Update app.py

app.py

@@ -1,64 +1,84 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+import google.generativeai as genai
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Folder to store the merged vector index
+INDEX_DIR = "rag_multi_pdf_index"
 
+# Load documents from multiple PDFs and build a knowledge base
+def create_knowledge_base(pdf_files):
+    all_chunks = []
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    for pdf_file in pdf_files:
+        loader = PyPDFLoader(pdf_file.name)
+        docs = loader.load()
+        chunks = splitter.split_documents(docs)
+        all_chunks.extend(chunks)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Create embeddings and save vector index
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    vectorstore = FAISS.from_documents(all_chunks, embeddings)
+    vectorstore.save_local(INDEX_DIR)
 
-    messages.append({"role": "user", "content": message})
+    return f"✅ Knowledge base created from {len(pdf_files)} PDFs and saved."
 
-    response = ""
+# Load existing vectorstore
+def load_vectorstore():
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    return FAISS.load_local(INDEX_DIR, embeddings)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+# Ask a question using Gemini + FAISS
+def chat_with_rag(api_key, question):
+    if not api_key or not api_key.startswith("AI"):
+        return "❌ Please provide a valid Gemini API Key starting with 'AI'."
 
-        response += token
-        yield response
+    # Set up Gemini
+    try:
+        genai.configure(api_key=api_key)
+        model = genai.GenerativeModel("gemini-pro")
+    except Exception as e:
+        return f"❌ Gemini API setup failed: {str(e)}"
 
+    try:
+        vs = load_vectorstore()
+        top_docs = vs.similarity_search(question, k=3)
+        context = "\n\n".join([doc.page_content for doc in top_docs])
+    except Exception as e:
+        return f"❌ Error retrieving from vector store: {str(e)}"
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    prompt = f"""Use the following context to answer the question:\n\n{context}\n\nQuestion: {question}"""
 
+    try:
+        response = model.generate_content(prompt)
+        return response.text
+    except Exception as e:
+        return f"❌ Gemini Error: {str(e)}"
+
+# Gradio UI
+with gr.Blocks(title="📚 Multi-PDF RAG Chat with Gemini") as demo:
+    gr.Markdown("## 🧠 Upload multiple PDFs and ask questions using Gemini")
+    
+    with gr.Row():
+        api_key = gr.Textbox(label="🔐 Gemini API Key", placeholder="Paste your Gemini API Key here", type="password")
+    
+    with gr.Row():
+        pdfs = gr.File(label="📂 Upload PDFs", file_types=[".pdf"], file_count="multiple")
+        create_btn = gr.Button("📄 Create Knowledge Base")
+        kb_status = gr.Textbox(label="Knowledge Base Status", interactive=False)
+    
+    create_btn.click(fn=create_knowledge_base, inputs=[pdfs], outputs=[kb_status])
+
+    with gr.Row():
+        question = gr.Textbox(label="❓ Your Question")
+        answer = gr.Textbox(label="💬 Gemini Answer", lines=10)
+        ask_btn = gr.Button("🚀 Ask")
+
+    ask_btn.click(fn=chat_with_rag, inputs=[api_key, question], outputs=[answer])
 
 if __name__ == "__main__":
     demo.launch()