Update app.py

app.py

@@ -1,91 +1,77 @@
-import gradio as gr
 import os
+import gradio as gr
 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 as LangchainPinecone
 from langchain.chains import RetrievalQA
-from pinecone import Pinecone, ServerlessSpec
+import pinecone  # OLD SDK (pinecone-client==2.2.4)
 
-# Global constants
 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 split PDF
+        # Step 1: Load and split 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: Gemini Embeddings
+        # Step 2: Set up embeddings using Gemini
         embeddings = GoogleGenerativeAIEmbeddings(
-            model="models/embedding-001",
+            model="models/embedding-001", 
             google_api_key=api_key_gemini
         )
 
-        # Step 3: Pinecone setup (new SDK)
-        pc = Pinecone(api_key=api_key_pinecone)
+        # Step 3: Initialize Pinecone (old SDK)
+        pinecone.init(api_key=api_key_pinecone, environment=pinecone_env)
 
-        # Create index if it doesn't exist
-        if INDEX_NAME not in pc.list_indexes().names():
-            pc.create_index(
-                name=INDEX_NAME,
-                dimension=768,
-                metric="cosine",
-                spec=ServerlessSpec(
-                    cloud="aws",  # or "gcp"
-                    region=pinecone_env  # example: "us-east-1"
-                )
-            )
+        if INDEX_NAME not in pinecone.list_indexes():
+            pinecone.create_index(name=INDEX_NAME, dimension=768, metric="cosine")
 
-        index = pc.Index(INDEX_NAME)
-
-        # Step 4: Store documents in Pinecone
+        # Step 4: Store docs in Pinecone using LangChain wrapper
         vectordb = LangchainPinecone.from_documents(
-            docs,
-            embedding=embeddings,
-            index=index
+            docs, 
+            embedding=embeddings, 
+            index_name=INDEX_NAME
         )
 
-        # Step 5: Create retriever
+        # Step 5: Create retriever and chain
         retriever = vectordb.as_retriever()
-
-        # Step 6: Use Gemini LLM
         llm = ChatGoogleGenerativeAI(
-            model="gemini-pro",
+            model="gemini-pro", 
             google_api_key=api_key_gemini,
             temperature=0
         )
         qa_chain = RetrievalQA.from_chain_type(
-            llm=llm,
-            retriever=retriever,
+            llm=llm, 
+            retriever=retriever, 
             return_source_documents=True
         )
 
-        # Step 7: Ask the question
+        # Step 6: Ask question
         result = qa_chain({"query": user_question})
         return result["result"]
 
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-# Gradio interface
+# 🎛️ Gradio UI
 with gr.Blocks() as app:
-    gr.Markdown("## 📄🔍 PDF Question Answering using Pinecone + Gemini (RAG)")
+    gr.Markdown("## 📄🔍 PDF Q&A 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 Region (e.g., us-east-1)", value="us-east-1")
+        pinecone_env = gr.Textbox(label="🌍 Pinecone Environment (e.g., us-east-1)")
 
-    pdf_file = gr.File(label="📄 Upload your PDF", file_types=[".pdf"])
+    pdf_file = gr.File(label="📄 Upload PDF", file_types=[".pdf"])
     user_question = gr.Textbox(label="❓ Ask your question")
     answer_output = gr.Textbox(label="🤖 Gemini Answer", lines=10)