app.py

# chatbot_url_query.py

import os
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.retrievers import TavilyRetriever
from langchain.chains import RetrievalQA

# 1. Set API keys (Replace with your actual keys)
os.environ["GOOGLE_API_KEY"] = "your-google-api-key"
os.environ["TAVILY_API_KEY"] = "your-tavily-api-key"

# 2. Load Google Gemini model
llm = ChatGoogleGenerativeAI(
    model="models/gemini-1.5-flash",
    google_api_key=os.environ["GOOGLE_API_KEY"]
)

# 3. Initialize Tavily Retriever (fetches data from web)
retriever = TavilyRetriever(k=3)

# 4. Create Retrieval QA Chain
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    retriever=retriever,
    return_source_documents=True
)

# 5. Function to run the chatbot
def ask_web_query(url, question):
    query = f"Given the content of the website {url}, answer the following: {question}"
    response = qa_chain.invoke({"query": query})
    
    print("\n✅ Answer:")
    print(response["result"])

    print("\n📄 Sources:")
    for doc in response["source_documents"]:
        print("-", doc.metadata.get("source", "Unknown"))

# 6. Run your chatbot
if __name__ == "__main__":
    url = input("Enter website URL: ")
    question = input("Ask your question about the website: ")
    ask_web_query(url, question)