api first commit by me :)

rag.py

@@ -98,7 +98,7 @@ def generate_response_via_langchain(query: str, stream: bool = False, model: str
         return llm_chain.astream({ "query": query, "context": context, "messages": messages})
     
     # Invoke the LLM chain and return the result
-    return llm_chain.invoke({"query": query})
+    return llm_chain.invoke({ "query": query, "context": context, "messages": messages})