Create app.py

app.py

@@ -0,0 +1,80 @@
+import streamlit as st
+from dotenv import load_dotenv
+import os
+from pinecone import Pinecone
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_pinecone import PineconeVectorStore
+from langchain_core.documents import Document
+from uuid import uuid4
+from langchain.chains import RetrievalQA
+from langchain.llms import HuggingFaceHub
+
+# Load environment variables
+load_dotenv()
+
+# Get API keys from environment variables
+pinecone_api_key = os.getenv("PINECONE_API_KEY")
+google_api_key = os.getenv("GOOGLE_API_KEY")
+huggingfacehub_api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+# Check if API keys are available
+if not pinecone_api_key or not google_api_key or not huggingfacehub_api_token:
+    st.error("API keys not found. Please set PINECONE_API_KEY, GOOGLE_API_KEY, and HUGGINGFACEHUB_API_TOKEN in your .env file.")
+    st.stop()
+
+# Initialize Pinecone
+pc = Pinecone(api_key=pinecone_api_key, environment="us-east1-gcp")  # Replace with your environment if needed
+index_name = "online-rag"
+index = pc.Index(index_name)
+
+# Initialize embeddings
+os.environ['GOOGLE_API_KEY'] = google_api_key
+embeddings = GoogleGenerativeAIEmbeddings(model="models/text-embedding-004")
+
+# Initialize vector store
+vector_store = PineconeVectorStore(index=index, embedding=embeddings)
+
+# Initialize LLaMA 30B model from Hugging Face
+llm = HuggingFaceHub(repo_id="meta-llama/Llama-2-30b-chat-hf", huggingfacehub_api_token=huggingfacehub_api_token)
+
+# Streamlit app
+st.title("LLaMA 30B RAG Chatbot")
+
+# Upload document
+uploaded_file = st.file_uploader("Upload a document", type=["txt", "pdf"])
+
+if uploaded_file is not None:
+    # Read the file
+    file_details = {"filename": uploaded_file.name, "filetype": uploaded_file.type, "filesize": uploaded_file.size}
+    st.write(file_details)
+    file_content = uploaded_file.read().decode("utf-8")
+
+    # Create a document
+    document = Document(page_content=file_content, metadata={"source": uploaded_file.name})
+
+    # Add document to vector store
+    uuids = [str(uuid4()) for _ in range(1)]
+    vector_store.add_documents(documents=[document], ids=uuids)
+    st.write("Document added to Pinecone.")
+
+# Query the chatbot
+query = st.text_input("Enter your query:")
+
+if query:
+    try:
+        # Perform similarity search
+        results = vector_store.similarity_search(query, k=2)
+        st.write("Search Results:")
+        for res in results:
+            st.write(f"* {res.page_content} [{res.metadata}]")
+
+        # Create a RetrievalQA chain
+        qa_chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=vector_store.as_retriever())
+
+        # Get the answer
+        answer = qa_chain.run(query)
+        st.write("Chatbot Response:")
+        st.write(answer)
+
+    except Exception as e:
+        st.error(f"An error occurred: {e}")