Update app.py

app.py

@@ -1,5 +1,6 @@
 import chainlit as cl
 import arxiv
+from typing import List  # <— add this
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import ConversationalRetrievalChain
 from langchain.memory import ConversationBufferMemory
@@ -17,22 +18,46 @@ class ArxivResearchAssistant:
         self.papers: List[arxiv.Result] = []
         self.state = "SEARCH"
 
+        # NEW: modern client that uses HTTPS + retry/backoff
+        self.client = arxiv.Client(
+            page_size=50,
+            delay_seconds=3,
+            num_retries=3,
+            user_agent="chainlit-arxiv-app/1.0 (mailto:your-email@example.com)"
+        )
+
     async def search_papers(self, query: str):
+        query = (query or "").strip()
+        if not query:
+            await cl.Message(content="Please enter a non-empty search query.").send()
+            return None
+
         search = arxiv.Search(
             query=query,
             max_results=5,
             sort_by=arxiv.SortCriterion.Relevance
         )
 
-        self.papers = list(search.results())
-        
+        # CHANGED: use the client to fetch results (handles HTTPS correctly)
+        self.papers = list(self.client.results(search))
+
         if not self.papers:
             await cl.Message(content="No papers found. Please try another search query.").send()
             return None
 
-        paper_list = "\n".join([f"{i+1}. {paper.title} - {paper.authors[0]}\nLink: {paper.entry_id}" for i, paper in enumerate(self.papers)])
-        
-        await cl.Message(content=f"Please select a paper by entering its number:\n\n{paper_list}\n\nEnter the number of the paper you want to select:").send()
+        paper_list = "\n".join(
+            [
+                f"{i+1}. {paper.title} - {paper.authors[0]}\nLink: {paper.entry_id}"
+                for i, paper in enumerate(self.papers)
+            ]
+        )
+
+        await cl.Message(
+            content=(
+                f"Please select a paper by entering its number:\n\n{paper_list}\n\n"
+                "Enter the number of the paper you want to select:"
+            )
+        ).send()
         self.state = "SELECT"
         return self.papers
 
@@ -48,32 +73,30 @@ class ArxivResearchAssistant:
             await cl.Message(content="Invalid input. Please enter a number.").send()
             return None
 
-        # Download the entire paper content (if available)
         paper_text = f"{self.selected_paper.title}\n\n{self.selected_paper.summary}\n\n{self.selected_paper.comment or ''}"
 
-        # Split the text into chunks
         text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
         chunks = text_splitter.split_text(paper_text)
 
-        # Create embeddings and vector store, include chunk-specific metadata
         embeddings = OpenAIEmbeddings()
         vectorstore = FAISS.from_texts(
             chunks,
             embeddings,
-            metadatas=[{
-                "title": self.selected_paper.title,
-                "link": self.selected_paper.entry_id,
-                "chunk": f"Chunk {i+1}/{len(chunks)}"
-            } for i in range(len(chunks))]
+            metadatas=[
+                {
+                    "title": self.selected_paper.title,
+                    "link": self.selected_paper.entry_id,
+                    "chunk": f"Chunk {i+1}/{len(chunks)}"
+                } for i in range(len(chunks))
+            ]
         )
 
-        # Create the conversational chain
         memory = ConversationBufferMemory(
-            memory_key="chat_history", 
-            return_messages=True, 
+            memory_key="chat_history",
+            return_messages=True,
             output_key="answer"
         )
-        
+
         self.qa_chain = ConversationalRetrievalChain.from_llm(
             ChatOpenAI(temperature=0, model="gpt-4o-mini"),
             vectorstore.as_retriever(),
@@ -81,7 +104,13 @@ class ArxivResearchAssistant:
             return_source_documents=True
         )
 
-        await cl.Message(content=f"Selected paper: {self.selected_paper.title}\nLink: {self.selected_paper.entry_id}\nYou can now ask questions about this paper. Type 'new search' when you want to search for a different paper.").send()
+        await cl.Message(
+            content=(
+                f"Selected paper: {self.selected_paper.title}\n"
+                f"Link: {self.selected_paper.entry_id}\n"
+                "You can now ask questions about this paper. Type 'new search' when you want to search for a different paper."
+            )
+        ).send()
         self.state = "QA"
         return self.selected_paper
 
@@ -94,8 +123,14 @@ class ArxivResearchAssistant:
         response = self.qa_chain({"question": message})
         answer = response["answer"]
 
-        # Handling the sources with chunk-specific metadata
-        sources = "\n".join([f"- {doc.metadata.get('title', 'Unknown title')} ({doc.metadata.get('link', 'No link')}) - {doc.metadata.get('chunk', 'No chunk info')}" for doc in response.get("source_documents", [])])
+        sources = "\n".join(
+            [
+                f"- {doc.metadata.get('title', 'Unknown title')} "
+                f"({doc.metadata.get('link', 'No link')}) - "
+                f"{doc.metadata.get('chunk', 'No chunk info')}"
+                for doc in response.get("source_documents", [])
+            ]
+        )
         if sources:
             answer += f"\n\nSources:\n{sources}"
 
@@ -107,32 +142,27 @@ class ArxivResearchAssistant:
         self.papers = []
         self.state = "SEARCH"
 
-# Global assistant instance
 assistant = ArxivResearchAssistant()
 
 @cl.on_chat_start
 async def start():
-    await cl.Message(content=( 
-        "Welcome! This tool helps you search for papers on arXiv, pick one, and ask questions about its content. \n\n"
-        "Please enter a topic to search for on arXiv papers.\n\n"
-        #"balance sheets, and cash flow reports. It generates summaries and strategic due diligence.\n\n"
-        #"Please enter the ticker symbol for the company you want to analyze:"
-    )
+    await cl.Message(
+        content=(
+            "Welcome! This tool helps you search for papers on arXiv, pick one, and ask questions about its content.\n\n"
+            "Please enter a topic to search for on arXiv papers.\n\n"
+        )
     ).send()
 
 @cl.on_message
 async def main(message: cl.Message):
-    # Route the message based on the current state
     if assistant.state == "SEARCH":
         await assistant.search_papers(message.content)
-    
     elif assistant.state == "SELECT":
         await assistant.select_paper(message.content)
-    
     elif assistant.state == "QA":
         answer = await assistant.process_question(message.content)
         if answer:
             await cl.Message(content=answer).send()
 
 if __name__ == "__main__":
-    cl.run()
+    cl.run()