Change reduce prompt, limit communities to 3

rag.py

@@ -227,37 +227,9 @@ def global_retriever(query: str, level: int, response_type: str):
 
     {report_data}
 
-
-    ---Goal---
-
-    Generate a response of the target length and format that responds to the user's question, summarize all the reports from multiple analysts who focused on different parts of the dataset.
-
-    Note that the analysts' reports provided below are ranked in the **descending order of importance**.
-
-    If you don't know the answer or if the provided reports do not contain sufficient information to provide an answer, just say so. Do not make anything up.
-
-    The final response should remove all irrelevant information from the analysts' reports and merge the cleaned information into a comprehensive answer that provides explanations of all the key points and implications appropriate for the response length and format.
-
-    The response shall preserve the original meaning and use of modal verbs such as "shall", "may" or "will".
-
-    The response should also preserve all the data references previously included in the analysts' reports, but do not mention the roles of multiple analysts in the analysis process.
-
-    **Do not list more than 5 record ids in a single reference**. Instead, list the top 5 most relevant record ids and add "+more" to indicate that there are more.
-
-    For example:
-
-    "Person X is the owner of Company Y and subject to many allegations of wrongdoing [Data: Reports (2, 7, 34, 46, 64, +more)]. He is also CEO of company X [Data: Reports (1, 3)]"
-
-    where 1, 2, 3, 7, 34, 46, and 64 represent the id (not the index) of the relevant data record.
-
-    Do not include information where the supporting evidence for it is not provided.
-
-
-    ---Target response length and format---
-
-    {response_type}
-
     Add sections and commentary to the response as appropriate for the length and format. Style the response in markdown.
+
+    ---Real Data---
     """
 
     reduce_prompt = ChatPromptTemplate.from_messages(
@@ -293,7 +265,7 @@ def global_retriever(query: str, level: int, response_type: str):
     # print(community_data)
     intermediate_results = []
     i = 0
-    for community in tqdm(community_data[:10], desc="Processing communities"):
+    for community in tqdm(community_data[:3], desc="Processing communities"):
         intermediate_response = map_chain.invoke(
             {"question": query, "context_data": community["output"]}
         )