update article query service prompt

controllers/article_query_service.py

@@ -13,6 +13,7 @@ load_dotenv()
 PINECONE_API_KEY = os.getenv('PINECONE_API_KEY')
 OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
 
+
 def article_agent(query, filter_params=None):
     # Initialize Pinecone
     try:
@@ -37,7 +38,8 @@ def article_agent(query, filter_params=None):
 
     # Validate and setup retriever with dynamic filtering based on IDs provided in filter_params
     try:
-        if filter_params and isinstance(filter_params, list) and all(isinstance(id, str) for id in filter_params):
+        if filter_params and isinstance(filter_params, list) and all(
+                isinstance(id, str) for id in filter_params):
             search_filter = {"id": {"$in": filter_params}}
         else:
             if filter_params is not None:
@@ -45,7 +47,8 @@ def article_agent(query, filter_params=None):
                 return None
             search_filter = {}
 
-        retriever = vectorstore.as_retriever(search_kwargs={'filter': search_filter})
+        retriever = vectorstore.as_retriever(
+            search_kwargs={'filter': search_filter})
         print('Retriever Initialized')
     except Exception as e:
         print(f"Error configuring the retriever: {e}")
@@ -63,29 +66,29 @@ def article_agent(query, filter_params=None):
     try:
         prompt_template = """
         Assistant:
-        You are an AI trained to assist users by analyzing financial documents.
-        Your task is to extract pertinent information from these documents and answer 
-        queries based on them. 
-        Your responses should not only answer the query but also highlight key details 
-        and provide analytical depth where relevant. 
-        Make sure all responses are grammatically correct, well-structured, and 
-        formatted to meet professional standards.
+        You are an AI trained to assist users by analyzing financial documents. 
+        Your task is to extract pertinent information from these documents and answer queries based on them
+        Your responses should not only answer the query but also highlight key details and provide analytical depth where relevant.
+        Make sure all responses are grammatically correct, well-structured, and formatted to meet professional standards.
 
         Query: {query}
 
         Context:
-        Here are the key points from the financial documents provided:
+        These are the finanicial documents that are relevant to the query:
         {context}
 
-        Please synthesize this information and answer the query comprehensively, providing actionable           insights and detailed explanations where necessary.
+        Please synthesize this information and answer the query comprehensively, providing actionable insights and detailed explanations where necessary.
 
         Response:
         """
-        prompt = PromptTemplate(input_variables=['context', 'query'], template=prompt_template)
-        rag_chain = ({"context": retriever, "query": RunnablePassthrough()} | prompt | llm |                    StrOutputParser())
+        prompt = PromptTemplate(input_variables=['context', 'query'],
+                                template=prompt_template)
+        rag_chain = ({
+            "context": retriever,
+            "query": RunnablePassthrough()
+        } | prompt | llm | StrOutputParser())
 
         return rag_chain.invoke(query)
     except Exception as e:
         print(f"Error during RAG chain setup or execution: {e}")
         return None
-