llama-stack/llama_stack/apis/models/models.py
Ben Browning 2b2db5fbda
feat: OpenAI-Compatible models, completions, chat/completions (#1894)
# What does this PR do?

This stubs in some OpenAI server-side compatibility with three new
endpoints:

/v1/openai/v1/models
/v1/openai/v1/completions
/v1/openai/v1/chat/completions

This gives common inference apps using OpenAI clients the ability to
talk to Llama Stack using an endpoint like
http://localhost:8321/v1/openai/v1 .

The two "v1" instances in there isn't awesome, but the thinking is that
Llama Stack's API is v1 and then our OpenAI compatibility layer is
compatible with OpenAI V1. And, some OpenAI clients implicitly assume
the URL ends with "v1", so this gives maximum compatibility.

The openai models endpoint is implemented in the routing layer, and just
returns all the models Llama Stack knows about.

The following providers should be working with the new OpenAI
completions and chat/completions API:
* remote::anthropic (untested)
* remote::cerebras-openai-compat (untested)
* remote::fireworks (tested)
* remote::fireworks-openai-compat (untested)
* remote::gemini (untested)
* remote::groq-openai-compat (untested)
* remote::nvidia (tested)
* remote::ollama (tested)
* remote::openai (untested)
* remote::passthrough (untested)
* remote::sambanova-openai-compat (untested)
* remote::together (tested)
* remote::together-openai-compat (untested)
* remote::vllm (tested)

The goal to support this for every inference provider - proxying
directly to the provider's OpenAI endpoint for OpenAI-compatible
providers. For providers that don't have an OpenAI-compatible API, we'll
add a mixin to translate incoming OpenAI requests to Llama Stack
inference requests and translate the Llama Stack inference responses to
OpenAI responses.

This is related to #1817 but is a bit larger in scope than just chat
completions, as I have real use-cases that need the older completions
API as well.

## Test Plan

### vLLM

```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" llama stack build --template remote-vllm --image-type venv --run

LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "meta-llama/Llama-3.2-3B-Instruct"
```

### ollama
```
INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" llama stack build --template ollama --image-type venv --run

LLAMA_STACK_CONFIG=http://localhost:8321 INFERENCE_MODEL="llama3.2:3b-instruct-q8_0" python -m pytest -v tests/integration/inference/test_openai_completion.py --text-model "llama3.2:3b-instruct-q8_0"
```



## Documentation

Run a Llama Stack distribution that uses one of the providers mentioned
in the list above. Then, use your favorite OpenAI client to send
completion or chat completion requests with the base_url set to
http://localhost:8321/v1/openai/v1 . Replace "localhost:8321" with the
host and port of your Llama Stack server, if different.

---------

Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-04-11 13:14:17 -07:00

108 lines
2.8 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from enum import Enum
from typing import Any, Dict, List, Literal, Optional, Protocol, runtime_checkable
from pydantic import BaseModel, ConfigDict, Field
from llama_stack.apis.resource import Resource, ResourceType
from llama_stack.providers.utils.telemetry.trace_protocol import trace_protocol
from llama_stack.schema_utils import json_schema_type, webmethod
class CommonModelFields(BaseModel):
metadata: Dict[str, Any] = Field(
default_factory=dict,
description="Any additional metadata for this model",
)
@json_schema_type
class ModelType(str, Enum):
llm = "llm"
embedding = "embedding"
@json_schema_type
class Model(CommonModelFields, Resource):
type: Literal[ResourceType.model.value] = ResourceType.model.value
@property
def model_id(self) -> str:
return self.identifier
@property
def provider_model_id(self) -> str:
return self.provider_resource_id
model_config = ConfigDict(protected_namespaces=())
model_type: ModelType = Field(default=ModelType.llm)
class ModelInput(CommonModelFields):
model_id: str
provider_id: Optional[str] = None
provider_model_id: Optional[str] = None
model_type: Optional[ModelType] = ModelType.llm
model_config = ConfigDict(protected_namespaces=())
class ListModelsResponse(BaseModel):
data: List[Model]
@json_schema_type
class OpenAIModel(BaseModel):
"""A model from OpenAI.
:id: The ID of the model
:object: The object type, which will be "model"
:created: The Unix timestamp in seconds when the model was created
:owned_by: The owner of the model
"""
id: str
object: Literal["model"] = "model"
created: int
owned_by: str
class OpenAIListModelsResponse(BaseModel):
data: List[OpenAIModel]
@runtime_checkable
@trace_protocol
class Models(Protocol):
@webmethod(route="/models", method="GET")
async def list_models(self) -> ListModelsResponse: ...
@webmethod(route="/openai/v1/models", method="GET")
async def openai_list_models(self) -> OpenAIListModelsResponse: ...
@webmethod(route="/models/{model_id:path}", method="GET")
async def get_model(
self,
model_id: str,
) -> Model: ...
@webmethod(route="/models", method="POST")
async def register_model(
self,
model_id: str,
provider_model_id: Optional[str] = None,
provider_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
model_type: Optional[ModelType] = None,
) -> Model: ...
@webmethod(route="/models/{model_id:path}", method="DELETE")
async def unregister_model(
self,
model_id: str,
) -> None: ...