test: agentic rag

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 import os
 from datasets import load_from_disk, Dataset
 import torch
@@ -8,8 +8,6 @@ import pandas as pd
 import arxiv
 import requests
 import xml.etree.ElementTree as ET
-from agno.embedder.huggingface import HuggingfaceCustomEmbedder
-from agno.vectordb.lancedb import LanceDb, SearchType
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -167,15 +165,26 @@ Answer:"""
 
 # Streamlit App
 st.title("🧩 AMA Autism")
-st.write("This app searches through scientific papers to answer your questions about autism. For best results, be specific in your questions.")
-query = st.text_input("Please ask me anything about autism ✨")
+
+st.write("""
+This app searches through scientific papers to answer your questions about autism.
+For best results, be specific in your questions.
+""")
+
+query = st.text_input("Please ask me anything about autism >")
 
 if query:
     with st.status("Searching for answers...") as status:
         # Search for papers
         df = search_research_papers(query)
+        
         st.write("Searching for data in PubMed and arXiv...")
-        st.write("Data found!")
+        st.write(f"Found {len(df)} relevant papers!")
+        
+        # Display paper sources
+        with st.expander("View source papers"):
+            for _, paper in df.iterrows():
+                st.markdown(f"- [{paper['title']}]({paper['url']}) ({paper['published']})")
         
         # Get relevant context
         context = "\n".join([
@@ -183,21 +192,6 @@ if query:
         ])
         
         # Generate answer
-        answer = generate_answer(query, context)
         st.write("Generating answer...")
-        status.update(
-            label="Search complete!", state="complete", expanded=False
-        )
-    if answer and not answer.isspace():
-        st.success("Answer found!")
-        st.write(answer)
-        
-        st.write("### Sources used:")
-        for _, row in df.head(3).iterrows():
-            st.markdown(f"**[{row['title']}]({row['url']})** ({row['published']})")
-            st.write(f"**Summary:** {row['text'][:200]}...")
-            st.write("---")
-    else:
-        st.warning("I couldn't find a specific answer in the research papers. Try rephrasing your question.")
-    if df.empty:
-        st.warning("I couldn't find any relevant research papers about this topic. Please try rephrasing your question or ask something else about autism.")
+        answer = generate_answer(query, context)
+        st.markdown(answer)

requirements.txt

@@ -7,6 +7,4 @@ accelerate>=0.26.0
 numpy>=1.24.0
 pandas>=2.2.0
 requests>=2.31.0
-arxiv>=2.1.0
-lancedb>=0.3.3
-tantivy>=0.19.2
+arxiv>=2.1.0