app.py

import gradio as gr
from langchain_community.document_loaders import WebBaseLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings
from langchain.chat_models import ChatOpenAI
from langchain import hub
from langchain.schema.runnable import RunnablePassthrough
from langchain.schema.output_parser import StrOutputParser
import os

# Set your OpenAI API key
os.environ["OPENAI_API_KEY"] = "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"

# Global variable to store the RAG chain object
rag_chain = None

def process_url(url):
    try:
        # Initialize the loader with the specified web path
        loader = WebBaseLoader(web_paths=[url])
        docs = loader.load()

        # Split the documents
        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200, add_start_index=True)
        all_splits = text_splitter.split_documents(docs)

        # Create vectorstore
        vectorstore = Chroma.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())
        retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 2})

        # Define the prompt
        prompt = hub.pull("rlm/rag-prompt")

        # Define the LLM
        llm = ChatOpenAI(model="gpt-4")

        # Define the RAG chain
        def format_docs(docs):
            return "\n\n".join(doc.page_content for doc in docs)

        global rag_chain
        rag_chain = (
            {"context": retriever | format_docs, "question": RunnablePassthrough()}
            | prompt
            | llm
            | StrOutputParser()
        )

        return "Successfully processed the URL. You can now ask questions."
    except Exception as e:
        return f"Error processing URL: {e}"

def chat_with_rag_chain(message):
    global rag_chain
    if rag_chain:
        try:
            response = rag_chain.invoke(message)
            return response
        except Exception as e:
            return f"Error invoking RAG chain: {e}"
    else:
        return "Please enter a URL first and process it."

# Gradio interface for entering the URL
url_input_interface = gr.Interface(
    fn=process_url,
    inputs=gr.Textbox(label="Enter URL", placeholder="https://example.com"),
    outputs=gr.Textbox(label="Status"),
    title="RAG Chain URL Processor",
    description="Enter a URL to process the article using a RAG chain model."
)

# Gradio chat interface for Q&A
chat_interface = gr.Interface(
    fn=chat_with_rag_chain,
    inputs=gr.Textbox(label="Your Question"),
    outputs=gr.Textbox(label="Response"),
    title="RAG Chain Chat Interface",
    description="Chat with the RAG chain model after processing a URL."
)

# Combining the two interfaces in a tab layout
gr.TabbedInterface([url_input_interface, chat_interface], ["URL Processor", "Chat Interface"]).launch(debug=True, share=True)