Update processing.py

processing.py

@@ -4,8 +4,9 @@ from langchain_openai import OpenAIEmbeddings
 from langchain_community.vectorstores import FAISS
 from llm_loader import load_model
 from config import openai_api_key
-from langchain.chains import RetrievalQA
+from langchain.chains import RetrievalQA, LLMChain
 from langchain.retrievers import MultiQueryRetriever
+from langchain.prompts import PromptTemplate
 import os
 import json
 
@@ -41,14 +42,27 @@ text_retriever = text_faiss_index.as_retriever()
 attachments_retriever = attachments_faiss_index.as_retriever()
 personalities_retriever = personalities_faiss_index.as_retriever()
 
-# Combine retrievers
-combined_retriever = MultiQueryRetriever(
-    retrievers=[text_retriever, attachments_retriever, personalities_retriever],
-    llm=llm
+# Create a combined retriever
+combined_retriever = text_retriever.add_retrievers([attachments_retriever, personalities_retriever])
+
+# Create prompt template for query generation
+prompt_template = PromptTemplate(
+    input_variables=["question"],
+    template="Generate multiple search queries for the following question: {question}"
+)
+
+# Create LLM chain for query generation
+llm_chain = LLMChain(llm=llm, prompt=prompt_template)
+
+# Initialize MultiQueryRetriever
+multi_query_retriever = MultiQueryRetriever(
+    retriever=combined_retriever,
+    llm_chain=llm_chain,
+    parser_key="lines"  # Assuming the LLM outputs queries line by line
 )
 
-# Create QA chain with combined retriever
-qa_chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=combined_retriever)
+# Create QA chain with multi-query retriever
+qa_chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=multi_query_retriever)
 
 def load_text(file_path: str) -> str:
     with open(file_path, 'r', encoding='utf-8') as file: