309260830748826,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0001824579667299986,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-earth]",
|
||||
"lineno": 73,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_basic[gpt-4o-mini-earth]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-earth",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "earth"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.007922374992631376,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.31756504194345325,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0005268750246614218,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
|
||||
"lineno": 73,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_basic[gpt-4o-mini-saturn]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-saturn",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "saturn"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.01643404201604426,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.7479908330133185,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0004037501057609916,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-earth]",
|
||||
"lineno": 92,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_basic[gpt-4o-earth]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-earth",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "earth"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.021671707974746823,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.6701172919711098,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0005569590721279383,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-saturn]",
|
||||
"lineno": 92,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_basic[gpt-4o-saturn]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-saturn",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "saturn"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.015847125090658665,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.636536999954842,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00029395800083875656,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-earth]",
|
||||
"lineno": 92,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_basic[gpt-4o-mini-earth]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-earth",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "earth"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.011792832985520363,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.5610962919890881,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0003578749019652605,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_basic[gpt-4o-mini-saturn]",
|
||||
"lineno": 92,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_basic[gpt-4o-mini-saturn]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-saturn",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "saturn"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.016500207944773138,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.8060244580265135,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0005296670133247972,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-case0]",
|
||||
"lineno": 116,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_image[gpt-4o-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.008338792016729712,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 7.009252917021513,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0003042910248041153,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_image[gpt-4o-mini-case0]",
|
||||
"lineno": 116,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_image[gpt-4o-mini-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.007238540914840996,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 3.134693874977529,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0003104590578004718,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-case0]",
|
||||
"lineno": 135,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_image[gpt-4o-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.0161851670127362,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 3.0745719589758664,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00022620800882577896,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_image[gpt-4o-mini-case0]",
|
||||
"lineno": 135,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_image[gpt-4o-mini-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.013220708002336323,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 3.624867417034693,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00020633300300687551,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-calendar]",
|
||||
"lineno": 159,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_structured_output[gpt-4o-calendar]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-calendar",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "calendar"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.017596833989955485,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 1.248568250099197,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0004248750628903508,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-math]",
|
||||
"lineno": 159,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_structured_output[gpt-4o-math]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-math",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "math"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.01512012502644211,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 8.170285542029887,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00043537491001188755,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
|
||||
"lineno": 159,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_structured_output[gpt-4o-mini-calendar]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-calendar",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "calendar"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.010376665974035859,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.756480542011559,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00025695806834846735,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
|
||||
"lineno": 159,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_structured_output[gpt-4o-mini-math]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-math",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "math"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.006846625008620322,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 2.6833953330060467,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00022558309137821198,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-calendar]",
