phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 13:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-09 17:28:44 -07:00
parent f50ce11a3b
commit 972f2395a1
29 changed files with 1726 additions and 2149 deletions
Download patch file Download diff file Expand all files Collapse all files

545
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -7343,6 +7343,233 @@
"title": "OpenAIUserMessageParam",
"description": "A message from the user in an OpenAI-compatible chat completion request."
},
"OpenAIChatCompletionRequestParams": {
"type": "object",
"properties": {
"model": {
"type": "string"
},
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIMessageParam"
}
},
"frequency_penalty": {
"type": "number"
},
"function_call": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
]
},
"functions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
}
},
"logprobs": {
"type": "boolean"
},
"max_completion_tokens": {
"type": "integer"
},
"max_tokens": {
"type": "integer"
},
"n": {
"type": "integer"
},
"parallel_tool_calls": {
"type": "boolean"
},
"presence_penalty": {
"type": "number"
},
"response_format": {
"$ref": "#/components/schemas/OpenAIResponseFormatParam"
},
"seed": {
"type": "integer"
},
"stop": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"stream": {
"type": "boolean"
},
"stream_options": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"temperature": {
"type": "number"
},
"tool_choice": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
]
},
"tools": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"top_logprobs": {
"type": "integer"
},
"top_p": {
"type": "number"
},
"user": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"model",
"messages"
],
"title": "OpenAIChatCompletionRequestParams",
"description": "Request parameters for OpenAI-compatible chat completion endpoint.\nThis model uses extra=\"allow\" to capture provider-specific parameters\nwhich are passed through as extra_body."
},
"OpenAIJSONSchema": {
"type": "object",
"properties": {
@ -7472,249 +7699,14 @@
"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": {
"$ref": "#/components/schemas/OpenAIMessageParam"
},
"description": "List of messages in the conversation."
},
"frequency_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
},
"function_call": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
],
"description": "(Optional) The function call to use."
},
"functions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"description": "(Optional) List of functions to use."
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "(Optional) The logit bias to use."
},
"logprobs": {
"type": "boolean",
"description": "(Optional) The log probabilities to use."
},
"max_completion_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
},
"max_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
},
"n": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
},
"parallel_tool_calls": {
"type": "boolean",
"description": "(Optional) Whether to parallelize tool calls."
},
"presence_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
},
"response_format": {
"$ref": "#/components/schemas/OpenAIResponseFormatParam",
"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."
"params": {
"$ref": "#/components/schemas/OpenAIChatCompletionRequestParams",
"description": "Request parameters including model, messages, and optional parameters. Use params.get_extra_body() to extract provider-specific parameters (e.g., chat_template_kwargs for vLLM)."
}
},
"additionalProperties": false,
"required": [
"model",
"messages"
"params"
],
"title": "OpenaiChatCompletionRequest"
},
@ -7900,12 +7892,11 @@
],
"title": "OpenAICompletionWithInputMessages"
},
"OpenaiCompletionRequest": {
"OpenAICompletionRequestParams": {
"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."
"type": "string"
},
"prompt": {
"oneOf": [
@ -7933,47 +7924,37 @@
}
}
}
],
"description": "The prompt to generate a completion for."
]
},
"best_of": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
"type": "integer"
},
"echo": {
"type": "boolean",
"description": "(Optional) Whether to echo the prompt."
"type": "boolean"
},
"frequency_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
"type": "number"
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "(Optional) The logit bias to use."
}
},
"logprobs": {
"type": "boolean",
"description": "(Optional) The log probabilities to use."
"type": "boolean"
},
"max_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
"type": "integer"
},
"n": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
"type": "integer"
},
"presence_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
"type": "number"
},
"seed": {
"type": "integer",
"description": "(Optional) The seed to use."
"type": "integer"
},
"stop": {
"oneOf": [
@ -7986,12 +7967,10 @@
"type": "string"
}
}
],
"description": "(Optional) The stop tokens to use."
]
},
"stream": {
"type": "boolean",
"description": "(Optional) Whether to stream the response."
"type": "boolean"
},
"stream_options": {
"type": "object",
@ -8016,20 +7995,19 @@
"type": "object"
}
]
},
"description": "(Optional) The stream options to use."
}
},
"temperature": {
"type": "number",
"description": "(Optional) The temperature to use."
