app.py

import os
import pathlib
import re
import gradio as gr
from langchain.docstore.document import Document
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS

os.environ["OPENAI_API_KEY"] = "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"

from langchain.prompts.chat import (
    ChatPromptTemplate,
    SystemMessagePromptTemplate,
    HumanMessagePromptTemplate,
)
from langchain.chat_models import ChatOpenAI
from langchain.chains import RetrievalQAWithSourcesChain

# Set the data store directory
DATA_STORE_DIR = "data_store"

if os.path.exists(DATA_STORE_DIR):
    vector_store = FAISS.load_local(
        DATA_STORE_DIR,
        OpenAIEmbeddings()
    )
else:
    print(f"Missing files. Upload index.faiss and index.pkl files to {DATA_STORE_DIR} directory first")

system_template = """Use the following pieces of context to answer the user's question.
Take note of the sources and include them in the answer in the format: "SOURCES: source1", use "SOURCES" in capital letters regardless of the number of sources.
If you don't know the answer, just say "I don't know", don't try to make up an answer.
----------------
{summaries}"""

messages = [
    SystemMessagePromptTemplate.from_template(system_template),
    HumanMessagePromptTemplate.from_template("{question}")
]
prompt = ChatPromptTemplate.from_messages(messages)

llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0,
                 max_tokens=256)  # Modify model_name if you have access to GPT-4

chain_type_kwargs = {"prompt": prompt}
chain = RetrievalQAWithSourcesChain.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vector_store.as_retriever(),
    return_source_documents=True,
    chain_type_kwargs=chain_type_kwargs
)


def chatbot_interface(query):
    result = chain(query)
    return result['answer']


# Create a Gradio interface
gr.Interface(
    fn=chatbot_interface,
    inputs="text",
    outputs="text",
    title="LLM Chatbot",
    description="Chat with the LLM Chatbot on Custom Data"
).launch()