Update app.py

app.py

@@ -29,7 +29,7 @@ document_prompt = PromptTemplate(
 )
 prompt = PromptTemplate(
   template=
-  """Write a personalised newsletter for a researcher. The researcher describes his work as follows:"{context}". Base the newsletter on the following articles:\n\n"{text}"\n\nNEWSLETTER:\n#Your AI curated newsletter\n""",
+  """Write a personalised newsletter for a researcher on the most recent exciting developments in his field. The researcher describes his work as follows:"{context}". Base the newsletter on the articles below. Extract the most exciting points and combine them into an excillerating newsletter.\n#ARTICLES\n\n"{text}"\n\nNEWSLETTER:\n# Your AI curated newsletter\n""",
   input_variables=["context", "text"])
 
 # llm = FakeListLLM(responses=list(map(str, range(100))))
@@ -58,6 +58,7 @@ def process_document(doc: Document):
     return Document(page_content=doc.metadata["Summary"], metadata=metadata)
 
 def get_data(user_query: str):
+    print("User query:", user_query)
     docs = loader.load()
     docs = [process_document(doc) for doc in docs]
     db = Chroma.from_documents(docs, embeddings)
@@ -69,7 +70,8 @@ def get_data(user_query: str):
         articles += f"**Title: {doc.metadata['Title']}**\n\nAbstract: {doc.metadata['Summary']}\n\n"
     output = stuff_chain({"input_documents": relevant_docs, "context": user_query})
     output_text = output["output_text"].split("<|end|>")[0]
-    return f"#Your AI curated newsletter\n{output['output_text']}\n\n\n\nUsed articles:\n\n{articles}"
+    print("LLM output:", output_text)
+    return f"# Your AI curated newsletter\n{output['output_text']}\n\n\n\n## Used articles:\n\n{articles}"
 
 demo = gr.Interface(
     fn=get_data,