added sources

app.py

@@ -100,16 +100,24 @@ async def main(message):
     # Send the response back to the user
     # await msg.send()
 
-    # context_documents = response["context"]
+    context_documents = response["context"]
     # num_contexts = len(context_documents)
     # context_msg = f"Number of found context: {num_contexts}"
 
 
     # await cl.Message(content=context_msg).send()
-
-    # for doc in context_documents:
-    #     document_title = doc.metadata.get("source", "Unknown Document") 
-    #     chunk_number = doc.metadata.get("chunk_number", "Unknown Chunk")  
+    chunk_str = "Sources: "
+    for doc in context_documents:
+        document_title = doc.metadata.get("source", "Unknown Document") 
+        chunk_number = doc.metadata.get("chunk_id", "Unknown Chunk") 
+        chunk_string = chunk_string + " " + chunk_number 
+
+    await cl.Message(
+        content=f"**{document_title} ( Chunk: {chunk_number})**",
+        elements=[
+            cl.Text(content=chunk_string, display="inline")  
+        ]
+    ).send()
 
     #     document_context = doc.page_content.strip() 
     #     truncated_context = document_context[:MAX_PREVIEW_LENGTH] + ("..." if len(document_context) > MAX_PREVIEW_LENGTH else "")

chainlit.md

@@ -6,3 +6,10 @@ AI Mentor has been trained to answer questions on 2 documents:
 *    Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People 
 *    National Institute of Standards and Technology (NIST) Artificial Intelligent Risk Management Framework 
 
+The following technology stack was used:
+*    Chainlit - application
+*    Langchain
+*    Qdrant - vector store
+*    Fine tuned Snowflake embedding model
+*    Ragas - evaluating the models and the chunking strategy
+*    Hugging Face - application and fine tuned model hosting