feat: add backend

main.py

@@ -2,8 +2,6 @@ import os
 import glob
 import shutil
 import subprocess
-import contextvars
-import asyncio
 
 from typing import Any, Dict, List
 
@@ -17,7 +15,7 @@ from langchain.chains import RetrievalQA
 from langchain.embeddings import HuggingFaceInstructEmbeddings
 from langchain.prompts import PromptTemplate
 from langchain.memory import ConversationBufferMemory
-from langchain.callbacks.base import BaseCallbackHandler, AsyncCallbackHandler
+from langchain.callbacks.base import BaseCallbackHandler
 from langchain.schema import LLMResult
 
 # from langchain.embeddings import HuggingFaceEmbeddings
@@ -34,15 +32,8 @@ class Predict(BaseModel):
 class Delete(BaseModel):
     filename: str
 
-websocket_state = None
-
-class MyCustomSyncHandler(AsyncCallbackHandler):
+class MyCustomSyncHandler(BaseCallbackHandler):
     def on_llm_new_token(self, token: str, **kwargs) -> None:
-        print(f"{websocket_state}")
-
-        asyncio.sleep(1.5)
-        websocket_state.send_text(f"token: {token}")
-
         print(f"token: {token}")
 
 # if torch.backends.mps.is_available():
@@ -76,13 +67,13 @@ Always answer in the most helpful and safe way possible.
 If you don't know the answer to a question, just say that you don't know, don't try to make up an answer, don't share false information.
 Use 15 sentences maximum. Keep the answer as concise as possible.
 Always say "thanks for asking!" at the end of the answer.
-Context: {history} \n {context}
+Context: {context}
 Question: {question}
 """
 
 memory = ConversationBufferMemory(input_key="question", memory_key="history")
 
-QA_CHAIN_PROMPT = PromptTemplate(input_variables=["history", "context", "question"], template=template)
+QA_CHAIN_PROMPT = PromptTemplate(input_variables=["context", "question"], template=template)
 
 QA = RetrievalQA.from_chain_type(
     llm=LLM,
@@ -91,7 +82,6 @@ QA = RetrievalQA.from_chain_type(
     return_source_documents=SHOW_SOURCES,
     chain_type_kwargs={
         "prompt": QA_CHAIN_PROMPT,
-        "memory": memory
     },
 )