mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-25 13:48:03 +00:00
Inference
This commit is contained in:
Sai Soundararaj
parent
c5fd9886ae
commit
8fc72e4669
3 changed files with 297 additions and 53 deletions
98
docs/_static/llama-stack-spec.yaml
vendored
98
docs/_static/llama-stack-spec.yaml
vendored
|
|
@ -3636,10 +3636,15 @@ components:
|
|||
type: string
|
||||
const: greedy
|
||||
default: greedy
|
||||
description: >-
|
||||
Must be "greedy" to identify this sampling strategy
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: GreedySamplingStrategy
|
||||
description: >-
|
||||
Greedy sampling strategy that selects the highest probability token at each
|
||||
step.
|
||||
ImageContentItem:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -3997,13 +4002,19 @@ components:
|
|||
type: string
|
||||
const: top_k
|
||||
default: top_k
|
||||
description: >-
|
||||
Must be "top_k" to identify this sampling strategy
|
||||
top_k:
|
||||
type: integer
|
||||
description: >-
|
||||
Number of top tokens to consider for sampling. Must be at least 1
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- top_k
|
||||
title: TopKSamplingStrategy
|
||||
description: >-
|
||||
Top-k sampling strategy that restricts sampling to the k most likely tokens.
|
||||
TopPSamplingStrategy:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -4011,15 +4022,24 @@ components:
|
|||
type: string
|
||||
const: top_p
|
||||
default: top_p
|
||||
description: >-
|
||||
Must be "top_p" to identify this sampling strategy
|
||||
temperature:
|
||||
type: number
|
||||
description: >-
|
||||
Controls randomness in sampling. Higher values increase randomness
|
||||
top_p:
|
||||
type: number
|
||||
default: 0.95
|
||||
description: >-
|
||||
Cumulative probability threshold for nucleus sampling. Defaults to 0.95
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: TopPSamplingStrategy
|
||||
description: >-
|
||||
Top-p (nucleus) sampling strategy that samples from the smallest set of tokens
|
||||
with cumulative probability >= p.
|
||||
URL:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -4111,10 +4131,14 @@ components:
|
|||
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
|
||||
description: >-
|
||||
Response from a batch chat completion request.
|
||||
ChatCompletionResponse:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -4211,10 +4235,14 @@ components:
|
|||
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
|
||||
description: >-
|
||||
Response from a batch completion request.
|
||||
CompletionResponse:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -4967,6 +4995,8 @@ components:
|
|||
properties:
|
||||
call_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier for the tool call this response is for
|
||||
tool_name:
|
||||
oneOf:
|
||||
- type: string
|
||||
|
|
@ -4977,8 +5007,10 @@ components:
|
|||
- code_interpreter
|
||||
title: BuiltinTool
|
||||
- type: string
|
||||
description: Name of the tool that was invoked
|
||||
content:
|
||||
$ref: '#/components/schemas/InterleavedContent'
|
||||
description: The response content from the tool
|
||||
metadata:
|
||||
type: object
|
||||
additionalProperties:
|
||||
|
|
@ -4989,12 +5021,15 @@ components:
|
|||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: >-
|
||||
(Optional) Additional metadata about the tool response
|
||||
additionalProperties: false
|
||||
required:
|
||||
- call_id
|
||||
- tool_name
|
||||
- content
|
||||
title: ToolResponse
|
||||
description: Response from a tool invocation.
|
||||
Turn:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -6991,14 +7026,20 @@ components:
|
|||
type: string
|
||||
const: image_url
|
||||
default: image_url
|
||||
description: >-
|
||||
Must be "image_url" to identify this as image content
|
||||
image_url:
|
||||
$ref: '#/components/schemas/OpenAIImageURL'
|
||||
description: >-
|
||||
Image URL specification and processing details
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- image_url
|
||||
title: >-
|
||||
OpenAIChatCompletionContentPartImageParam
|
||||
description: >-
|
||||
Image content part for OpenAI-compatible chat completion messages.
|
||||
OpenAIChatCompletionContentPartParam:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
|
||||
|
|
@ -7015,39 +7056,58 @@ components:
|
|||
type: string
|
||||
const: text
|
||||
default: text
|
||||
description: >-
|
||||
Must be "text" to identify this as text content
|
||||
text:
|
||||
type: string
|
||||
description: The text content of the message
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- text
|
||||
title: OpenAIChatCompletionContentPartTextParam
|
||||
description: >-
|
||||
Text content part for OpenAI-compatible chat completion messages.
|
||||
OpenAIChatCompletionToolCall:
|
||||
type: object
|
||||
properties:
|
||||
index:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) Index of the tool call in the list
|
||||
id:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) Unique identifier for the tool call
|
||||
type:
|
||||
type: string
|
||||
const: function
|
||||
default: function
|
||||
description: >-
|
||||
Must be "function" to identify this as a function call
|
||||
function:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
|
||||
description: (Optional) Function call details
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: OpenAIChatCompletionToolCall
|
||||
description: >-
|
||||
Tool call specification for OpenAI-compatible chat completion responses.
|
||||
OpenAIChatCompletionToolCallFunction:
|
||||
type: object
|
||||
properties:
|
||||
name:
|
||||
type: string
|
||||
description: (Optional) Name of the function to call
|
||||
arguments:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) Arguments to pass to the function as a JSON string
|
||||
additionalProperties: false
|
||||
title: OpenAIChatCompletionToolCallFunction
|
||||
description: >-
|
||||
Function call details for OpenAI-compatible tool calls.
|
||||
OpenAIChoice:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -7124,12 +7184,19 @@ components:
|
|||
properties:
|
||||
url:
|
||||
type: string
|
||||
description: >-
|
||||
URL of the image to include in the message
|
||||
detail:
|
||||
type: string
|
||||
description: >-
|
||||
(Optional) Level of detail for image processing. Can be "low", "high",
|
||||
or "auto"
|
||||
additionalProperties: false
|
||||
required:
|
||||
- url
|
||||
title: OpenAIImageURL
|
||||
description: >-
|
||||
Image URL specification for OpenAI-compatible chat completion messages.
|
||||
OpenAIMessageParam:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIUserMessageParam'
|
||||
|
|
@ -8405,16 +8472,24 @@ components:
|
|||
- model
|
||||
- input_messages
|
||||
title: OpenAICompletionWithInputMessages
|
||||
description: >-
|
||||
List of chat completion objects with their input messages
|
||||
has_more:
|
||||
type: boolean
|
||||
description: >-
|
||||
Whether there are more completions available beyond this list
|
||||
first_id:
|
||||
type: string
|
||||
description: ID of the first completion in this list
|
||||
last_id:
|
||||
type: string
|
||||
description: ID of the last completion in this list
|
||||
object:
|
||||
type: string
|
||||
const: list
|
||||
default: list
|
||||
description: >-
|
||||
Must be "list" to identify this as a list response
|
||||
additionalProperties: false
|
||||
required:
|
||||
- data
|
||||
|
|
@ -8423,6 +8498,8 @@ components:
|
|||
- last_id
|
||||
- object
|
||||
title: ListOpenAIChatCompletionResponse
|
||||
description: >-
|
||||
Response from listing OpenAI-compatible chat completions.
|
||||
ListDatasetsResponse:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -8989,10 +9066,14 @@ components:
|
|||
properties:
|
||||
name:
|
||||
type: string
|
||||
description: Name of the schema
|
||||
description:
|
||||
type: string
|
||||
description: (Optional) Description of the schema
|
||||
strict:
|
||||
type: boolean
|
||||
description: >-
|
||||
(Optional) Whether to enforce strict adherence to the schema
|
||||
schema:
|
||||
type: object
|
||||
additionalProperties:
|
||||
|
|
@ -9003,10 +9084,13 @@ components:
|
|||
- type: string
|
||||
- type: array
|
||||
- type: object
|
||||
description: (Optional) The JSON schema definition
|
||||
additionalProperties: false
|
||||
required:
|
||||
- name
|
||||
title: OpenAIJSONSchema
|
||||
description: >-
|
||||
JSON schema specification for OpenAI-compatible structured response format.
|
||||
OpenAIResponseFormatJSONObject:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -9014,10 +9098,14 @@ components:
|
|||
type: string
|
||||
const: json_object
|
||||
default: json_object
|
||||
description: >-
|
||||
Must be "json_object" to indicate generic JSON object response format
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: OpenAIResponseFormatJSONObject
|
||||
description: >-
|
||||
JSON object response format for OpenAI-compatible chat completion requests.
|
||||
OpenAIResponseFormatJSONSchema:
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -9025,13 +9113,19 @@ components:
|
|||
type: string
|
||||
const: json_schema
|
||||
default: json_schema
|
||||
description: >-
|
||||
Must be "json_schema" to indicate structured JSON response format
|
||||
json_schema:
|
||||
$ref: '#/components/schemas/OpenAIJSONSchema'
|
||||
description: >-
|
||||
The JSON schema specification for the response
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- json_schema
|
||||
title: OpenAIResponseFormatJSONSchema
|
||||
description: >-
|
||||
JSON schema response format for OpenAI-compatible chat completion requests.
|
||||
OpenAIResponseFormatParam:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseFormatText'
|
||||
|
|
@ -9050,10 +9144,14 @@ components:
|
|||
type: string
|
||||
const: text
|
||||
default: text
|
||||
description: >-
|
||||
Must be "text" to indicate plain text response format
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
title: OpenAIResponseFormatText
|
||||
description: >-
|
||||
Text response format for OpenAI-compatible chat completion requests.
|
||||
OpenaiChatCompletionRequest:
|
||||
type: object
|
||||
properties:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue