Create app.py

app.py

@@ -0,0 +1,125 @@
+import os
+import gradio as gr
+from langchain_community.document_loaders import PyPDFLoader, TextLoader, Docx2txtLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_groq import ChatGroq
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+
+# --- 1. SETUP API ---
+# In Hugging Face, we use os.environ to get the secret
+api_key = os.environ.get("GROQ_API")
+
+# --- 2. FILE LOADING LOGIC ---
+def load_any(path: str):
+    p = path.lower()
+    if p.endswith(".pdf"): return PyPDFLoader(path).load()
+    if p.endswith(".txt"): return TextLoader(path, encoding="utf-8").load()
+    if p.endswith(".docx"): return Docx2txtLoader(path).load()
+    return []
+
+# --- 3. PROCESSING FUNCTION ---
+# This function runs when the user clicks "Build Chatbot"
+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."
+
+    try:
+        # Load Documents
+        docs = []
+        for file_obj in files:
+            # Gradio passes file objects, we need their paths
+            docs.extend(load_any(file_obj.name))
+        
+        if not docs:
+            return None, "⚠️ No readable text found in files."
+
+        # Split Text
+        splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+        chunks = splitter.split_documents(docs)
+
+        # Create Embeddings & Vector Store
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+        db = FAISS.from_documents(chunks, embeddings)
+        retriever = db.as_retriever(search_kwargs={"k": 4})
+
+        # Create Chain
+        llm = ChatGroq(
+            groq_api_key=api_key,
+            model="llama-3.3-70b-versatile",
+            temperature=0
+        )
+        
+        memory = ConversationBufferMemory(
+            memory_key="chat_history",
+            return_messages=True,
+            output_key="answer"
+        )
+
+        chain = ConversationalRetrievalChain.from_llm(
+            llm=llm,
+            retriever=retriever,
+            memory=memory,
+            return_source_documents=True,
+            output_key="answer"
+        )
+
+        return chain, f"✅ Success! Processed {len(chunks)} chunks. You can chat now."
+
+    except Exception as e:
+        return None, f"❌ Error: {str(e)}"
+
+# --- 4. CHAT FUNCTION ---
+def chat_function(message, history, chain):
+    if not chain:
+        return "⚠️ Please upload files and click 'Build 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)")
+    
+    # Store the RAG chain in the user's browser session (State)
+    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)
+        
+        with gr.Column(scale=2):
+            chatbot = gr.ChatInterface(
+                fn=chat_function, 
+                additional_inputs=[chain_state] # Pass the chain to the chat function
+            )
+
+    # Connect the "Build" button to the processing function
+    build_btn.click(
+        fn=process_files, 
+        inputs=[file_input], 
+        outputs=[chain_state, status_output]
+    )
+
+if __name__ == "__main__":
+    demo.launch()