Update handler.py

handler.py

@@ -59,7 +59,7 @@ class EndpointHandler():
         vectorstore = Chroma.from_documents(documents=all_splits, embedding=embedding_function)
         retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
         
-        compressor = LLMChainExtractor.from_llm(self.llm)
+        compressor = LLMChainExtractor.from_llm(chat)
         retriever = ContextualCompressionRetriever(base_compressor=compressor, base_retriever=retriever)
 
         _template = """Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.