app.py

import gradio as gr
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

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 = PromptTemplate(template=custom_prompt_template,
                            input_variables=['context', 'question'])
    return prompt

def retrieval_qa_chain(llm, prompt, db):
    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': prompt}
                                          )
    return qa_chain

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

def qa_bot():
    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 = retrieval_qa_chain(llm, qa_prompt, db)
    return qa

# Define a function to respond to messages using your QA model
def respond(message, history, system_message, max_tokens, temperature, top_p):
    qa_result = qa_bot()
    response = qa_result({'query': message})
    return response

# Create a Gradio interface using the respond function
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)

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