|
||||
"lineno": 182,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_structured_output[gpt-4o-calendar]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-calendar",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "calendar"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.009646040969528258,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.6117532079806551,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00015258300118148327,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-math]",
|
||||
"lineno": 182,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_structured_output[gpt-4o-math]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-math",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "math"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.012024458032101393,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 4.522625041077845,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0004230838967487216,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
|
||||
"lineno": 182,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_structured_output[gpt-4o-mini-calendar]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-calendar",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "calendar"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.009566582972183824,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 2.5591942919418216,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0007555419579148293,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_structured_output[gpt-4o-mini-math]",
|
||||
"lineno": 182,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_structured_output[gpt-4o-mini-math]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-math",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "math"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.010828875005245209,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 2.495122667052783,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0002802090020850301,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-case0]",
|
||||
"lineno": 204,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_tool_calling[gpt-4o-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.012762792059220374,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.5655921660363674,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.00022304197773337364,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
|
||||
"lineno": 204,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_non_streaming_tool_calling[gpt-4o-mini-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.03188708401285112,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.6159415419679135,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0005549580091610551,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-case0]",
|
||||
"lineno": 228,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_tool_calling[gpt-4o-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.014768208027817309,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.47373537498060614,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0005811670562252402,
|
||||
"outcome": "passed"
|
||||
}
|
||||
},
|
||||
{
|
||||
"nodeid": "tests/verifications/openai_api/test_chat_completion.py::test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
|
||||
"lineno": 228,
|
||||
"outcome": "passed",
|
||||
"keywords": [
|
||||
"test_chat_streaming_tool_calling[gpt-4o-mini-case0]",
|
||||
"parametrize",
|
||||
"pytestmark",
|
||||
"gpt-4o-mini-case0",
|
||||
"test_chat_completion.py",
|
||||
"openai_api",
|
||||
"verifications",
|
||||
"tests",
|
||||
"llama-stack",
|
||||
""
|
||||
],
|
||||
"metadata": {
|
||||
"model": "gpt-4o-mini",
|
||||
"case_id": "case0"
|
||||
},
|
||||
"setup": {
|
||||
"duration": 0.010271625011228025,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"call": {
|
||||
"duration": 0.5656027499353513,
|
||||
"outcome": "passed"
|
||||
},
|
||||
"teardown": {
|
||||
"duration": 0.0025699170073494315,
|
||||
"outcome": "passed"
|
||||
}
|
||||
}
|
||||
],
|
||||
"run_timestamp": 1744328848
|
||||
}
|
||||
File diff suppressed because it is too large
Load diff
1561
tests/verifications/test_results/together.json
Normal file
1561
tests/verifications/test_results/together.json
Normal file
File diff suppressed because it is too large
Load diff
File diff suppressed because it is too large
Load diff
8
uv.lock
generated
8
uv.lock
generated
|
|
@ -1384,6 +1384,7 @@ dependencies = [
|
|||
{ name = "jinja2" },
|
||||
{ name = "jsonschema" },
|
||||
{ name = "llama-stack-client" },
|
||||
{ name = "openai" },
|
||||
{ name = "pillow" },
|
||||
{ name = "prompt-toolkit" },
|
||||
{ name = "pydantic" },
|
||||
|
|
@ -1485,6 +1486,7 @@ requires-dist = [
|
|||
{ name = "mcp", marker = "extra == 'test'" },
|
||||
{ name = "myst-parser", marker = "extra == 'docs'" },
|
||||
{ name = "nbval", marker = "extra == 'dev'" },
|
||||
{ name = "openai", specifier = ">=1.66" },
|
||||
{ name = "openai", marker = "extra == 'test'" },
|
||||
{ name = "openai", marker = "extra == 'unit'" },
|
||||
{ name = "opentelemetry-exporter-otlp-proto-http", marker = "extra == 'test'" },
|
||||
|
|
@ -2016,7 +2018,7 @@ wheels = [
|
|||
|
||||
[[package]]
|
||||
name = "openai"
|
||||
version = "1.63.2"
|
||||
version = "1.71.0"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "anyio" },
|
||||
|
|
@ -2028,9 +2030,9 @@ dependencies = [
|
|||
{ name = "tqdm" },
|
||||
{ name = "typing-extensions" },
|
||||
]
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/e6/1c/11b520deb71f9ea54ced3c52cd6a5f7131215deba63ad07f23982e328141/openai-1.63.2.tar.gz", hash = "sha256:aeabeec984a7d2957b4928ceaa339e2ead19c61cfcf35ae62b7c363368d26360", size = 356902 }
|
||||
sdist = { url = "https://files.pythonhosted.org/packages/d9/19/b8f0347090a649dce55a008ec54ac6abb50553a06508cdb5e7abb2813e99/openai-1.71.0.tar.gz", hash = "sha256:52b20bb990a1780f9b0b8ccebac93416343ebd3e4e714e3eff730336833ca207", size = 409926 }
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/15/64/db3462b358072387b8e93e6e6a38d3c741a17b4a84171ef01d6c85c63f25/openai-1.63.2-py3-none-any.whl", hash = "sha256:1f38b27b5a40814c2b7d8759ec78110df58c4a614c25f182809ca52b080ff4d4", size = 472282 },
|
||||
{ url = "https://files.pythonhosted.org/packages/c4/f7/049e85faf6a000890e5ca0edca8e9183f8a43c9e7bba869cad871da0caba/openai-1.71.0-py3-none-any.whl", hash = "sha256:e1c643738f1fff1af52bce6ef06a7716c95d089281e7011777179614f32937aa", size = 598975 },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue