mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-11 21:48:36 +00:00
test
# What does this PR do? ## Test Plan
This commit is contained in:
Eric Huang
parent
f50ce11a3b
commit
972f2395a1
29 changed files with 1726 additions and 2149 deletions
309
docs/static/deprecated-llama-stack-spec.yaml
vendored
309
docs/static/deprecated-llama-stack-spec.yaml
vendored
|
|
@ -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
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue