Update app.py

app.py

@@ -8,11 +8,14 @@ from langchain_groq import ChatGroq
 from langchain_classic.chains import ConversationalRetrievalChain
 from langchain_classic.memory import ConversationBufferMemory
 
-# --- 1. SETUP API ---
-# In Hugging Face, we use os.environ to get the secret
+# --- NEW IMPORTS FOR HYBRID SEARCH ---
+from langchain_community.retrievers import BM25Retriever
+from langchain.retrievers import EnsembleRetriever
+
+# 1. SETUP API
 api_key = os.environ.get("GROQ_API")
 
-# --- 2. FILE LOADING LOGIC ---
+# 2. FILE LOADING LOGIC
 def load_any(path: str):
     p = path.lower()
     if p.endswith(".pdf"): return PyPDFLoader(path).load()
@@ -20,109 +23,89 @@ def load_any(path: str):
     if p.endswith(".docx"): return Docx2txtLoader(path).load()
     return []
 
-# --- 3. PROCESSING FUNCTION ---
-# This function runs when the user clicks "Build Chatbot"
+# 3. HYBRID PROCESSING FUNCTION
 def process_files(files):
-    if not files:
-        return None, "⚠️ Please upload at least one file."
-    
-    if not api_key:
-        return None, "❌ Error: GROQ_API key not found in Secrets."
+    if not files or not api_key:
+        return None, "⚠️ Missing files or API key."
 
     try:
-        # Load Documents
+        # Load all documents
         docs = []
         for file_obj in files:
             docs.extend(load_any(file_obj.name))
         
         if not docs:
-            return None, "⚠️ No readable text found in files."
+            return None, "⚠️ No readable text found."
 
-        # Split Text
-        splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+        # Split into chunks
+        splitter = RecursiveCharacterTextSplitter(chunk_size=700, chunk_overlap=100)
         chunks = splitter.split_documents(docs)
 
-        # --- SAFETY CHECK (This fixes the error) ---
-        if not chunks:
-            return None, "❌ Error: The PDF contains no selectable text. It might be a scanned image. Please convert it to Word/Text first."
-
-        # Create Embeddings & Vector Store
+        # A. Semantic Search (FAISS)
         embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-        db = FAISS.from_documents(chunks, embeddings)
-        retriever = db.as_retriever(search_kwargs={"k": 4})
+        faiss_db = FAISS.from_documents(chunks, embeddings)
+        faiss_retriever = faiss_db.as_retriever(search_kwargs={"k": 3})
+
+        # B. Keyword Search (BM25) - THIS IS THE MULTI-RETRIEVER ADDITION
+        bm25_retriever = BM25Retriever.from_documents(chunks)
+        bm25_retriever.k = 3
 
-        # Create Chain
-        llm = ChatGroq(
-            groq_api_key=api_key,
-            model="llama-3.3-70b-versatile",
-            temperature=0
+        # C. Ensemble (Hybrid Search)
+        ensemble_retriever = EnsembleRetriever(
+            retrievers=[faiss_retriever, bm25_retriever],
+            weights=[0.6, 0.4] # 60% Semantic, 40% Keyword
         )
-        
+
+        # D. Classic Chain Setup
+        llm = ChatGroq(groq_api_key=api_key, model="llama-3.3-70b-versatile", temperature=0)
         memory = ConversationBufferMemory(
-            memory_key="chat_history",
-            return_messages=True,
+            memory_key="chat_history", 
+            return_messages=True, 
             output_key="answer"
         )
-
+        
         chain = ConversationalRetrievalChain.from_llm(
             llm=llm,
-            retriever=retriever,
+            retriever=ensemble_retriever, # Use Hybrid Retriever
             memory=memory,
             return_source_documents=True,
             output_key="answer"
         )
-
-        return chain, f"✅ Success! Processed {len(chunks)} chunks. You can chat now."
+        
+        return chain, f"✅ Hybrid Multi-RAG Ready! ({len(chunks)} chunks)"
 
     except Exception as e:
         return None, f"❌ Error: {str(e)}"
 
-# --- 4. CHAT FUNCTION ---
+# 4. CHAT FUNCTION
 def chat_function(message, history, chain):
     if not chain:
-        return "⚠️ Please upload files and click 'Build Chatbot' first."
+        return "⚠️ Build the chatbot first."
     
-    try:
-        res = chain.invoke({"question": message})
-        answer = res["answer"]
-        
-        # Format Sources
-        sources = []
-        for d in res.get("source_documents", []):
-            src = os.path.basename(d.metadata.get("source", "unknown"))
-            text = (d.page_content or "").replace("\n", " ")[:100] + "..."
-            sources.append(f"- {src}: {text}")
-            
-        final_answer = answer + "\n\n---\n**Sources:**\n" + "\n".join(sources)
-        return final_answer
-    except Exception as e:
-        return f"❌ Error generating answer: {str(e)}"
-
-# --- 5. BUILD UI ---
-with gr.Blocks(title="RAG Chatbot") as demo:
-    gr.Markdown("# 📚 RAG Chatbot (LangChain + Groq)")
+    res = chain.invoke({"question": message})
+    answer = res["answer"]
     
-    # Store the RAG chain in the user's browser session (State)
+    # Format Sources
+    sources = list(set([os.path.basename(d.metadata.get("source", "unknown")) for d in res.get("source_documents", [])]))
+    source_text = "\n\n---\n**Sources:** " + ", ".join(sources)
+    
+    return answer + source_text
+
+# 5. UI
+with gr.Blocks(title="Hybrid RAG") as demo:
+    gr.Markdown("# 🚀 Hybrid Multi-RAG Chatbot")
     chain_state = gr.State(None)
     
     with gr.Row():
         with gr.Column(scale=1):
-            file_input = gr.File(file_count="multiple", label="Upload PDF/TXT/DOCX")
-            build_btn = gr.Button("Build Chatbot", variant="primary")
-            status_output = gr.Textbox(label="Status", interactive=False)
+            file_input = gr.File(file_count="multiple", label="Upload Docs")
+            build_btn = gr.Button("Build Hybrid RAG", variant="primary")
+            status = gr.Textbox(label="Status", interactive=False)
         
         with gr.Column(scale=2):
-            chatbot = gr.ChatInterface(
-                fn=chat_function, 
-                additional_inputs=[chain_state] # Pass the chain to the chat function
-            )
+            gr.ChatInterface(fn=chat_function, additional_inputs=[chain_state])
 
-    # Connect the "Build" button to the processing function
-    build_btn.click(
-        fn=process_files, 
-        inputs=[file_input], 
-        outputs=[chain_state, status_output]
-    )
+    build_btn.click(process_files, inputs=[file_input], outputs=[chain_state, status])
 
 if __name__ == "__main__":
     demo.launch()