Update app.py

app.py

@@ -1,91 +1,74 @@
-import os
 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
 
-# Constants
+# Global flag to avoid multiple index creations
 INDEX_NAME = "rag-demo-index"
 
-def process_rag(pdf_file, user_question):
-    # Load secrets from Hugging Face (or env manually)
-    pinecone_api_key = os.environ.get("PINECONE_API_KEY")
-    pinecone_env = os.environ.get("PINECONE_ENVIRONMENT")  # Example: "gcp-starter"
-    google_api_key = os.environ.get("GOOGLE_API_KEY")
-
-    if not all([pinecone_api_key, pinecone_env, google_api_key]):
-        return "❌ Missing API key(s). Please check Pinecone & Google Gemini keys."
+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:
-        # 1. Load and split PDF
+        # 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)
 
-        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        docs = text_splitter.split_documents(documents)
-
-        # 2. Gemini Embeddings
-        embeddings = GoogleGenerativeAIEmbeddings(
-            model="models/embedding-001",
-            google_api_key=google_api_key
-        )
+        # Step 2: Init Gemini Embeddings
+        embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key_gemini)
 
-        # 3. Init Pinecone (old client)
-        pinecone.init(api_key=pinecone_api_key, environment=pinecone_env)
+        # 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")
 
-        # 4. Create LangChain-compatible Vector DB
-        vectorstore = Pinecone.from_documents(
-            documents=docs,
-            embedding=embeddings,
-            index_name=INDEX_NAME
-        )
-
-        retriever = vectorstore.as_retriever()
-
-        # 5. Gemini LLM
-        llm = ChatGoogleGenerativeAI(
-            model="gemini-pro",
-            google_api_key=google_api_key,
-            temperature=0
-        )
-
-        # 6. Retrieval QA chain
-        qa_chain = RetrievalQA.from_chain_type(
-            llm=llm,
-            retriever=retriever,
-            return_source_documents=False
-        )
-
-        # 7. Ask question
+        # 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 UI
-with gr.Blocks() as demo:
-    gr.Markdown("## 🔍 Ask Questions from PDF using Gemini + Pinecone (LangChain RAG)")
-
-    with gr.Row():
-        pdf_input = gr.File(label="📄 Upload PDF", file_types=[".pdf"])
-        question_input = gr.Textbox(label="❓ Ask your question")
+# Gradio Interface
+with gr.Blocks() as app:
+    gr.Markdown("## 📄🔍 PDF Question Answering using Pinecone + Gemini (RAG)")
     
-    answer_output = gr.Textbox(label="🤖 Gemini Answer", lines=8)
+    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)
 
-    ask_button = gr.Button("🔎 Run RAG")
+    submit_btn = gr.Button("🔍 Ask")
 
-    ask_button.click(fn=process_rag, inputs=[pdf_input, question_input], outputs=answer_output)
+    submit_btn.click(
+        fn=process_rag,
+        inputs=[gemini_key, pinecone_key, pinecone_env, pdf_file, user_question],
+        outputs=answer_output
+    )
 
-demo.launch()
+app.launch()