phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 07:14:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update CLI reference and add typing

Browse source
This commit is contained in:
Celina Hanouti 2024-09-09 17:49:07 +02:00
parent b96e705680
commit eee6c69f46
3 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/cli_reference.md
View file

@ -285,10 +285,10 @@ llama stack list-distributions
| | "agentic_system": "meta-reference", | |
| | "memory": "meta-reference-faiss" | |
| | } | |
+--------------------------------+---------------------------------------+-------------------------------------------------------------------------------------------+
| local-plus-tgi-inference | { | Use TGI (local or with <a href="https://huggingface.co/inference-endpoints/dedicated"> |
| | "inference": "remote::tgi", | Hugging Face Inference Endpoints</a>) for running LLM inference |
| | "safety": "meta-reference", | |
|--------------------------------|---------------------------------------|-------------------------------------------------------------------------------------------|
| local-plus-tgi-inference | { | Use TGI (local or with [Hugging Face Inference Endpoints](https://huggingface.co/ |
| | "inference": "remote::tgi", | inference-endpoints/dedicated)) for running LLM inference. When using HF Inference |
| | "safety": "meta-reference", | Endpoints, please provide hf_namespace (username or organization name) and endpoint name. |
| | "agentic_system": "meta-reference", | |
| | "memory": "meta-reference-faiss" | |
| | } | |

2
llama_toolchain/inference/adapters/tgi/config.py
View file

@ -7,7 +7,7 @@
from typing import Optional
from llama_models.schema_utils import json_schema_type
from pydantic import BaseModel, Field, field_validator
from pydantic import BaseModel, Field
@json_schema_type

2
llama_toolchain/inference/adapters/tgi/tgi.py
View file

@ -41,7 +41,7 @@ class LocalTGIAdapter(Inference):
def client(self) -> InferenceClient:
return InferenceClient(model=self.config.url, token=self.config.api_token)
def _get_endpoint_info(self):
def _get_endpoint_info(self) -> Dict[str, Any]:
return {**self.client.get_endpoint_info(), "inference_url": self.config.url}
async def initialize(self) -> None: