UPDATE: chat history retention

functions.py

@@ -196,21 +196,24 @@ def answerQuery(query: str, vectorstore: str, llmModel: str = "llama3-70b-8192")
     retriever = ContextualCompressionRetriever(
         base_compressor=compressor, base_retriever=retriever
     )
-    chain = (
+    baseChain = (
         {"context": retriever | RunnableLambda(format_docs), "question": RunnablePassthrough(), "chatHistory": RunnablePassthrough()}
         | prompt
         | ChatGroq(model = llmModel, temperature = 0.75, max_tokens = 512)
         | StrOutputParser()
         )
-    chain = RunnableWithMessageHistory(
-        chain,
+    messageChain = RunnableWithMessageHistory(
+        baseChain,
         get_session_history,
         input_messages_key = "question",
         history_messages_key = "chatHistory"
     )
-    chain = RunnablePassthrough.assign(messages_trimmed = trimMessages) | chain
+    chain = RunnablePassthrough.assign(messages_trimmed = trimMessages) | messageChain
     return {
-        "output": chain.invoke(query)
+        "output": chain.invoke(
+            {"question": query},
+            {"configurable": {"session_id": vectorstore}}
+        )
     }