GPU Inference Server (#1112)

* 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>

gpt4all-api/gpt4all_api/app/api_v1/routes/engines.py

@@ -1,22 +1,27 @@
+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
-from typing import List, Dict
-import logging
-from api_v1.settings import settings
 
 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():
     '''
@@ -29,10 +34,7 @@ async def list_engines():
 
 @router.get("/{engine_id}", response_model=EngineResponse)
 async def retrieve_engine(engine_id: str):
-    '''
-
-    '''
+    ''' '''
 
     raise NotImplementedError()
     return EngineResponse()
-