Update QnA.py

QnA.py

@@ -3,6 +3,8 @@ from langchain_core.prompts import ChatPromptTemplate
 from langchain.chains import create_retrieval_chain
 from langchain.chains.summarize.chain import load_summarize_chain
 from langchain_community.llms.huggingface_hub import HuggingFaceHub
+from langchain.retrievers.document_compressors import LLMChainExtractor
+from langchain.retrievers import ContextualCompressionRetriever
 
 #from Api_Key import google_plam
 from langchain_groq import ChatGroq
@@ -55,7 +57,7 @@ def summarize(documents,llm):
     return results['output_text']
 
 
-def get_hugging_face_model(model_id='mistralai/Mixtral-8x7B-Instruct-v0.1',temperature=0.01,max_tokens=2048,api_key=None):
+def get_hugging_face_model(model_id='mistralai/Mixtral-8x7B-Instruct-v0.1',temperature=0.01,max_tokens=4096,api_key=None):
     llm = HuggingFaceHub(
         huggingfacehub_api_token =api_key ,
         repo_id=model_id, 
@@ -72,6 +74,10 @@ def Q_A(vectorstore,question,API_KEY):
     
     # Create a retriever
     retriever = vectorstore.as_retriever(search_type = 'similarity',search_kwargs = {'k':2},)
+    #Create a contextual compressor
+    compressor = LLMChainExtractor.from_llm(chat_llm)
+    compression_retriever = ContextualCompressionRetriever(base_compressor=compressor,base_retriever=retriever)
+    
     if  'reliable' in question.lower() or 'relaibility' in question.lower():
         question_answer_chain = create_stuff_documents_chain(chat_llm, prompt_template_for_relaibility())