Creating app.py

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import tempfile
+import os
+import shutil
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain_community.document_loaders import WebBaseLoader
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+
+# Streamlit UI
+st.title("🔍 Chat with Any Website")
+
+# User inputs
+openai_api_key = st.text_input("Enter OpenAI API Key", type="password")
+website_url = st.text_input("Enter Website URL")
+
+# Temporary directory to store FAISS index
+temp_dir = tempfile.gettempdir()
+faiss_db_path = os.path.join(temp_dir, "faiss_index_dir")
+
+# Ensure FAISS directory exists
+if not os.path.exists(faiss_db_path):
+    os.makedirs(faiss_db_path)
+
+# Load embeddings if already created
+if os.path.exists(os.path.join(faiss_db_path, "index.faiss")):
+    docsearch = FAISS.load_local(faiss_db_path, OpenAIEmbeddings(), allow_dangerous_deserialization=True)
+else:
+    docsearch = None
+
+if st.button("Build Embeddings") and openai_api_key and website_url:
+    st.info("Fetching website data...")
+    os.environ['OPENAI_API_KEY'] = openai_api_key
+    
+    # Load website data
+    loader = WebBaseLoader(website_url)
+    raw_text = loader.load()
+    
+    # Chunking the fetched text
+    text_splitter = CharacterTextSplitter(separator='\n', chunk_size=500, chunk_overlap=50)
+    docs = text_splitter.split_documents(raw_text)
+    
+    # Creating embeddings
+    embeddings = OpenAIEmbeddings()
+    docsearch = FAISS.from_documents(docs, embeddings)
+    
+    # Save FAISS index
+    if os.path.exists(faiss_db_path):
+        shutil.rmtree(faiss_db_path)
+    os.makedirs(faiss_db_path)
+    docsearch.save_local(faiss_db_path)
+    
+    st.success("Embeddings built and saved successfully!")
+
+# Chat section
+if docsearch:
+    st.subheader("💬 Chat with Website")
+    user_query = st.text_input("Enter your question")
+    if st.button("Get Answer") and user_query:
+        chain = load_qa_chain(OpenAI(), chain_type="stuff")
+        docs = docsearch.similarity_search(user_query)
+        response = chain.run(input_documents=docs, question=user_query)
+        st.write("**Response:**", response)