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/chat.py

@@ -1,9 +1,10 @@
-from fastapi import APIRouter, Depends, Response, Security, status
-from pydantic import BaseModel, Field
-from typing import List, Dict
 import logging
 import time
+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)
@@ -11,11 +12,11 @@ logger.setLevel(logging.DEBUG)
 ### This should follow https://github.com/openai/openai-openapi/blob/master/openapi.yaml
 
 
-
 class ChatCompletionMessage(BaseModel):
     role: str
     content: str
 
+
 class ChatCompletionRequest(BaseModel):
     model: str = Field(..., description='The model to generate a completion from.')
     messages: List[ChatCompletionMessage] = Field(..., description='The model to generate a completion from.')
@@ -26,11 +27,13 @@ class ChatCompletionChoice(BaseModel):
     index: int
     finish_reason: str
 
+
 class ChatCompletionUsage(BaseModel):
     prompt_tokens: int
     completion_tokens: int
     total_tokens: int
 
+
 class ChatCompletionResponse(BaseModel):
     id: str
     object: str = 'text_completion'
@@ -42,6 +45,7 @@ class ChatCompletionResponse(BaseModel):
 
 router = APIRouter(prefix="/chat", tags=["Completions Endpoints"])
 
+
 @router.post("/completions", response_model=ChatCompletionResponse)
 async def chat_completion(request: ChatCompletionRequest):
     '''
@@ -53,11 +57,5 @@ async def chat_completion(request: ChatCompletionRequest):
         created=time.time(),
         model=request.model,
         choices=[{}],
-        usage={
-            'prompt_tokens': 0,
-            'completion_tokens': 0,
-            'total_tokens': 0
-        }
+        usage={'prompt_tokens': 0, 'completion_tokens': 0, 'total_tokens': 0},
     )
-
-