app.py

from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
from langchain.prompts import PromptTemplate
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.llms import CTransformers
from langchain.chains import RetrievalQA
import gradio as gr

DB_FAISS_PATH = 'vectorstore/db_faiss'

custom_prompt_template = """Use the following pieces of information to answer the user's question.
If you don't know the answer, just say that you don't know, don't try to make up an answer.

Context: {context}
Question: {question}

Only return the helpful answer below and nothing else.
Helpful answer:
"""

def set_custom_prompt():
    """
    Prompt template for QA retrieval for each vectorstore
    """
    prompt = PromptTemplate(template=custom_prompt_template,
                            input_variables=['context', 'question'])
    return prompt

def load_llm():
    # Load the locally downloaded model here
    llm = CTransformers(
        model = "TheBloke/Llama-2-7B-Chat-GGML",
        model_type="llama",
        max_new_tokens = 512,
        temperature = 0.5
    )
    return llm

def qa_bot(query):
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
                                       model_kwargs={'device': 'cpu'})
    db = FAISS.load_local(DB_FAISS_PATH, embeddings)
    llm = load_llm()
    qa_prompt = set_custom_prompt()
    qa_chain = RetrievalQA.from_chain_type(llm=llm,
                                           chain_type='stuff',
                                           retriever=db.as_retriever(search_kwargs={'k': 2}),
                                           return_source_documents=True,
                                           chain_type_kwargs={'prompt': qa_prompt}
                                          )
    result = qa_chain({'query': query})
    response = result['answers'][0]['text'] if result['answers'] else "Sorry, I don't have an answer for that."

    return response

iface = gr.Interface(
    fn=qa_bot,
    inputs="text",
    outputs="text",
    title="Medical Query Bot",
    description="Enter your medical query to get an answer."
)

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