Update app.py

app.py

@@ -23,9 +23,16 @@ model_name = "gpt-3.5-turbo"
 # Define the template
 template = PromptTemplate(
     prompt="""
-Answer the given question using the provided documents. The answer should be in the style of an academic report and should provide example quotes and references. Always start the response by stating the name of the country relevant to the documents. When relevant, use bullet points and lists to structure your answers. When relevant, use facts and numbers from the following documents in your answer. Whenever you use information from a document, reference it at the end of the sentence (ex: [doc 2]). You don't have to use all documents, only if it makes sense in the conversation. If no relevant information to answer the question is present in the documents, just say you don't have enough information to answer.
-
-Context: {join(documents)}\n\nQuestion: {query}\n\nAnswer:""",
+Answer the given question using the following documents \
+Formulate your answer in the style of an academic report \
+Provide example quotes and citations using extracted text from the documents. \
+Use facts and numbers from the documents in your answer. \
+Reference information used from documents at the end of each applicable sentence (ex: [source: document_name]), where 'document_name' is the text provided at the start of each document (demarcated by '- &&&' and '&&&:')'. \
+If no relevant information to answer the question is present in the documents, just say you don't have enough information to answer. \
+Format your response as a JSON object with "answer" and "sources" as the keys. \
+The "answer" key is the response to the query and "sources" key is the reference information used from the documents. \
+
+Context: {' - '.join(['&&& '+d.meta['document_name']+' ref. '+str(d.meta['ref_id'])+' &&&: '+d.content for d in documents])}; Question: {query}; Answer:""",
 )
 
 # Create a list of options for the dropdown
@@ -44,21 +51,30 @@ def get_docs(input_query, country = None):
         query = "For the country of "+country+", "+input_query
     else:
         query = input_query
-    # Get top 150 because we want to make sure we have 10 pertaining to the selected country 
+    # Get top 150 because we want to make sure we have 10 pertaining to the selected country
     # TEMP SOLUTION: not ideal, but FAISS document store doesnt allow metadata filtering. Needs to be tested with the full dataset
     docs = retriever.retrieve(query=query,top_k = 150)
-    # Break out the key fields and convert to pandas for filtering 
+    # Break out the key fields and convert to pandas for filtering
     docs = [{**x.meta,"score":x.score,"content":x.content} for x in docs]
     df_docs = pd.DataFrame(docs)
     if country:
       df_docs = df_docs.query('country in @country')
     # Take the top 10
     df_docs = df_docs.head(10)
+    df_docs = df_docs.reset_index()
+    df_docs['ref_id'] = df_docs.index + 1
     # Convert back to Document format
     ls_dict = []
-    for doc, _ in df_docs.iterrows():
-       x = Document(df_docs['content'][doc])
-       ls_dict.append(x)
+    # Iterate over df and add relevant fields to the dict object
+    for index, row in df_docs.iterrows():
+        # Create a Document object for each row
+        doc = Document(
+            row['content'],
+            meta={'country': row['country'],'document_name': row['document'], 'ref_id': row['ref_id'], 'score': row['score']}
+        )
+        
+        # Append the Document object to the documents list
+        ls_dict.append(doc)
     return(ls_dict)
 
 def run_query(input_text):