mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-23 20:51:53 +00:00
Inference
This commit is contained in:
Sai Soundararaj
parent
c5fd9886ae
commit
8fc72e4669
3 changed files with 297 additions and 53 deletions
159
docs/_static/llama-stack-spec.html
vendored
159
docs/_static/llama-stack-spec.html
vendored
|
|
@ -5144,14 +5144,16 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "greedy",
|
||||
"default": "greedy"
|
||||
"default": "greedy",
|
||||
"description": "Must be \"greedy\" to identify this sampling strategy"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "GreedySamplingStrategy"
|
||||
"title": "GreedySamplingStrategy",
|
||||
"description": "Greedy sampling strategy that selects the highest probability token at each step."
|
||||
},
|
||||
"ImageContentItem": {
|
||||
"type": "object",
|
||||
|
|
@ -5671,10 +5673,12 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "top_k",
|
||||
"default": "top_k"
|
||||
"default": "top_k",
|
||||
"description": "Must be \"top_k\" to identify this sampling strategy"
|
||||
},
|
||||
"top_k": {
|
||||
"type": "integer"
|
||||
"type": "integer",
|
||||
"description": "Number of top tokens to consider for sampling. Must be at least 1"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -5682,7 +5686,8 @@
|
|||
"type",
|
||||
"top_k"
|
||||
],
|
||||
"title": "TopKSamplingStrategy"
|
||||
"title": "TopKSamplingStrategy",
|
||||
"description": "Top-k sampling strategy that restricts sampling to the k most likely tokens."
|
||||
},
|
||||
"TopPSamplingStrategy": {
|
||||
"type": "object",
|
||||
|
|
@ -5690,21 +5695,25 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "top_p",
|
||||
"default": "top_p"
|
||||
"default": "top_p",
|
||||
"description": "Must be \"top_p\" to identify this sampling strategy"
|
||||
},
|
||||
"temperature": {
|
||||
"type": "number"
|
||||
"type": "number",
|
||||
"description": "Controls randomness in sampling. Higher values increase randomness"
|
||||
},
|
||||
"top_p": {
|
||||
"type": "number",
|
||||
"default": 0.95
|
||||
"default": 0.95,
|
||||
"description": "Cumulative probability threshold for nucleus sampling. Defaults to 0.95"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "TopPSamplingStrategy"
|
||||
"title": "TopPSamplingStrategy",
|
||||
"description": "Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p."
|
||||
},
|
||||
"URL": {
|
||||
"type": "object",
|
||||
|
|
@ -5808,14 +5817,16 @@
|
|||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/ChatCompletionResponse"
|
||||
}
|
||||
},
|
||||
"description": "List of chat completion responses, one for each conversation in the batch"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"batch"
|
||||
],
|
||||
"title": "BatchChatCompletionResponse"
|
||||
"title": "BatchChatCompletionResponse",
|
||||
"description": "Response from a batch chat completion request."
|
||||
},
|
||||
"ChatCompletionResponse": {
|
||||
"type": "object",
|
||||
|
|
@ -5939,14 +5950,16 @@
|
|||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/CompletionResponse"
|
||||
}
|
||||
},
|
||||
"description": "List of completion responses, one for each input in the batch"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"batch"
|
||||
],
|
||||
"title": "BatchCompletionResponse"
|
||||
"title": "BatchCompletionResponse",
|
||||
"description": "Response from a batch completion request."
|
||||
},
|
||||
"CompletionResponse": {
|
||||
"type": "object",
|
||||
|
|
@ -6938,7 +6951,8 @@
|
|||
"type": "object",
|
||||
"properties": {
|
||||
"call_id": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "Unique identifier for the tool call this response is for"
|
||||
},
|
||||
"tool_name": {
|
||||
"oneOf": [
|
||||
|
|
@ -6955,10 +6969,12 @@
|
|||
{
|
||||
"type": "string"
|
||||
}
|
||||
]
|
||||
],
|
||||
"description": "Name of the tool that was invoked"
|
||||
},
|
||||
"content": {
|
||||
"$ref": "#/components/schemas/InterleavedContent"
|
||||
"$ref": "#/components/schemas/InterleavedContent",
|
||||
"description": "The response content from the tool"
|
||||
},
|
||||
"metadata": {
|
||||
"type": "object",
|
||||
|
|
@ -6983,7 +6999,8 @@
|
|||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"description": "(Optional) Additional metadata about the tool response"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -6992,7 +7009,8 @@
|
|||
"tool_name",
|
||||
"content"
|
||||
],
|
||||
"title": "ToolResponse"
|
||||
"title": "ToolResponse",
|
||||
"description": "Response from a tool invocation."
|
||||
},
|
||||
"Turn": {
|
||||
"type": "object",
|
||||
|
|
@ -9838,10 +9856,12 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "image_url",
|
||||
"default": "image_url"
|
||||
"default": "image_url",
|
||||
"description": "Must be \"image_url\" to identify this as image content"
|
||||
},
|
||||
"image_url": {
|
||||
"$ref": "#/components/schemas/OpenAIImageURL"
|
||||
"$ref": "#/components/schemas/OpenAIImageURL",
|
||||
"description": "Image URL specification and processing details"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -9849,7 +9869,8 @@
|
|||
"type",
|
||||
"image_url"
|
||||
],
|
||||
"title": "OpenAIChatCompletionContentPartImageParam"
|
||||
"title": "OpenAIChatCompletionContentPartImageParam",
|
||||
"description": "Image content part for OpenAI-compatible chat completion messages."
|
||||
},
|
||||
"OpenAIChatCompletionContentPartParam": {
|
||||
"oneOf": [
|
||||
|
|
@ -9874,10 +9895,12 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "text",
|
||||
"default": "text"
|
||||
"default": "text",
|
||||
"description": "Must be \"text\" to identify this as text content"
|
||||
},
|
||||
"text": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "The text content of the message"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -9885,44 +9908,53 @@
|
|||
"type",
|
||||
"text"
|
||||
],
|
||||
"title": "OpenAIChatCompletionContentPartTextParam"
|
||||
"title": "OpenAIChatCompletionContentPartTextParam",
|
||||
"description": "Text content part for OpenAI-compatible chat completion messages."
|
||||
},
|
||||
"OpenAIChatCompletionToolCall": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"index": {
|
||||
"type": "integer"
|
||||
"type": "integer",
|
||||
"description": "(Optional) Index of the tool call in the list"
|
||||
},
|
||||
"id": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "(Optional) Unique identifier for the tool call"
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "function",
|
||||
"default": "function"
|
||||
"default": "function",
|
||||
"description": "Must be \"function\" to identify this as a function call"
|
||||
},
|
||||
"function": {
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionToolCallFunction"
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionToolCallFunction",
|
||||
"description": "(Optional) Function call details"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIChatCompletionToolCall"
|
||||
"title": "OpenAIChatCompletionToolCall",
|
||||
"description": "Tool call specification for OpenAI-compatible chat completion responses."
|
||||
},
|
||||
"OpenAIChatCompletionToolCallFunction": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "(Optional) Name of the function to call"
|
||||
},
|
||||
"arguments": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "(Optional) Arguments to pass to the function as a JSON string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"title": "OpenAIChatCompletionToolCallFunction"
|
||||
"title": "OpenAIChatCompletionToolCallFunction",
|
||||
"description": "Function call details for OpenAI-compatible tool calls."
|
||||
},
|
||||
"OpenAIChoice": {
|
||||
"type": "object",
|
||||
|
|
@ -10015,17 +10047,20 @@
|
|||
"type": "object",
|
||||
"properties": {
|
||||
"url": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "URL of the image to include in the message"
|
||||
},
|
||||
"detail": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "(Optional) Level of detail for image processing. Can be \"low\", \"high\", or \"auto\""
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"url"
|
||||
],
|
||||
"title": "OpenAIImageURL"
|
||||
"title": "OpenAIImageURL",
|
||||
"description": "Image URL specification for OpenAI-compatible chat completion messages."
|
||||
},
|
||||
"OpenAIMessageParam": {
|
||||
"oneOf": [
|
||||
|
|
@ -11882,21 +11917,26 @@
|
|||
"input_messages"
|
||||
],
|
||||
"title": "OpenAICompletionWithInputMessages"
|
||||
}
|
||||
},
|
||||
"description": "List of chat completion objects with their input messages"
|
||||
},
|
||||
"has_more": {
|
||||
"type": "boolean"
|
||||
"type": "boolean",
|
||||
"description": "Whether there are more completions available beyond this list"
|
||||
},
|
||||
"first_id": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "ID of the first completion in this list"
|
||||
},
|
||||
"last_id": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "ID of the last completion in this list"
|
||||
},
|
||||
"object": {
|
||||
"type": "string",
|
||||
"const": "list",
|
||||
"default": "list"
|
||||
"default": "list",
|
||||
"description": "Must be \"list\" to identify this as a list response"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -11907,7 +11947,8 @@
|
|||
"last_id",
|
||||
"object"
|
||||
],
|
||||
"title": "ListOpenAIChatCompletionResponse"
|
||||
"title": "ListOpenAIChatCompletionResponse",
|
||||
"description": "Response from listing OpenAI-compatible chat completions."
|
||||
},
|
||||
"ListDatasetsResponse": {
|
||||
"type": "object",
|
||||
|
|
@ -12762,13 +12803,16 @@
|
|||
"type": "object",
|
||||
"properties": {
|
||||
"name": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "Name of the schema"
|
||||
},
|
||||
"description": {
|
||||
"type": "string"
|
||||
"type": "string",
|
||||
"description": "(Optional) Description of the schema"
|
||||
},
|
||||
"strict": {
|
||||
"type": "boolean"
|
||||
"type": "boolean",
|
||||
"description": "(Optional) Whether to enforce strict adherence to the schema"
|
||||
},
|
||||
"schema": {
|
||||
"type": "object",
|
||||
|
|
@ -12793,14 +12837,16 @@
|
|||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"description": "(Optional) The JSON schema definition"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"name"
|
||||
],
|
||||
"title": "OpenAIJSONSchema"
|
||||
"title": "OpenAIJSONSchema",
|
||||
"description": "JSON schema specification for OpenAI-compatible structured response format."
|
||||
},
|
||||
"OpenAIResponseFormatJSONObject": {
|
||||
"type": "object",
|
||||
|
|
@ -12808,14 +12854,16 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "json_object",
|
||||
"default": "json_object"
|
||||
"default": "json_object",
|
||||
"description": "Must be \"json_object\" to indicate generic JSON object response format"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseFormatJSONObject"
|
||||
"title": "OpenAIResponseFormatJSONObject",
|
||||
"description": "JSON object response format for OpenAI-compatible chat completion requests."
|
||||
},
|
||||
"OpenAIResponseFormatJSONSchema": {
|
||||
"type": "object",
|
||||
|
|
@ -12823,10 +12871,12 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "json_schema",
|
||||
"default": "json_schema"
|
||||
"default": "json_schema",
|
||||
"description": "Must be \"json_schema\" to indicate structured JSON response format"
|
||||
},
|
||||
"json_schema": {
|
||||
"$ref": "#/components/schemas/OpenAIJSONSchema"
|
||||
"$ref": "#/components/schemas/OpenAIJSONSchema",
|
||||
"description": "The JSON schema specification for the response"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
@ -12834,7 +12884,8 @@
|
|||
"type",
|
||||
"json_schema"
|
||||
],
|
||||
"title": "OpenAIResponseFormatJSONSchema"
|
||||
"title": "OpenAIResponseFormatJSONSchema",
|
||||
"description": "JSON schema response format for OpenAI-compatible chat completion requests."
|
||||
},
|
||||
"OpenAIResponseFormatParam": {
|
||||
"oneOf": [
|
||||
|
|
@ -12863,14 +12914,16 @@
|
|||
"type": {
|
||||
"type": "string",
|
||||
"const": "text",
|
||||
"default": "text"
|
||||
"default": "text",
|
||||
"description": "Must be \"text\" to indicate plain text response format"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseFormatText"
|
||||
"title": "OpenAIResponseFormatText",
|
||||
"description": "Text response format for OpenAI-compatible chat completion requests."
|
||||
},
|
||||
"OpenaiChatCompletionRequest": {
|
||||
"type": "object",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue