phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 03:13:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Use our own pydantic models for OpenAI Server APIs

Browse source 
Importing the models from the OpenAI client library required a
top-level dependency on the openai python package, and also was
incompatible with our API generation code due to some quirks in how
the OpenAI pydantic models are defined.

So, this creates our own stubs of those pydantic models so that we're
in more direct control of our API surface for this OpenAI-compatible
API, so that it works with our code generation, and so that the openai
python client isn't a hard requirement of Llama Stack's API.
This commit is contained in:
Ben Browning 2025-04-08 09:01:35 -04:00
parent a193c9fc3f
commit 92fdf6d0c9
8 changed files with 1826 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -10,7 +10,6 @@ from typing import Any, AsyncGenerator, Dict, List, Optional, Union
import httpx
from openai import AsyncOpenAI
from openai.types.chat import ChatCompletion as OpenAIChatCompletion
from openai.types.chat import ChatCompletionMessageParam as OpenAIChatCompletionMessageParam
from openai.types.chat.chat_completion_chunk import (
ChatCompletionChunk as OpenAIChatCompletionChunk,
)
@ -48,6 +47,7 @@ from llama_stack.apis.inference import (
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.inference.inference import OpenAIMessageParam
from llama_stack.apis.models import Model, ModelType
from llama_stack.models.llama.datatypes import BuiltinTool, StopReason, ToolCall
from llama_stack.models.llama.sku_list import all_registered_models
@ -471,7 +471,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
async def openai_chat_completion(
self,
model: str,
messages: List[OpenAIChatCompletionMessageParam],
messages: List[OpenAIMessageParam],
frequency_penalty: Optional[float] = None,
function_call: Optional[Union[str, Dict[str, Any]]] = None,
functions: Optional[List[Dict[str, Any]]] = None,