app.py

import streamlit as st
from src.helper import download_hugging_face_embeddings
from langchain.vectorstores import FAISS
from langchain.schema import Document
from langchain.llms import CTransformers
from langchain.chains import RetrievalQA
from dotenv import load_dotenv
import os

app = Flask(__name__)
load_dotenv()

# Download embeddings model
embeddings = download_hugging_face_embeddings()

# Create Document objects with dummy texts and embeddings
documents = [Document(page_content="dummy", embedding=embedding) for embedding in embeddings]

# Initialize FAISS vector store with documents
vector_store = FAISS.from_documents(documents, embeddings)

# Initialize CTransformers model (LLAMA)
llm = CTransformers(model="E:\\project\\Medical-Chatbot\\llama-2-7b-chat.ggmlv3.q4_0.bin", model_type="llama", config={'max_new_tokens': 512, 'temperature': 0.8})

# Initialize RetrievalQA chain
qa = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vector_store.as_retriever(search_kwargs={'k': 2}),
    return_source_documents=True
)

@app.route("/")
def index():
    return render_template('chat.html')

@app.route("/get", methods=["GET", "POST"])
def chat():
    msg = request.form["msg"]
    input = msg
    print(input)
    result = qa({"query": input})
    print("Response : ", result["result"])
    return str(result["result"])

if __name__ == '__main__':
    app.run(host="0.0.0.0", port=8080, debug=True)