Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: openai.Model.list() #499

Merged
merged 9 commits into from
Oct 14, 2023
Merged

feat: openai.Model.list() #499

Changes from 4 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
3826d5c
Model list endpoint with asgi app
XunchaoZ Oct 14, 2023
8b0608a
Merge branch 'main' into features/openaimodellist
XunchaoZ Oct 14, 2023
4861331
ci: auto fixes from pre-commit.ci
pre-commit-ci[bot] Oct 14, 2023
fd6c65e
Merge branch 'main' into features/openaimodellist
aarnphm Oct 14, 2023
967be2f
chore: use plain starlette app
aarnphm Oct 14, 2023
89f55fd
chore: update schemas
aarnphm Oct 14, 2023
4e8d98c
chore: update examples openai client
aarnphm Oct 14, 2023
9c05eb7
chore: only warn instead of error out
aarnphm Oct 14, 2023
aec0e1c
chore: put model list before
aarnphm Oct 14, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions openllm-python/src/openllm/_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
import _service_vars as svars
import orjson

from fastapi import FastAPI
aarnphm marked this conversation as resolved.
Show resolved Hide resolved
from starlette.applications import Starlette
from starlette.responses import JSONResponse
from starlette.routing import Route
Expand Down Expand Up @@ -62,6 +63,7 @@ async def generate_stream_v1(input_dict: dict[str, t.Any]) -> t.AsyncGenerator[s
input=bentoml.io.JSON.from_sample(openllm.utils.bentoml_cattr.unstructure(openllm.openai.CompletionRequest(prompt='What is 1+1?', model=runner.llm_type))),
output=bentoml.io.Text())
async def completion_v1(input_dict: dict[str, t.Any], ctx: bentoml.Context) -> str | t.AsyncGenerator[str, None]:
if input_dict.get('model', None) is not model: raise ValueError(f"Model '{input_dict['model']}' is not supported. Run openai.Model.list() to see all supported models.")
prompt = input_dict.pop('prompt', None)
if prompt is None: raise ValueError("'prompt' should not be None.")
stream = input_dict.pop('stream', False)
Expand Down Expand Up @@ -118,6 +120,7 @@ async def stream_response_generator(responses: t.AsyncGenerator[str, None]) -> t
}], model=runner.llm_type))),
output=bentoml.io.Text())
async def chat_completion_v1(input_dict: dict[str, t.Any], ctx: bentoml.Context) -> str | t.AsyncGenerator[str, None]:
if input_dict.get('model', None) is not model: raise ValueError(f"Model '{input_dict['model']}' is not supported. Run openai.Model.list() to see all supported models.")
prompt = openllm.openai.messages_to_prompt(input_dict['messages'])
stream = input_dict.pop('stream', False)
config = {
Expand Down Expand Up @@ -164,6 +167,12 @@ async def stream_response_generator(responses: t.AsyncGenerator[str, None]) -> t
model=model) # TODO: logprobs, finish_reason and usage
)).decode('utf-8')

fastapi_app = FastAPI()
@fastapi_app.get('/v1/models')
def models_v1() -> t.List[dict[str, t.Any]]:
return [{'data': {'model': model, 'id': model_id}}]
svc.mount_asgi_app(fastapi_app)

@svc.api(route='/v1/metadata',
input=bentoml.io.Text(),
output=bentoml.io.JSON.from_sample({
Expand Down
Loading