"type": "number"
},
"top_p": {
"type": "number",
"description": "(Optional) The top p to use."
"type": "number"
},
"user": {
"type": "string",
"description": "(Optional) The user to use."
"type": "string"
},
"suffix": {
"type": "string"
},
"guided_choice": {
"type": "array",
@ -8039,10 +8017,6 @@
},
"prompt_logprobs": {
"type": "integer"
},
"suffix": {
"type": "string",
"description": "(Optional) The suffix that should be appended to the completion."
}
},
"additionalProperties": false,
@ -8050,6 +8024,21 @@
"model",
"prompt"
],
"title": "OpenAICompletionRequestParams",
"description": "Request parameters for OpenAI-compatible completion endpoint.\nThis model uses extra=\"allow\" to capture provider-specific parameters\n(like vLLM's guided_choice) which are passed through as extra_body."
},
"OpenaiCompletionRequest": {
"type": "object",
"properties": {
"params": {
"$ref": "#/components/schemas/OpenAICompletionRequestParams",
"description": "Request parameters including model, prompt, and optional parameters. Use params.get_extra_body() to extract provider-specific parameters."
}
},
"additionalProperties": false,
"required": [
"params"
],
"title": "OpenaiCompletionRequest"
},
"OpenAICompletion": {

309
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -5437,6 +5437,122 @@ components:
title: OpenAIUserMessageParam
description: >-
A message from the user in an OpenAI-compatible chat completion request.
OpenAIChatCompletionRequestParams:
type: object
properties:
model:
type: string
messages:
type: array
items:
$ref: '#/components/schemas/OpenAIMessageParam'
frequency_penalty:
type: number
function_call:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
functions:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
logit_bias:
type: object
additionalProperties:
type: number
logprobs:
type: boolean
max_completion_tokens:
type: integer
max_tokens:
type: integer
n:
type: integer
parallel_tool_calls:
type: boolean
presence_penalty:
type: number
response_format:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
seed:
type: integer
stop:
oneOf:
- type: string
- type: array
items:
type: string
stream:
type: boolean
stream_options:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
temperature:
type: number
tool_choice:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
tools:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
top_logprobs:
type: integer
top_p:
type: number
user:
type: string
additionalProperties: false
required:
- model
- messages
title: OpenAIChatCompletionRequestParams
description: >-
Request parameters for OpenAI-compatible chat completion endpoint.
This model uses extra="allow" to capture provider-specific parameters
which are passed through as extra_body.
OpenAIJSONSchema:
type: object
properties:
@ -5531,145 +5647,15 @@ components:
OpenaiChatCompletionRequest:
type: object
properties:
model:
type: string
params:
$ref: '#/components/schemas/OpenAIChatCompletionRequestParams'
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:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
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.
Request parameters including model, messages, and optional parameters.
Use params.get_extra_body() to extract provider-specific parameters (e.g.,
chat_template_kwargs for vLLM).
additionalProperties: false
required:
- model
- messages
- params
title: OpenaiChatCompletionRequest
OpenAIChatCompletion:
type: object
@ -5824,14 +5810,11 @@ components:
- model
- input_messages
title: OpenAICompletionWithInputMessages
OpenaiCompletionRequest:
OpenAICompletionRequestParams:
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
@ -5846,52 +5829,34 @@ components:
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:
@ -5902,30 +5867,42 @@ components:
- 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.
suffix:
type: string
guided_choice:
type: array
items:
type: string
prompt_logprobs:
type: integer
suffix:
type: string
description: >-
(Optional) The suffix that should be appended to the completion.
additionalProperties: false
required:
- model
- prompt
title: OpenAICompletionRequestParams
description: >-
Request parameters for OpenAI-compatible completion endpoint.
This model uses extra="allow" to capture provider-specific parameters
(like vLLM's guided_choice) which are passed through as extra_body.
OpenaiCompletionRequest:
type: object
properties:
params:
$ref: '#/components/schemas/OpenAICompletionRequestParams'
description: >-
Request parameters including model, prompt, and optional parameters. Use
params.get_extra_body() to extract provider-specific parameters.
additionalProperties: false
required:
- params
title: OpenaiCompletionRequest
OpenAICompletion:
type: object

545
docs/static/llama-stack-spec.html vendored
View file

@ -4839,6 +4839,233 @@
"title": "OpenAIUserMessageParam",
"description": "A message from the user in an OpenAI-compatible chat completion request."
},
"OpenAIChatCompletionRequestParams": {
"type": "object",
"properties": {
"model": {
"type": "string"
},
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIMessageParam"
}
},
"frequency_penalty": {
"type": "number"
},
"function_call": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
]
},
"functions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
}
},
"logprobs": {
"type": "boolean"
},
"max_completion_tokens": {
"type": "integer"
},
"max_tokens": {
"type": "integer"
},
"n": {
"type": "integer"
},
"parallel_tool_calls": {
"type": "boolean"
},
"presence_penalty": {
"type": "number"
},
"response_format": {
"$ref": "#/components/schemas/OpenAIResponseFormatParam"
},
"seed": {
"type": "integer"
},
"stop": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"stream": {
"type": "boolean"
},
"stream_options": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"temperature": {
"type": "number"
},
"tool_choice": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
]
},
"tools": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"top_logprobs": {
"type": "integer"
},
"top_p": {
"type": "number"
},
"user": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"model",
"messages"
],
"title": "OpenAIChatCompletionRequestParams",
"description": "Request parameters for OpenAI-compatible chat completion endpoint.\nThis model uses extra=\"allow\" to capture provider-specific parameters\nwhich are passed through as extra_body."
},
"OpenAIJSONSchema": {
"type": "object",
"properties": {
@ -4968,249 +5195,14 @@
"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": {
"$ref": "#/components/schemas/OpenAIMessageParam"
},
"description": "List of messages in the conversation."
},
"frequency_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
},
"function_call": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
],
"description": "(Optional) The function call to use."
},
"functions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"description": "(Optional) List of functions to use."
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "(Optional) The logit bias to use."
},
"logprobs": {
"type": "boolean",
"description": "(Optional) The log probabilities to use."
},
"max_completion_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
},
"max_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
},
"n": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
},
"parallel_tool_calls": {
"type": "boolean",
"description": "(Optional) Whether to parallelize tool calls."
},
"presence_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
},
"response_format": {
"$ref": "#/components/schemas/OpenAIResponseFormatParam",
"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."
"params": {
"$ref": "#/components/schemas/OpenAIChatCompletionRequestParams",
"description": "Request parameters including model, messages, and optional parameters. Use params.get_extra_body() to extract provider-specific parameters (e.g., chat_template_kwargs for vLLM)."
}
},
"additionalProperties": false,
"required": [
"model",
"messages"
"params"
],
"title": "OpenaiChatCompletionRequest"
},
@ -5396,12 +5388,11 @@
],
"title": "OpenAICompletionWithInputMessages"
},
"OpenaiCompletionRequest": {
"OpenAICompletionRequestParams": {
"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."
"type": "string"
},
"prompt": {
"oneOf": [
@ -5429,47 +5420,37 @@
}
}
}
],
"description": "The prompt to generate a completion for."
]
},
"best_of": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
"type": "integer"
},
"echo": {
"type": "boolean",
"description": "(Optional) Whether to echo the prompt."
"type": "boolean"
},
"frequency_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
"type": "number"
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "(Optional) The logit bias to use."
}
},
"logprobs": {
"type": "boolean",
"description": "(Optional) The log probabilities to use."
"type": "boolean"
},
"max_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
"type": "integer"
},
"n": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
"type": "integer"
},
"presence_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
"type": "number"
},
"seed": {
"type": "integer",
"description": "(Optional) The seed to use."
"type": "integer"
},
"stop": {
"oneOf": [
@ -5482,12 +5463,10 @@
"type": "string"
}
}
],
"description": "(Optional) The stop tokens to use."
]
},
"stream": {
"type": "boolean",
"description": "(Optional) Whether to stream the response."
"type": "boolean"
},
"stream_options": {
"type": "object",
@ -5512,20 +5491,19 @@
"type": "object"
}
]
},
"description": "(Optional) The stream options to use."
}
},
"temperature": {
"type": "number",
"description": "(Optional) The temperature to use."
"type": "number"
},
"top_p": {
"type": "number",
"description": "(Optional) The top p to use."
"type": "number"
},
"user": {
"type": "string",
"description": "(Optional) The user to use."
"type": "string"
},
"suffix": {
"type": "string"
},
"guided_choice": {
"type": "array",
@ -5535,10 +5513,6 @@
},
"prompt_logprobs": {
"type": "integer"
},
"suffix": {
"type": "string",
"description": "(Optional) The suffix that should be appended to the completion."
}
},
"additionalProperties": false,
@ -5546,6 +5520,21 @@
"model",
"prompt"
],
"title": "OpenAICompletionRequestParams",
"description": "Request parameters for OpenAI-compatible completion endpoint.\nThis model uses extra=\"allow\" to capture provider-specific parameters\n(like vLLM's guided_choice) which are passed through as extra_body."
},
"OpenaiCompletionRequest": {
"type": "object",
"properties": {
"params": {
"$ref": "#/components/schemas/OpenAICompletionRequestParams",
"description": "Request parameters including model, prompt, and optional parameters. Use params.get_extra_body() to extract provider-specific parameters."
}
},
"additionalProperties": false,
"required": [
"params"
],
"title": "OpenaiCompletionRequest"
},
"OpenAICompletion": {

309
docs/static/llama-stack-spec.yaml vendored
View file

@ -3686,6 +3686,122 @@ components:
title: OpenAIUserMessageParam
description: >-
A message from the user in an OpenAI-compatible chat completion request.
OpenAIChatCompletionRequestParams:
type: object
properties:
model:
type: string
messages:
type: array
items:
$ref: '#/components/schemas/OpenAIMessageParam'
frequency_penalty:
type: number
function_call:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
functions:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
logit_bias:
type: object
additionalProperties:
type: number
logprobs:
type: boolean
max_completion_tokens:
type: integer
max_tokens:
type: integer
n:
type: integer
parallel_tool_calls:
type: boolean
presence_penalty:
type: number
response_format:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
seed:
type: integer
stop:
oneOf:
- type: string
- type: array
items:
type: string
stream:
type: boolean
stream_options:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
temperature:
type: number
tool_choice:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
tools:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
top_logprobs:
type: integer
top_p:
type: number
user:
type: string
additionalProperties: false
required:
- model
- messages
title: OpenAIChatCompletionRequestParams
description: >-
Request parameters for OpenAI-compatible chat completion endpoint.
This model uses extra="allow" to capture provider-specific parameters
which are passed through as extra_body.
OpenAIJSONSchema:
type: object
properties:
@ -3780,145 +3896,15 @@ components:
OpenaiChatCompletionRequest:
type: object
properties:
model:
type: string
params:
$ref: '#/components/schemas/OpenAIChatCompletionRequestParams'
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:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
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.
Request parameters including model, messages, and optional parameters.
Use params.get_extra_body() to extract provider-specific parameters (e.g.,
chat_template_kwargs for vLLM).
additionalProperties: false
required:
- model
- messages
- params
title: OpenaiChatCompletionRequest
OpenAIChatCompletion:
type: object
@ -4073,14 +4059,11 @@ components:
- model
- input_messages
title: OpenAICompletionWithInputMessages
OpenaiCompletionRequest:
OpenAICompletionRequestParams:
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
@ -4095,52 +4078,34 @@ components:
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:
@ -4151,30 +4116,42 @@ components:
- 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.
suffix:
type: string
guided_choice:
type: array
items:
type: string
prompt_logprobs:
type: integer
suffix:
type: string
description: >-
(Optional) The suffix that should be appended to the completion.
additionalProperties: false
required:
- model
- prompt
title: OpenAICompletionRequestParams
description: >-
Request parameters for OpenAI-compatible completion endpoint.
This model uses extra="allow" to capture provider-specific parameters
(like vLLM's guided_choice) which are passed through as extra_body.
OpenaiCompletionRequest:
type: object
properties:
params:
$ref: '#/components/schemas/OpenAICompletionRequestParams'
description: >-
Request parameters including model, prompt, and optional parameters. Use
params.get_extra_body() to extract provider-specific parameters.
additionalProperties: false
required:
- params
title: OpenaiCompletionRequest
OpenAICompletion:
type: object

545
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -6848,6 +6848,233 @@
"title": "OpenAIUserMessageParam",
"description": "A message from the user in an OpenAI-compatible chat completion request."
},
"OpenAIChatCompletionRequestParams": {
"type": "object",
"properties": {
"model": {
"type": "string"
},
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIMessageParam"
}
},
"frequency_penalty": {
"type": "number"
},
"function_call": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
]
},
"functions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
}
},
"logprobs": {
"type": "boolean"
},
"max_completion_tokens": {
"type": "integer"
},
"max_tokens": {
"type": "integer"
},
"n": {
"type": "integer"
},
"parallel_tool_calls": {
"type": "boolean"
},
"presence_penalty": {
"type": "number"
},
"response_format": {
"$ref": "#/components/schemas/OpenAIResponseFormatParam"
},
"seed": {
"type": "integer"
},
"stop": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
]
},
"stream": {
"type": "boolean"
},
"stream_options": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"temperature": {
"type": "number"
},
"tool_choice": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
]
},
"tools": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"top_logprobs": {
"type": "integer"
},
"top_p": {
"type": "number"
},
"user": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"model",
"messages"
],
"title": "OpenAIChatCompletionRequestParams",
"description": "Request parameters for OpenAI-compatible chat completion endpoint.\nThis model uses extra=\"allow\" to capture provider-specific parameters\nwhich are passed through as extra_body."
},
"OpenAIJSONSchema": {
"type": "object",
"properties": {
@ -6977,249 +7204,14 @@
"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": {
"$ref": "#/components/schemas/OpenAIMessageParam"
},
"description": "List of messages in the conversation."
},
"frequency_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
},
"function_call": {
"oneOf": [
{
"type": "string"
},
{
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
],
"description": "(Optional) The function call to use."
},
"functions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
},
"description": "(Optional) List of functions to use."
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "(Optional) The logit bias to use."
},
"logprobs": {
"type": "boolean",
"description": "(Optional) The log probabilities to use."
},
"max_completion_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
},
"max_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
},
"n": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
},
"parallel_tool_calls": {
"type": "boolean",
"description": "(Optional) Whether to parallelize tool calls."
},
"presence_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
},
"response_format": {
"$ref": "#/components/schemas/OpenAIResponseFormatParam",
"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."
"params": {
"$ref": "#/components/schemas/OpenAIChatCompletionRequestParams",
"description": "Request parameters including model, messages, and optional parameters. Use params.get_extra_body() to extract provider-specific parameters (e.g., chat_template_kwargs for vLLM)."
}
},
"additionalProperties": false,
"required": [
"model",
"messages"
"params"
],
"title": "OpenaiChatCompletionRequest"
},
@ -7405,12 +7397,11 @@
],
"title": "OpenAICompletionWithInputMessages"
},
"OpenaiCompletionRequest": {
"OpenAICompletionRequestParams": {
"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."
"type": "string"
},
"prompt": {
"oneOf": [
@ -7438,47 +7429,37 @@
}
}
}
],
"description": "The prompt to generate a completion for."
]
},
"best_of": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
"type": "integer"
},
"echo": {
"type": "boolean",
"description": "(Optional) Whether to echo the prompt."
"type": "boolean"
},
"frequency_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
"type": "number"
},
"logit_bias": {
"type": "object",
"additionalProperties": {
"type": "number"
},
"description": "(Optional) The logit bias to use."
}
},
"logprobs": {
"type": "boolean",
"description": "(Optional) The log probabilities to use."
"type": "boolean"
},
"max_tokens": {
"type": "integer",
"description": "(Optional) The maximum number of tokens to generate."
"type": "integer"
},
"n": {
"type": "integer",
"description": "(Optional) The number of completions to generate."
"type": "integer"
},
"presence_penalty": {
"type": "number",
"description": "(Optional) The penalty for repeated tokens."
"type": "number"
},
"seed": {
"type": "integer",
"description": "(Optional) The seed to use."
"type": "integer"
},
"stop": {
"oneOf": [
@ -7491,12 +7472,10 @@
"type": "string"
}
}
],
"description": "(Optional) The stop tokens to use."
]
},
"stream": {
"type": "boolean",
"description": "(Optional) Whether to stream the response."
"type": "boolean"
},
"stream_options": {
"type": "object",
@ -7521,20 +7500,19 @@
"type": "object"
}
]
},
"description": "(Optional) The stream options to use."
}
},
"temperature": {
"type": "number",
"description": "(Optional) The temperature to use."
"type": "number"
},
"top_p": {
"type": "number",
"description": "(Optional) The top p to use."
"type": "number"
},
"user": {
"type": "string",
"description": "(Optional) The user to use."
"type": "string"
},
"suffix": {
"type": "string"
},
"guided_choice": {
"type": "array",
@ -7544,10 +7522,6 @@
},
"prompt_logprobs": {
"type": "integer"
},
"suffix": {
"type": "string",
"description": "(Optional) The suffix that should be appended to the completion."
}
},
"additionalProperties": false,
@ -7555,6 +7529,21 @@
"model",
"prompt"
],
"title": "OpenAICompletionRequestParams",
"description": "Request parameters for OpenAI-compatible completion endpoint.\nThis model uses extra=\"allow\" to capture provider-specific parameters\n(like vLLM's guided_choice) which are passed through as extra_body."
},
"OpenaiCompletionRequest": {
"type": "object",
"properties": {
"params": {
"$ref": "#/components/schemas/OpenAICompletionRequestParams",
"description": "Request parameters including model, prompt, and optional parameters. Use params.get_extra_body() to extract provider-specific parameters."
}
},
"additionalProperties": false,
"required": [
"params"
],
"title": "OpenaiCompletionRequest"
},
"OpenAICompletion": {

309
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -5131,6 +5131,122 @@ components:
title: OpenAIUserMessageParam
description: >-
A message from the user in an OpenAI-compatible chat completion request.
OpenAIChatCompletionRequestParams:
type: object
properties:
model:
type: string
messages:
type: array
items:
$ref: '#/components/schemas/OpenAIMessageParam'
frequency_penalty:
type: number
function_call:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
functions:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
logit_bias:
type: object
additionalProperties:
type: number
logprobs:
type: boolean
max_completion_tokens:
type: integer
max_tokens:
type: integer
n:
type: integer
parallel_tool_calls:
type: boolean
presence_penalty:
type: number
response_format:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
seed:
type: integer
stop:
oneOf:
- type: string
- type: array
items:
type: string
stream:
type: boolean
stream_options:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
temperature:
type: number
tool_choice:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
tools:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
top_logprobs:
type: integer
top_p:
type: number
user:
type: string
additionalProperties: false
required:
- model
- messages
title: OpenAIChatCompletionRequestParams
description: >-
Request parameters for OpenAI-compatible chat completion endpoint.
This model uses extra="allow" to capture provider-specific parameters
which are passed through as extra_body.
OpenAIJSONSchema:
type: object
properties:
@ -5225,145 +5341,15 @@ components:
OpenaiChatCompletionRequest:
type: object
properties:
model:
type: string
params:
$ref: '#/components/schemas/OpenAIChatCompletionRequestParams'
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:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
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.
Request parameters including model, messages, and optional parameters.
Use params.get_extra_body() to extract provider-specific parameters (e.g.,
chat_template_kwargs for vLLM).
additionalProperties: false
required:
- model
- messages
- params
title: OpenaiChatCompletionRequest
OpenAIChatCompletion:
type: object
@ -5518,14 +5504,11 @@ components:
- model
- input_messages
title: OpenAICompletionWithInputMessages
OpenaiCompletionRequest:
OpenAICompletionRequestParams:
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
@ -5540,52 +5523,34 @@ components:
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:
@ -5596,30 +5561,42 @@ components:
- 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.
suffix:
type: string
guided_choice:
type: array
items:
type: string
prompt_logprobs:
type: integer
suffix:
type: string
description: >-
(Optional) The suffix that should be appended to the completion.
additionalProperties: false
required:
- model
- prompt
title: OpenAICompletionRequestParams
description: >-
Request parameters for OpenAI-compatible completion endpoint.
This model uses extra="allow" to capture provider-specific parameters
(like vLLM's guided_choice) which are passed through as extra_body.
OpenaiCompletionRequest:
type: object
properties:
params:
$ref: '#/components/schemas/OpenAICompletionRequestParams'
description: >-
Request parameters including model, prompt, and optional parameters. Use
params.get_extra_body() to extract provider-specific parameters.
additionalProperties: false
required:
- params
title: OpenaiCompletionRequest
OpenAICompletion:
type: object