phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 23:14:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into nvidia-eval-integration

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-15 13:36:42 -04:00
commit 72711287ec
96 changed files with 9868 additions and 1444 deletions
Download patch file Download diff file Expand all files Collapse all files

451
docs/_static/llama-stack-spec.yaml vendored
View file

@ -40,7 +40,7 @@ paths:
schema:
$ref: '#/components/schemas/AppendRowsRequest'
required: true
/v1/batch-inference/chat-completion:
/v1/inference/batch-chat-completion:
post:
responses:
'200':
@ -60,7 +60,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- BatchInference (Coming Soon)
- Inference
description: ''
parameters: []
requestBody:
@ -69,7 +69,7 @@ paths:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
/v1/batch-inference/completion:
/v1/inference/batch-completion:
post:
responses:
'200':
@ -89,7 +89,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- BatchInference (Coming Soon)
- Inference
description: ''
parameters: []
requestBody:
@ -148,7 +148,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
- BatchInference (Coming Soon)
description: >-
Generate a chat completion for the given messages using the specified model.
parameters: []
@ -183,7 +183,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
- BatchInference (Coming Soon)
description: >-
Generate a completion for the given content using the specified model.
parameters: []
@ -2135,11 +2135,15 @@ paths:
post:
responses:
'200':
description: OK
description: >-
Response from an OpenAI-compatible chat completion request. **OR** Chunk
from a streaming response to an OpenAI-compatible chat completion request.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIChatCompletion'
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletion'
- $ref: '#/components/schemas/OpenAIChatCompletionChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -3009,6 +3013,54 @@ components:
- tool_name
- arguments
title: ToolCall
ToolConfig:
type: object
properties:
tool_choice:
oneOf:
- type: string
enum:
- auto
- required
- none
title: ToolChoice
description: >-
Whether tool use is required or automatic. This is a hint to the model
which may not be followed. It depends on the Instruction Following
capabilities of the model.
- type: string
default: auto
description: >-
(Optional) Whether tool use is automatic, required, or none. Can also
specify a tool name to use a specific tool. Defaults to ToolChoice.auto.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
description: >-
(Optional) Instructs the model how to format tool calls. By default, Llama
Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name>
tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python
syntax -- a list of function calls.
system_message_behavior:
type: string
enum:
- append
- replace
description: >-
(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`:
Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`:
Replaces the default system prompt with the provided system message. The
system message can include the string '{{function_definitions}}' to indicate
where the function definitions should be inserted.
default: append
additionalProperties: false
title: ToolConfig
description: Configuration for tool use.
ToolDefinition:
type: object
properties:
@ -3145,7 +3197,7 @@ components:
BatchChatCompletionRequest:
type: object
properties:
model:
model_id:
type: string
messages_batch:
type: array
@ -3159,26 +3211,8 @@ components:
type: array
items:
$ref: '#/components/schemas/ToolDefinition'
tool_choice:
type: string
enum:
- auto
- required
- none
title: ToolChoice
description: >-
Whether tool use is required or automatic. This is a hint to the model
which may not be followed. It depends on the Instruction Following capabilities
of the model.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
title: ToolPromptFormat
description: >-
Prompt format for calling custom / zero shot tools.
tool_config:
$ref: '#/components/schemas/ToolConfig'
response_format:
$ref: '#/components/schemas/ResponseFormat'
logprobs:
@ -3193,7 +3227,7 @@ components:
title: LogProbConfig
additionalProperties: false
required:
- model
- model_id
- messages_batch
title: BatchChatCompletionRequest
BatchChatCompletionResponse:
@ -3261,7 +3295,7 @@ components:
BatchCompletionRequest:
type: object
properties:
model:
model_id:
type: string
content_batch:
type: array
@ -3283,7 +3317,7 @@ components:
title: LogProbConfig
additionalProperties: false
required:
- model
- model_id
- content_batch
title: BatchCompletionRequest
BatchCompletionResponse:
@ -3335,54 +3369,6 @@ components:
required:
- job_uuid
title: CancelTrainingJobRequest
ToolConfig:
type: object
properties:
tool_choice:
oneOf:
- type: string
enum:
- auto
- required
- none
title: ToolChoice
description: >-
Whether tool use is required or automatic. This is a hint to the model
which may not be followed. It depends on the Instruction Following
capabilities of the model.
- type: string
default: auto
description: >-
(Optional) Whether tool use is automatic, required, or none. Can also
specify a tool name to use a specific tool. Defaults to ToolChoice.auto.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
description: >-
(Optional) Instructs the model how to format tool calls. By default, Llama
Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name>
tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python
syntax -- a list of function calls.
system_message_behavior:
type: string
enum:
- append
- replace
description: >-
(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`:
Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`:
Replaces the default system prompt with the provided system message. The
system message can include the string '{{function_definitions}}' to indicate
where the function definitions should be inserted.
default: append
additionalProperties: false
title: ToolConfig
description: Configuration for tool use.
ChatCompletionRequest:
type: object
properties:
@ -5480,6 +5466,11 @@ components:
properties:
status:
type: string
enum:
- OK
- Error
- Not Implemented
title: HealthStatus
additionalProperties: false
required:
- status
@ -5591,12 +5582,23 @@ components:
- type: string
- type: array
- type: object
health:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- api
- provider_id
- provider_type
- config
- health
title: ProviderInfo
InvokeToolRequest:
type: object
@ -6074,7 +6076,11 @@ components:
description: >-
Must be "assistant" to identify this as the model's response
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The content of the model's response
name:
type: string
@ -6083,9 +6089,10 @@ components:
tool_calls:
type: array
items:
$ref: '#/components/schemas/ToolCall'
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
description: >-
List of tool calls. Each tool call is a ToolCall object.
List of tool calls. Each tool call is an OpenAIChatCompletionToolCall
object.
additionalProperties: false
required:
- role
@ -6094,6 +6101,70 @@ components:
description: >-
A message containing the model's (assistant) response in an OpenAI-compatible
chat completion request.
"OpenAIChatCompletionContentPartImageParam":
type: object
properties:
type:
type: string
const: image_url
default: image_url
image_url:
$ref: '#/components/schemas/OpenAIImageURL'
additionalProperties: false
required:
- type
- image_url
title: >-
OpenAIChatCompletionContentPartImageParam
OpenAIChatCompletionContentPartParam:
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
OpenAIChatCompletionContentPartTextParam:
type: object
properties:
type:
type: string
const: text
default: text
text:
type: string
additionalProperties: false
required:
- type
- text
title: OpenAIChatCompletionContentPartTextParam
OpenAIChatCompletionToolCall:
type: object
properties:
index:
type: integer
id:
type: string
type:
type: string
const: function
default: function
function:
$ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
additionalProperties: false
required:
- type
title: OpenAIChatCompletionToolCall
OpenAIChatCompletionToolCallFunction:
type: object
properties:
name:
type: string
arguments:
type: string
additionalProperties: false
title: OpenAIChatCompletionToolCallFunction
OpenAIDeveloperMessageParam:
type: object
properties:
@ -6104,7 +6175,11 @@ components:
description: >-
Must be "developer" to identify this as a developer message
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The content of the developer message
name:
type: string
@ -6117,6 +6192,40 @@ components:
title: OpenAIDeveloperMessageParam
description: >-
A message from the developer in an OpenAI-compatible chat completion request.
OpenAIImageURL:
type: object
properties:
url:
type: string
detail:
type: string
additionalProperties: false
required:
- url
title: OpenAIImageURL
OpenAIJSONSchema:
type: object
properties:
name:
type: string
description:
type: string
strict:
type: boolean
schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- name
title: OpenAIJSONSchema
OpenAIMessageParam:
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam'
@ -6132,6 +6241,53 @@ components:
assistant: '#/components/schemas/OpenAIAssistantMessageParam'
tool: '#/components/schemas/OpenAIToolMessageParam'
developer: '#/components/schemas/OpenAIDeveloperMessageParam'
OpenAIResponseFormatJSONObject:
type: object
properties:
type:
type: string
const: json_object
default: json_object
additionalProperties: false
required:
- type
title: OpenAIResponseFormatJSONObject
OpenAIResponseFormatJSONSchema:
type: object
properties:
type:
type: string
const: json_schema
default: json_schema
json_schema:
$ref: '#/components/schemas/OpenAIJSONSchema'
additionalProperties: false
required:
- type
- json_schema
title: OpenAIResponseFormatJSONSchema
OpenAIResponseFormatParam:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseFormatText'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONObject'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/OpenAIResponseFormatText'
json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema'
json_object: '#/components/schemas/OpenAIResponseFormatJSONObject'
OpenAIResponseFormatText:
type: object
properties:
type:
type: string
const: text
default: text
additionalProperties: false
required:
- type
title: OpenAIResponseFormatText
OpenAISystemMessageParam:
type: object
properties:
@ -6142,7 +6298,11 @@ components:
description: >-
Must be "system" to identify this as a system message
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
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
@ -6172,7 +6332,11 @@ components:
description: >-
Unique identifier for the tool call this response is for
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The response content from the tool
additionalProperties: false
required:
@ -6193,7 +6357,11 @@ components:
description: >-
Must be "user" to identify this as a user message
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: >-
The content of the message, which can include text and other media
name:
@ -6279,9 +6447,7 @@ components:
description: >-
(Optional) The penalty for repeated tokens
response_format:
type: object
additionalProperties:
type: string
$ref: '#/components/schemas/OpenAIResponseFormatParam'
description: (Optional) The response format to use
seed:
type: integer
@ -6387,6 +6553,41 @@ components:
title: OpenAIChatCompletion
description: >-
Response from an OpenAI-compatible chat completion request.
