mirror of
https://github.com/nomic-ai/gpt4all.git
synced 2024-10-01 01:06:10 -04:00
8aba2c9009
* feat: local inference server * fix: source to use bash + vars * chore: isort and black * fix: make file + inference mode * chore: logging * refactor: remove old links * fix: add new env vars * feat: hf inference server * refactor: remove old links * test: batch and single response * chore: black + isort * separate gpu and cpu dockerfiles * moved gpu to separate dockerfile * Fixed test endpoints * Edits to API. server won't start due to failed instantiation error * Method signature * fix: gpu_infer * tests: fix tests --------- Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
import logging
|
|
from typing import Dict, List
|
|
|
|
from api_v1.settings import settings
|
|
from fastapi import APIRouter, Depends, Response, Security, status
|
|
from pydantic import BaseModel, Field
|
|
|
|
logger = logging.getLogger(__name__)
|
|
logger.setLevel(logging.DEBUG)
|
|
|
|
### This should follow https://github.com/openai/openai-openapi/blob/master/openapi.yaml
|
|
|
|
|
|
class ListEnginesResponse(BaseModel):
|
|
data: List[Dict] = Field(..., description="All available models.")
|
|
|
|
|
|
class EngineResponse(BaseModel):
|
|
data: List[Dict] = Field(..., description="All available models.")
|
|
|
|
|
|
router = APIRouter(prefix="/engines", tags=["Search Endpoints"])
|
|
|
|
|
|
@router.get("/", response_model=ListEnginesResponse)
|
|
async def list_engines():
|
|
'''
|
|
List all available GPT4All models from
|
|
https://raw.githubusercontent.com/nomic-ai/gpt4all/main/gpt4all-chat/metadata/models.json
|
|
'''
|
|
raise NotImplementedError()
|
|
return ListEnginesResponse(data=[])
|
|
|
|
|
|
@router.get("/{engine_id}", response_model=EngineResponse)
|
|
async def retrieve_engine(engine_id: str):
|
|
''' '''
|
|
|
|
raise NotImplementedError()
|
|
return EngineResponse()
|