Update app.py

app.py

@@ -3,11 +3,11 @@ 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_community.vectorstores import Pinecone as LangchainPinecone
 from langchain.chains import RetrievalQA
-import pinecone
+from pinecone import Pinecone, ServerlessSpec
 
-# Global flag to avoid multiple index creations
+# Global constants
 INDEX_NAME = "rag-demo-index"
 
 def process_rag(api_key_gemini, api_key_pinecone, pinecone_env, pdf_file, user_question):
@@ -18,46 +18,72 @@ def process_rag(api_key_gemini, api_key_pinecone, pinecone_env, pdf_file, user_q
         return "❌ Please upload a PDF file."
 
     try:
-        # Step 1: Load and chunk the PDF
+        # Step 1: Load and split 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 2: Gemini Embeddings
+        embeddings = GoogleGenerativeAIEmbeddings(
+            model="models/embedding-001",
+            google_api_key=api_key_gemini
+        )
+
+        # Step 3: Pinecone setup (new SDK)
+        pc = Pinecone(api_key=api_key_pinecone)
+
+        # 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"
+                )
+            )
+
+        index = pc.Index(INDEX_NAME)
+
+        # Step 4: Store documents in Pinecone
+        vectordb = LangchainPinecone.from_documents(
+            docs,
+            embedding=embeddings,
+            index=index
+        )
 
         # 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
+        # Step 6: Use Gemini LLM
+        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 the question
         result = qa_chain({"query": user_question})
         return result["result"]
 
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-# Gradio Interface
+# 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)")
+        pinecone_env = gr.Textbox(label="🌍 Pinecone Region (e.g., us-east-1)", value="us-east-1")
 
     pdf_file = gr.File(label="📄 Upload your PDF", file_types=[".pdf"])
     user_question = gr.Textbox(label="❓ Ask your question")