Update app.py

app.py

@@ -59,7 +59,12 @@ development_texts = [
 # ------------------------------
 # Text Splitting & Document Creation
 # ------------------------------
-splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=10)
+splitter = RecursiveCharacterTextSplitter(
+    chunk_size=300,
+    chunk_overlap=30,
+    separators=["\n\n", "\n", ". ", "! ", "? ", " "]
+)
+
 research_docs = splitter.create_documents(research_texts)
 development_docs = splitter.create_documents(development_texts)
 
@@ -85,12 +90,27 @@ development_vectorstore = Chroma.from_documents(
     collection_name="development_collection"
 )
 
-research_retriever = research_vectorstore.as_retriever()
-development_retriever = development_vectorstore.as_retriever()
-
 # ------------------------------
-# Creating Retriever Tools
+# Creating Retriever Tools with MMR
 # ------------------------------
+research_retriever = research_vectorstore.as_retriever(
+    search_type="mmr",
+    search_kwargs={
+        'k': 3,
+        'fetch_k': 10,
+        'lambda_mult': 0.7
+    }
+)
+
+development_retriever = development_vectorstore.as_retriever(
+    search_type="mmr",
+    search_kwargs={
+        'k': 3,
+        'fetch_k': 10,
+        'lambda_mult': 0.7
+    }
+)
+
 research_tool = create_retriever_tool(
     research_retriever,
     "research_db_tool",
@@ -205,10 +225,20 @@ def generate(state: AgentState):
         "Content-Type": "application/json"
     }
     
-    prompt = f"""Based on these research documents, summarize the latest advancements in AI:
+    prompt = f"""Analyze these research documents and provide structured insights:
 Question: {question}
 Documents: {docs}
-Focus on extracting and synthesizing the key findings from the research papers.
+
+Format your response with:
+1. Key Findings section with bullet points
+2. Technical Innovations section
+3. Potential Applications
+4. References to source documents (Doc1, Doc2, etc.)
+
+Focus on:
+- Distilling unique insights
+- Connecting different research aspects
+- Highlighting practical implications
 """
     
     data = {
@@ -343,7 +373,7 @@ def process_question(user_question, app, config):
     return events
 
 # ------------------------------
-# Streamlit App UI (Dark Theme)
+# Streamlit App UI (Enhanced Dark Theme)
 # ------------------------------
 def main():
     st.set_page_config(
@@ -362,44 +392,81 @@ def main():
     .stTextArea textarea {
         background-color: #2d2d2d !important;
         color: #ffffff !important;
+        border: 1px solid #3d3d3d;
     }
     
     .stButton > button {
         background-color: #4CAF50;
         color: white;
+        border: none;
+        padding: 12px 28px;
+        border-radius: 6px;
         transition: all 0.3s;
+        font-weight: 500;
     }
     
     .stButton > button:hover {
         background-color: #45a049;
         transform: scale(1.02);
+        box-shadow: 0 2px 8px rgba(0,0,0,0.2);
     }
     
     .data-box {
+        padding: 18px;
+        margin: 12px 0;
+        border-radius: 8px;
         background-color: #2d2d2d;
-        border-left: 5px solid #2196F3;
+        border-left: 4px solid;
+    }
+    
+    .research-box {
+        border-color: #2196F3;
     }
     
     .dev-box {
-        border-left: 5px solid #4CAF50;
+        border-color: #4CAF50;
     }
     
     .st-expander {
         background-color: #2d2d2d;
         border: 1px solid #3d3d3d;
+        border-radius: 6px;
+        margin: 16px 0;
+    }
+    
+    .st-expander .streamlit-expanderHeader {
+        color: #ffffff !important;
+        font-weight: 500;
+    }
+    
+    .stAlert {
+        background-color: #2d2d2d !important;
+        border: 1px solid #3d3d3d;
+    }
+    
+    h1, h2, h3 {
+        color: #ffffff !important;
+        border-bottom: 2px solid #3d3d3d;
+        padding-bottom: 8px;
+    }
+    
+    .stMarkdown {
+        color: #e0e0e0;
+        line-height: 1.6;
     }
     </style>
     """, unsafe_allow_html=True)
 
     with st.sidebar:
         st.header("📚 Available Data")
+        
         st.subheader("Research Database")
         for text in research_texts:
-            st.markdown(f'<div class="data-box research-box" style="padding: 15px; margin: 10px 0; border-radius: 5px;">{text}</div>', unsafe_allow_html=True)
+            st.markdown(f'<div class="data-box research-box">{text}</div>', unsafe_allow_html=True)
             
         st.subheader("Development Database")
         for text in development_texts:
-            st.markdown(f'<div class="data-box dev-box" style="padding: 15px; margin: 10px 0; border-radius: 5px;">{text}</div>', unsafe_allow_html=True)
+            st.markdown(f'<div class="data-box dev-box">{text}</div>', unsafe_allow_html=True)
 
     st.title("🤖 AI Research & Development Assistant")
     st.markdown("---")
@@ -421,17 +488,36 @@ def main():
                                     if "Error" in content:
                                         st.error(content)
                                     elif "Results:" in content:
-                                        st.markdown("### 📑 Retrieved Documents:")
-                                        docs_start = content.find("Results:")
-                                        docs = content[docs_start:]
-                                        st.info(docs)
+                                        st.markdown("### 📑 Retrieved Documents")
+                                        docs = content.split("Results:")[1].strip()
+                                        
+                                        # Process and deduplicate documents
+                                        unique_docs = list({
+                                            doc.split('page_content=')[1].split(')')[0].strip("'") 
+                                            for doc in docs.split("Document(")[1:]
+                                        })
+                                        
+                                        for i, doc in enumerate(unique_docs, 1):
+                                            st.markdown(f"""
+                                            **Document {i}**  
+                                            {doc}
+                                            """)
                             elif 'generate' in event:
                                 content = event['generate']['messages'][0].content
                                 if "Error" in content:
                                     st.error(content)
                                 else:
-                                    st.markdown("### ✨ Final Answer:")
-                                    st.success(content)
+                                    st.markdown("### ✨ Final Answer")
+                                    st.markdown(f"""
+                                    <div style='
+                                        background-color: #2d2d2d;
+                                        padding: 20px;
+                                        border-radius: 8px;
+                                        margin-top: 16px;
+                                    '>
+                                        {content}
+                                    </div>
+                                    """, unsafe_allow_html=True)
                 except Exception as e:
                     st.error(f"""
                     **Processing Error**  
@@ -447,15 +533,21 @@ def main():
     with col2:
         st.markdown("""
         ### 🎯 How to Use
-        1. Enter your question in the text box
-        2. Click the search button
-        3. Review processing steps
-        4. See final answer
+        1. **Enter** your question in the text box  
+        2. **Click** the search button  
+        3. **Review** processing steps  
+        4. **Analyze** final structured answer  
 
         ### 💡 Example Questions
-        - What's new in AI image recognition?
-        - How is Project B progressing?
-        - Recent machine learning trends?
+        - What's new in quantum machine learning?  
+        - How is Project Y progressing?  
+        - Recent breakthroughs in AI image recognition?  
+
+        ### 🔍 Search Features
+        - Automatic query optimization  
+        - Technical document analysis  
+        - Cross-project insights  
+        - Source-aware reporting  
         """)
 
 if __name__ == "__main__":