app.py

import gradio as gr
from langchain.chains import RetrievalQA
from langchain_groq import ChatGroq
from langchain.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings # type: ignore

# Load FAISS Index and Embeddings
embeddings = HuggingFaceEmbeddings(model_name='all-MiniLM-L6-v2')
vector_store = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

# Initialize LLM
llm = ChatGroq(
    model_name="llama-3.3-70b-versatile",
    temperature=1,
    groq_api_key="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"
)

# Create RAG Chain
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vector_store.as_retriever()
)

# Define Query Function
def search_courses(query):
    result = qa_chain.run(query)
    return result

# Gradio Interface
iface = gr.Interface(
    fn=search_courses,
    inputs=gr.Textbox(label="Enter your query"),
    outputs=gr.Textbox(label="Response"),
    title="Smart Course Search Tool",
    description="Ask questions to find the best free courses on Analytics Vidhya."
)

# Launch the app
iface.launch()