phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 04:00:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

merge from main and run precommit again

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-22 12:17:48 -07:00
parent 13450c1a68
commit 678978a2c9
1 changed files with 30 additions and 126 deletions
Download patch file Download diff file Expand all files Collapse all files

130
client-sdks/stainless/openapi.yml
View file

@ -350,146 +350,46 @@ paths:
in: query
description: >-
An item ID to list items after, used in pagination.
required: true
required: false
schema:
oneOf:
- 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.
```
type: string
- name: include
in: query
description: >-
Specify additional output data to include in the response.
required: true
required: false
schema:
oneOf:
- type: array
type: array
items:
type: string
enum:
- web_search_call.action.sources
- code_interpreter_call.outputs
- computer_call_output.output.image_url
- file_search_call.results
- message.input_image.image_url
- message.output_text.logprobs
- reasoning.encrypted_content
- type: object
title: NotGiven
title: ConversationItemInclude
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.
```
Specify additional output data to include in the model response.
- name: limit
in: query
description: >-
A limit on the number of objects to be returned (1-100, default 20).
required: true
required: false
schema:
oneOf:
- 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.
```
type: integer
- name: order
in: query
description: >-
The order to return items in (asc or desc, default desc).
required: true
required: false
schema:
oneOf:
- type: string
type: string
enum:
- asc
- 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
post:
responses:
@ -6482,6 +6382,7 @@ components:
enum:
- llm
- embedding
- rerank
title: ModelType
description: >-
Enumeration of supported model types in Llama Stack.
@ -13585,13 +13486,16 @@ tags:
embeddings.
This API provides the raw interface to the underlying models. Two kinds of models
are supported:
This API provides the raw interface to the underlying models. Three kinds of
models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic
search.
- Rerank models: these models reorder the documents based on their relevance
to a query.
x-displayName: Inference
- name: Inspect
description: >-