OpenAIChatCompletionChunk:
type: object
properties:
id:
type: string
description: The ID of the chat completion
choices:
type: array
items:
$ref: '#/components/schemas/OpenAIChunkChoice'
description: List of choices
object:
type: string
const: chat.completion.chunk
default: chat.completion.chunk
description: >-
The object type, which will be "chat.completion.chunk"
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: OpenAIChatCompletionChunk
description: >-
Chunk from a streaming response to an OpenAI-compatible chat completion request.
OpenAIChoice:
type: object
properties:
@ -6398,8 +6599,11 @@ components:
description: The reason the model stopped generating
index:
type: integer
description: The index of the choice
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
required:
- message
@ -6408,6 +6612,27 @@ components:
title: OpenAIChoice
description: >-
A choice from an OpenAI-compatible chat completion response.
OpenAIChoiceDelta:
type: object
properties:
content:
type: string
description: (Optional) The content of the delta
refusal:
type: string
description: (Optional) The refusal of the delta
role:
type: string
description: (Optional) The role of the delta
tool_calls:
type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
description: (Optional) The tool calls of the delta
additionalProperties: false
title: OpenAIChoiceDelta
description: >-
A delta from an OpenAI-compatible chat completion streaming response.
OpenAIChoiceLogprobs:
type: object
properties:
@ -6415,15 +6640,43 @@ components:
type: array
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
description: >-
(Optional) The log probabilities for the tokens in the message
refusal:
type: array
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
title: OpenAIChoiceLogprobs
description: >-
The log probabilities for the tokens in the message from an OpenAI-compatible
chat completion response.
OpenAIChunkChoice:
type: object
properties:
delta:
$ref: '#/components/schemas/OpenAIChoiceDelta'
description: The delta from the chunk
finish_reason:
type: string
description: The reason the model stopped generating
index:
type: integer
description: The index of the choice
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
required:
- delta
- finish_reason
- index
title: OpenAIChunkChoice
description: >-
A chunk choice from an OpenAI-compatible chat completion streaming response.
OpenAITokenLogProb:
type: object
properties:
@ -6743,10 +6996,13 @@ components:
type: integer
max_steps_per_epoch:
type: integer
default: 1
gradient_accumulation_steps:
type: integer
default: 1
max_validation_steps:
type: integer
default: 1
data_config:
$ref: '#/components/schemas/DataConfig'
optimizer_config:
@ -6761,9 +7017,6 @@ components:
- n_epochs
- max_steps_per_epoch
- gradient_accumulation_steps
- max_validation_steps
- data_config
- optimizer_config
title: TrainingConfig
PreferenceOptimizeRequest:
type: object
@ -7497,7 +7750,6 @@ components:
- training_config
- hyperparam_search_config
- logger_config
- model
title: SupervisedFineTuneRequest
SyntheticDataGenerateRequest:
type: object
@ -7632,6 +7884,17 @@ tags:
x-displayName: >-
Agents API for creating and interacting with agentic systems.
- name: BatchInference (Coming Soon)
description: >-
This is an asynchronous API. If the request is successful, the response will
be a job which can be polled for completion.
NOTE: This API is not yet implemented and is subject to change in concert with
other asynchronous APIs
including (post-training, evals, etc).
x-displayName: >-
Batch inference API for generating completions and chat completions.
- name: Benchmarks
- name: DatasetIO
- name: Datasets