app.py

import gradio as gr
from huggingface_hub import InferenceClient

##########
import os
from dotenv import load_dotenv

from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings

from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_chroma import Chroma
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.embeddings import HuggingFaceEmbeddings

import gradio as gr

MODEL   = "gpt-4o-mini"
db_name = "vector_db"

CSS = """
.contain { display: flex; flex-direction: column; }
.gradio-container { height: 100vh !important; }
#component-0 { height: 100%; }
#chatbot { flex-grow: 1; overflow: auto;}
"""

load_dotenv()
os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')

vectorstore = Chroma(persist_directory=db_name, embedding_function=OpenAIEmbeddings())
llm         = ChatOpenAI(temperature=0.7, model_name=MODEL)
memory      = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
retriever   = vectorstore.as_retriever()
conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)

def chat(question, history):
    # Get model response
    result = conversation_chain.invoke({"question": question})
    bot_response = (result["answer"]).replace(f"\\[", " $$ ").replace(f"\\]", " $$ ")

    # Append the latest conversation
    history.append((question, bot_response))

    return history, ""  # Return updated history and clear the input box

# Create Gradio UI
with gr.Blocks(css=CSS) as demo:
    chatbot = gr.Chatbot(latex_delimiters=[{"left": "$$", "right": "$$", "display": True},
                                           {"left": "\\(", "right": "\\)", "display": False}], elem_id="chatbot")
    msg = gr.Textbox(placeholder="Ask something...", interactive=True)  
    btn = gr.Button("Send")

    # Trigger chat function when "Enter" is pressed in the textbox
    msg.submit(chat, [msg, chatbot], [chatbot, msg])

    # Button click also triggers chat function
    btn.click(chat, [msg, chatbot], [chatbot, msg])

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demoX = 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(inbrowser=True)