phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-23 00:27:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert "docs: API docstrings cleanup for better documentation rendering (#3661)"

Browse source 
This reverts commit a8da6ba3a7.
This commit is contained in:
Francisco Arceo 2025-10-07 10:18:47 -04:00 • committed by GitHub
parent 6389bf5ffb
commit 1b7e893cb5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 414 additions and 614 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/apis/inference/inference.py
View file

@ -1053,9 +1053,7 @@ class InferenceProvider(Protocol):
# for fill-in-the-middle type completion
suffix: str | None = None,
) -> OpenAICompletion:
"""Create completion.
Generate an OpenAI-compatible completion for the given prompt using the specified model.
"""Generate an OpenAI-compatible completion for the given prompt using the specified model.
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
:param prompt: The prompt to generate a completion for.
@ -1107,9 +1105,7 @@ class InferenceProvider(Protocol):
top_p: float | None = None,
user: str | None = None,
) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
"""Create chat completions.
Generate an OpenAI-compatible chat completion for the given messages using the specified model.
"""Generate an OpenAI-compatible chat completion for the given messages using the specified model.
:param model: The identifier of the model to use. The model must be registered with Llama Stack and available via the /models endpoint.
:param messages: List of messages in the conversation.
@ -1148,9 +1144,7 @@ class InferenceProvider(Protocol):
dimensions: int | None = None,
user: str | None = None,
) -> OpenAIEmbeddingsResponse:
"""Create embeddings.
Generate OpenAI-compatible embeddings for the given input using the specified model.
"""Generate OpenAI-compatible embeddings for the given input using the specified model.
:param model: The identifier of the model to use. The model must be an embedding model registered with Llama Stack and available via the /models endpoint.
:param input: Input text to embed, encoded as a string or array of strings. To embed multiple inputs in a single request, pass an array of strings.
@ -1163,9 +1157,7 @@ class InferenceProvider(Protocol):
class Inference(InferenceProvider):
"""Inference
Llama Stack Inference API for generating completions, chat completions, and embeddings.
"""Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
@ -1181,7 +1173,7 @@ class Inference(InferenceProvider):
model: str | None = None,
order: Order | None = Order.desc,
) -> ListOpenAIChatCompletionResponse:
"""List chat completions.
"""List all chat completions.
:param after: The ID of the last chat completion to return.
:param limit: The maximum number of chat completions to return.
@ -1196,9 +1188,7 @@ class Inference(InferenceProvider):
)
@webmethod(route="/chat/completions/{completion_id}", method="GET", level=LLAMA_STACK_API_V1)
async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
"""Get chat completion.
Describe a chat completion by its ID.
"""Describe a chat completion by its ID.
:param completion_id: ID of the chat completion.
:returns: A OpenAICompletionWithInputMessages.