The hello world of Chatbots, with domain specific text passed in

chat_with_llamas.py

from langchain_community.chat_models import ChatOpenAI
from llama_index import SimpleDirectoryReader
from llama_index import GPTVectorStoreIndex, LLMPredictor, ServiceContext, PromptHelper, load_index_from_storage, StorageContext

import gradio as gr
def init_index(directory_path):
    # model params - refer docs
    max_input_size = 4096
    num_outputs = 512
    chunk_size_limit = 600

    # llm predictor with langchain ChatOpenAI
    # ChatOpenAI model is a part of the LangChain library and is used to interact with the GPT-3.5-turbo model provided by OpenAI
    prompt_helper = PromptHelper(max_input_size, num_outputs,  chunk_size_limit=chunk_size_limit)
    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.7, model_name="gpt-3.5-turbo", max_tokens=num_outputs))

    # read documents from docs folder
    documents = SimpleDirectoryReader(directory_path).load_data()

    # This index is created using the LlamaIndex library. It processes the document content and constructs the index to facilitate efficient querying
    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
    index = GPTVectorStoreIndex.from_documents(documents, service_context=service_context)

    # save the created index
    index.storage_context.persist()

    return index

def chatbot(input_text):
    # rebuild storage context
    storage_context = StorageContext.from_defaults(persist_dir="storage")
    # load index
    index = load_index_from_storage(storage_context)
    # get response for the question
    response = index.as_query_engine( response_mode="compact").query(input_text)
    return response.response

def main():
    # Replace with the path to your folder containing text files
    # (If you have PDFs, extract text with "fitz" aka "PyMuPDF")
    data = "data" 
    # create index
    init_index(data)

    # create ui interface to interact with gpt-3 model
    iface = gr.Interface(fn=chatbot,
                        inputs=gr.components.Textbox(lines=7, placeholder="Enter your question here"),
                        outputs="text",
                        title="AI ChatBot: Your Knowledge Companion Powered-by ChatGPT",
                        description="Ask any question about the scanned docs",
                        )
    iface.launch(share=False)

if __name__ == "__main__":
    main()