app.py

import os
import gradio as gr
from langchain_community.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA
from langchain_groq import ChatGroq

# Load documents
loader = TextLoader("sample_readme.txt")
documents = loader.load()

# Split into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
docs = text_splitter.split_documents(documents)

# Create embeddings
embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")

# Vector DB
vectorstore = Chroma.from_documents(docs, embedding, persist_directory="rag_chroma_groq")
retriever = vectorstore.as_retriever()

# Groq LLM
groq_llm = ChatGroq(api_key=os.getenv("GROQ_API_KEY"), model_name="llama3-70b-8192")

# RAG chain
qa_chain = RetrievalQA.from_chain_type(
    llm=groq_llm,
    retriever=retriever,
    return_source_documents=False
)

# Chat function
def chatbot_interface(user_query):
    result = qa_chain({"query": user_query})
    return result["result"]

# Gradio UI
iface = gr.Interface(
    fn=chatbot_interface,
    inputs=gr.Textbox(label="Ask a question about the document"),
    outputs=gr.Textbox(label="Answer"),
    title="RAG Chatbot with Groq + LangChain",
    description="Ask questions about sample_readme.txt using Groq LLM"
)

if __name__ == "__main__":
    iface.launch()