Create app.py

app.py

@@ -0,0 +1,74 @@
+import gradio as gr
+import os
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
+from langchain_community.vectorstores import Pinecone
+from langchain.chains import RetrievalQA
+import pinecone
+
+# Global flag to avoid multiple index creations
+INDEX_NAME = "rag-demo-index"
+
+def process_rag(api_key_gemini, api_key_pinecone, pinecone_env, pdf_file, user_question):
+    if not api_key_gemini or not api_key_pinecone:
+        return "❌ Please provide both Gemini and Pinecone API keys."
+
+    if not pdf_file:
+        return "❌ Please upload a PDF file."
+
+    try:
+        # Step 1: Load and chunk the PDF
+        loader = PyPDFLoader(pdf_file.name)
+        documents = loader.load()
+        splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        docs = splitter.split_documents(documents)
+
+        # Step 2: Init Gemini Embeddings
+        embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key_gemini)
+
+        # Step 3: Init Pinecone
+        pinecone.init(api_key=api_key_pinecone, environment=pinecone_env)
+
+        if INDEX_NAME not in pinecone.list_indexes():
+            pinecone.create_index(name=INDEX_NAME, dimension=768, metric="cosine")
+
+        # Step 4: Store docs in Pinecone
+        vectordb = Pinecone.from_documents(docs, embedding=embeddings, index_name=INDEX_NAME)
+
+        # Step 5: Create retriever
+        retriever = vectordb.as_retriever()
+
+        # Step 6: Use Gemini for generation
+        llm = ChatGoogleGenerativeAI(model="gemini-pro", google_api_key=api_key_gemini, temperature=0)
+        qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever, return_source_documents=True)
+
+        # Step 7: Ask question
+        result = qa_chain({"query": user_question})
+        return result["result"]
+
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+# Gradio Interface
+with gr.Blocks() as app:
+    gr.Markdown("## 📄🔍 PDF Question Answering using Pinecone + Gemini (RAG)")
+    
+    with gr.Row():
+        gemini_key = gr.Textbox(label="🔐 Gemini API Key", type="password")
+        pinecone_key = gr.Textbox(label="🌲 Pinecone API Key", type="password")
+        pinecone_env = gr.Textbox(label="🌍 Pinecone Environment (e.g., us-east1-gcp)")
+
+    pdf_file = gr.File(label="📄 Upload your PDF", file_types=[".pdf"])
+    user_question = gr.Textbox(label="❓ Ask your question")
+    answer_output = gr.Textbox(label="🤖 Gemini Answer", lines=10)
+
+    submit_btn = gr.Button("🔍 Ask")
+
+    submit_btn.click(
+        fn=process_rag,
+        inputs=[gemini_key, pinecone_key, pinecone_env, pdf_file, user_question],
+        outputs=answer_output
+    )
+
+app.launch()