mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-12 12:06:04 +00:00
merge from main and run precommit again
This commit is contained in:
parent
13450c1a68
commit
678978a2c9
1 changed files with 30 additions and 126 deletions
|
|
@ -350,146 +350,46 @@ paths:
|
||||||
in: query
|
in: query
|
||||||
description: >-
|
description: >-
|
||||||
An item ID to list items after, used in pagination.
|
An item ID to list items after, used in pagination.
|
||||||
required: true
|
required: false
|
||||||
schema:
|
schema:
|
||||||
oneOf:
|
type: string
|
||||||
- type: string
|
|
||||||
- type: object
|
|
||||||
title: NotGiven
|
|
||||||
description: >-
|
|
||||||
A sentinel singleton class used to distinguish omitted keyword arguments
|
|
||||||
from those passed in with the value None (which may have different
|
|
||||||
behavior).
|
|
||||||
|
|
||||||
For example:
|
|
||||||
|
|
||||||
|
|
||||||
```py
|
|
||||||
|
|
||||||
def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response:
|
|
||||||
...
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
get(timeout=1) # 1s timeout
|
|
||||||
|
|
||||||
get(timeout=None) # No timeout
|
|
||||||
|
|
||||||
get() # Default timeout behavior, which may not be statically known
|
|
||||||
at the method definition.
|
|
||||||
|
|
||||||
```
|
|
||||||
- name: include
|
- name: include
|
||||||
in: query
|
in: query
|
||||||
description: >-
|
description: >-
|
||||||
Specify additional output data to include in the response.
|
Specify additional output data to include in the response.
|
||||||
required: true
|
required: false
|
||||||
schema:
|
schema:
|
||||||
oneOf:
|
type: array
|
||||||
- type: array
|
|
||||||
items:
|
items:
|
||||||
type: string
|
type: string
|
||||||
enum:
|
enum:
|
||||||
|
- web_search_call.action.sources
|
||||||
- code_interpreter_call.outputs
|
- code_interpreter_call.outputs
|
||||||
- computer_call_output.output.image_url
|
- computer_call_output.output.image_url
|
||||||
- file_search_call.results
|
- file_search_call.results
|
||||||
- message.input_image.image_url
|
- message.input_image.image_url
|
||||||
- message.output_text.logprobs
|
- message.output_text.logprobs
|
||||||
- reasoning.encrypted_content
|
- reasoning.encrypted_content
|
||||||
- type: object
|
title: ConversationItemInclude
|
||||||
title: NotGiven
|
|
||||||
description: >-
|
description: >-
|
||||||
A sentinel singleton class used to distinguish omitted keyword arguments
|
Specify additional output data to include in the model response.
|
||||||
from those passed in with the value None (which may have different
|
|
||||||
behavior).
|
|
||||||
|
|
||||||
For example:
|
|
||||||
|
|
||||||
|
|
||||||
```py
|
|
||||||
|
|
||||||
def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response:
|
|
||||||
...
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
get(timeout=1) # 1s timeout
|
|
||||||
|
|
||||||
get(timeout=None) # No timeout
|
|
||||||
|
|
||||||
get() # Default timeout behavior, which may not be statically known
|
|
||||||
at the method definition.
|
|
||||||
|
|
||||||
```
|
|
||||||
- name: limit
|
- name: limit
|
||||||
in: query
|
in: query
|
||||||
description: >-
|
description: >-
|
||||||
A limit on the number of objects to be returned (1-100, default 20).
|
A limit on the number of objects to be returned (1-100, default 20).
|
||||||
required: true
|
required: false
|
||||||
schema:
|
schema:
|
||||||
oneOf:
|
type: integer
|
||||||
- type: integer
|
|
||||||
- type: object
|
|
||||||
title: NotGiven
|
|
||||||
description: >-
|
|
||||||
A sentinel singleton class used to distinguish omitted keyword arguments
|
|
||||||
from those passed in with the value None (which may have different
|
|
||||||
behavior).
|
|
||||||
|
|
||||||
For example:
|
|
||||||
|
|
||||||
|
|
||||||
```py
|
|
||||||
|
|
||||||
def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response:
|
|
||||||
...
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
get(timeout=1) # 1s timeout
|
|
||||||
|
|
||||||
get(timeout=None) # No timeout
|
|
||||||
|
|
||||||
get() # Default timeout behavior, which may not be statically known
|
|
||||||
at the method definition.
|
|
||||||
|
|
||||||
```
|
|
||||||
- name: order
|
- name: order
|
||||||
in: query
|
in: query
|
||||||
description: >-
|
description: >-
|
||||||
The order to return items in (asc or desc, default desc).
|
The order to return items in (asc or desc, default desc).
|
||||||
required: true
|
required: false
|
||||||
schema:
|
schema:
|
||||||
oneOf:
|
type: string
|
||||||
- type: string
|
|
||||||
enum:
|
enum:
|
||||||
- asc
|
- asc
|
||||||
- desc
|
- desc
|
||||||
- type: object
|
|
||||||
title: NotGiven
|
|
||||||
description: >-
|
|
||||||
A sentinel singleton class used to distinguish omitted keyword arguments
|
|
||||||
from those passed in with the value None (which may have different
|
|
||||||
behavior).
|
|
||||||
|
|
||||||
For example:
|
|
||||||
|
|
||||||
|
|
||||||
```py
|
|
||||||
|
|
||||||
def get(timeout: Union[int, NotGiven, None] = NotGiven()) -> Response:
|
|
||||||
...
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
get(timeout=1) # 1s timeout
|
|
||||||
|
|
||||||
get(timeout=None) # No timeout
|
|
||||||
|
|
||||||
get() # Default timeout behavior, which may not be statically known
|
|
||||||
at the method definition.
|
|
||||||
|
|
||||||
```
|
|
||||||
deprecated: false
|
deprecated: false
|
||||||
post:
|
post:
|
||||||
responses:
|
responses:
|
||||||
|
|
@ -6482,6 +6382,7 @@ components:
|
||||||
enum:
|
enum:
|
||||||
- llm
|
- llm
|
||||||
- embedding
|
- embedding
|
||||||
|
- rerank
|
||||||
title: ModelType
|
title: ModelType
|
||||||
description: >-
|
description: >-
|
||||||
Enumeration of supported model types in Llama Stack.
|
Enumeration of supported model types in Llama Stack.
|
||||||
|
|
@ -13585,13 +13486,16 @@ tags:
|
||||||
embeddings.
|
embeddings.
|
||||||
|
|
||||||
|
|
||||||
This API provides the raw interface to the underlying models. Two kinds of models
|
This API provides the raw interface to the underlying models. Three kinds of
|
||||||
are supported:
|
models are supported:
|
||||||
|
|
||||||
- LLM models: these models generate "raw" and "chat" (conversational) completions.
|
- LLM models: these models generate "raw" and "chat" (conversational) completions.
|
||||||
|
|
||||||
- Embedding models: these models generate embeddings to be used for semantic
|
- Embedding models: these models generate embeddings to be used for semantic
|
||||||
search.
|
search.
|
||||||
|
|
||||||
|
- Rerank models: these models reorder the documents based on their relevance
|
||||||
|
to a query.
|
||||||
x-displayName: Inference
|
x-displayName: Inference
|
||||||
- name: Inspect
|
- name: Inspect
|
||||||
description: >-
|
description: >-
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue