Update app.py

app.py

@@ -1,111 +1,220 @@
-# pip install streamlit langchain lanchain-openai beautifulsoup4 python-dotenv chromadb
+# # pip install streamlit langchain lanchain-openai beautifulsoup4 python-dotenv chromadb
+# import os
+# import streamlit as st
+# from langchain_core.messages import AIMessage, HumanMessage
+# from langchain_community.document_loaders import WebBaseLoader
+# from langchain.text_splitter import RecursiveCharacterTextSplitter
+# from langchain_community.vectorstores import Chroma
+# from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+# #from dotenv import load_dotenv
+# from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+# from langchain.chains import create_history_aware_retriever, create_retrieval_chain
+# from langchain.chains.combine_documents import create_stuff_documents_chain
+# from constants import openai_key
+
+# os.environ["OPENAI_API_KEY"]=openai_key
+
+
+# #load_dotenv()
+
+# def get_vectorstore_from_url(url):
+#     # get the text in document form
+#     loader = WebBaseLoader(url)
+#     document = loader.load()
+    
+#     # split the document into chunks
+#     text_splitter = RecursiveCharacterTextSplitter()
+#     document_chunks = text_splitter.split_documents(document)
+    
+#     # create a vectorstore from the chunks
+#     vector_store = Chroma.from_documents(document_chunks, OpenAIEmbeddings())
+
+#     return vector_store
+
+# def get_context_retriever_chain(vector_store):
+#     llm = ChatOpenAI()
+    
+#     retriever = vector_store.as_retriever()
+    
+#     prompt = ChatPromptTemplate.from_messages([
+#       MessagesPlaceholder(variable_name="chat_history"),
+#       ("user", "{input}"),
+#       ("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
+#     ])
+    
+#     retriever_chain = create_history_aware_retriever(llm, retriever, prompt)
+    
+#     return retriever_chain
+    
+# def get_conversational_rag_chain(retriever_chain): 
+    
+#     llm = ChatOpenAI()
+    
+#     prompt = ChatPromptTemplate.from_messages([
+#       ("system", "Answer the user's questions based on the below context:\n\n{context}"),
+#       MessagesPlaceholder(variable_name="chat_history"),
+#       ("user", "{input}"),
+#     ])
+    
+#     stuff_documents_chain = create_stuff_documents_chain(llm,prompt)
+    
+#     return create_retrieval_chain(retriever_chain, stuff_documents_chain)
+
+# def get_response(user_input):
+#     retriever_chain = get_context_retriever_chain(st.session_state.vector_store)
+#     conversation_rag_chain = get_conversational_rag_chain(retriever_chain)
+    
+#     response = conversation_rag_chain.invoke({
+#         "chat_history": st.session_state.chat_history,
+#         "input": user_input
+#     })
+    
+#     return response['answer']
+
+# # app config
+# st.set_page_config(page_title="Chat with websites", page_icon="🤖")
+# st.title("Chat with websites")
+
+# # sidebar
+# with st.sidebar:
+#     st.header("Settings")
+#     website_url = st.text_input("Website URL")
+
+# if website_url is None or website_url == "":
+#     st.info("Please enter a website URL")
+
+# else:
+#     # session state
+#     if "chat_history" not in st.session_state:
+#         st.session_state.chat_history = [
+#             AIMessage(content="Hello, I am a bot. How can I help you?"),
+#         ]
+#     if "vector_store" not in st.session_state:
+#         st.session_state.vector_store = get_vectorstore_from_url(website_url)    
+
+#     # user input
+#     user_query = st.chat_input("Type your message here...")
+#     if user_query is not None and user_query != "":
+#         response = get_response(user_query)
+#         st.session_state.chat_history.append(HumanMessage(content=user_query))
+#         st.session_state.chat_history.append(AIMessage(content=response))
+        
+       
+
+#     # conversation
+#     for message in st.session_state.chat_history:
+#         if isinstance(message, AIMessage):
+#             with st.chat_message("AI"):
+#                 st.write(message.content)
+#         elif isinstance(message, HumanMessage):
+#             with st.chat_message("Human"):
+#                 st.write(message.content)
+
+
 import os
 import streamlit as st
 from langchain_core.messages import AIMessage, HumanMessage
 from langchain_community.document_loaders import WebBaseLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
-from langchain_openai import OpenAIEmbeddings, ChatOpenAI
-#from dotenv import load_dotenv
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.llms import HuggingFaceHub
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain.chains import create_history_aware_retriever, create_retrieval_chain
 from langchain.chains.combine_documents import create_stuff_documents_chain
-from constants import openai_key
+from dotenv import load_dotenv
 
-os.environ["OPENAI_API_KEY"]=openai_key
-
-
-#load_dotenv()
+# Load Hugging Face token from .env
+load_dotenv()
 
+# Function to get vectorstore from a website
 def get_vectorstore_from_url(url):
-    # get the text in document form
     loader = WebBaseLoader(url)
-    document = loader.load()
-    
-    # split the document into chunks
+    documents = loader.load()
+
+    # Split into chunks
     text_splitter = RecursiveCharacterTextSplitter()
-    document_chunks = text_splitter.split_documents(document)
-    
-    # create a vectorstore from the chunks
-    vector_store = Chroma.from_documents(document_chunks, OpenAIEmbeddings())
+    chunks = text_splitter.split_documents(documents)
+
+    # Embeddings using Hugging Face
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+    # Vector store
+    vector_store = Chroma.from_documents(chunks, embeddings)
 
     return vector_store
 
+# History-aware retriever
 def get_context_retriever_chain(vector_store):
-    llm = ChatOpenAI()
-    
+    llm = HuggingFaceHub(
+        repo_id="google/flan-t5-base",
+        model_kwargs={"temperature": 0.5, "max_length": 512}
+    )
+
     retriever = vector_store.as_retriever()
-    
+
     prompt = ChatPromptTemplate.from_messages([
-      MessagesPlaceholder(variable_name="chat_history"),
-      ("user", "{input}"),
-      ("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
+        MessagesPlaceholder(variable_name="chat_history"),
+        ("user", "{input}"),
+        ("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
     ])
-    
-    retriever_chain = create_history_aware_retriever(llm, retriever, prompt)
-    
-    return retriever_chain
-    
-def get_conversational_rag_chain(retriever_chain): 
-    
-    llm = ChatOpenAI()
-    
+
+    return create_history_aware_retriever(llm, retriever, prompt)
+
+# Conversational chain
+def get_conversational_rag_chain(retriever_chain):
+    llm = HuggingFaceHub(
+        repo_id="google/flan-t5-base",
+        model_kwargs={"temperature": 0.5, "max_length": 512}
+    )
+
     prompt = ChatPromptTemplate.from_messages([
-      ("system", "Answer the user's questions based on the below context:\n\n{context}"),
-      MessagesPlaceholder(variable_name="chat_history"),
-      ("user", "{input}"),
+        ("system", "Answer the user's questions based on the below context:\n\n{context}"),
+        MessagesPlaceholder(variable_name="chat_history"),
+        ("user", "{input}"),
     ])
-    
-    stuff_documents_chain = create_stuff_documents_chain(llm,prompt)
-    
+
+    stuff_documents_chain = create_stuff_documents_chain(llm, prompt)
+
     return create_retrieval_chain(retriever_chain, stuff_documents_chain)
 
+# Main response generator
 def get_response(user_input):
     retriever_chain = get_context_retriever_chain(st.session_state.vector_store)
-    conversation_rag_chain = get_conversational_rag_chain(retriever_chain)
-    
-    response = conversation_rag_chain.invoke({
+    rag_chain = get_conversational_rag_chain(retriever_chain)
+
+    response = rag_chain.invoke({
         "chat_history": st.session_state.chat_history,
         "input": user_input
     })
-    
+
     return response['answer']
 
-# app config
-st.set_page_config(page_title="Chat with websites", page_icon="🤖")
-st.title("Chat with websites")
+# Streamlit UI
+st.set_page_config(page_title="Chat with Websites", page_icon="🤖")
+st.title("🧠 Chat with Websites (Free Hugging Face Model)")
 
-# sidebar
 with st.sidebar:
-    st.header("Settings")
-    website_url = st.text_input("Website URL")
-
-if website_url is None or website_url == "":
-    st.info("Please enter a website URL")
+    st.header("🔧 Settings")
+    website_url = st.text_input("🌐 Website URL")
 
+# Handle input and chatbot logic
+if not website_url:
+    st.info("Please enter a website URL in the sidebar.")
 else:
-    # session state
     if "chat_history" not in st.session_state:
-        st.session_state.chat_history = [
-            AIMessage(content="Hello, I am a bot. How can I help you?"),
-        ]
+        st.session_state.chat_history = [AIMessage(content="Hello! Ask me anything about this website.")]
     if "vector_store" not in st.session_state:
-        st.session_state.vector_store = get_vectorstore_from_url(website_url)    
+        with st.spinner("🔍 Loading and indexing website..."):
+            st.session_state.vector_store = get_vectorstore_from_url(website_url)
 
-    # user input
-    user_query = st.chat_input("Type your message here...")
-    if user_query is not None and user_query != "":
-        response = get_response(user_query)
-        st.session_state.chat_history.append(HumanMessage(content=user_query))
+    user_input = st.chat_input("Type your message...")
+    if user_input:
+        response = get_response(user_input)
+        st.session_state.chat_history.append(HumanMessage(content=user_input))
         st.session_state.chat_history.append(AIMessage(content=response))
-        
-       
 
-    # conversation
-    for message in st.session_state.chat_history:
-        if isinstance(message, AIMessage):
-            with st.chat_message("AI"):
-                st.write(message.content)
-        elif isinstance(message, HumanMessage):
-            with st.chat_message("Human"):
-                st.write(message.content)
+    # Display messages
+    for msg in st.session_state.chat_history:
+        with st.chat_message("AI" if isinstance(msg, AIMessage) else "Human"):
+            st.write(msg.content)