app.py

from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
import torch
import gradio as gr


# PersistDataset -----
import os
import csv
import gradio as gr
from gradio import inputs, outputs
import huggingface_hub
from huggingface_hub import Repository, hf_hub_download, upload_file
from datetime import datetime

DATASET_REPO_URL = "https://huggingface.co/datasets/awacke1/Carddata.csv"
DATASET_REPO_ID = "awacke1/Carddata.csv"
DATA_FILENAME = "Carddata.csv"
DATA_FILE = os.path.join("data", DATA_FILENAME)
HF_TOKEN = os.environ.get("HF_TOKEN")

SCRIPT = """
<script>
if (!window.hasBeenRun) {
    window.hasBeenRun = true;
    console.log("should only happen once");
    document.querySelector("button.submit").click();
}
</script>
"""
#try:
#    hf_hub_download(
#        repo_id=DATASET_REPO_ID,
#        filename=DATA_FILENAME,
#        cache_dir=DATA_DIRNAME,
#        force_filename=DATA_FILENAME
#    )
#except:
#    print("file not found")
#repo = Repository(
#    local_dir="data", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
#)

def generate_html() -> str:
    with open(DATA_FILE) as csvfile:
        reader = csv.DictReader(csvfile)
        rows = []
        for row in reader:
            rows.append(row)
        rows.reverse()
        if len(rows) == 0:
            return "no messages yet"
        else:
            html = "<div class='chatbot'>"
            for row in rows:
                html += "<div>"
                html += f"<span>{row['inputs']}</span>"
                html += f"<span class='outputs'>{row['outputs']}</span>"
                html += "</div>"
            html += "</div>"
            return html
            
            
def store_message(name: str, message: str):
    if name and message:
        with open(DATA_FILE, "a") as csvfile:
            writer = csv.DictWriter(csvfile, fieldnames=["name", "message", "time"])
            writer.writerow(
                {"name": name.strip(), "message": message.strip(), "time": str(datetime.now())}
            )
        # uncomment line below to begin saving.  If creating your own copy you will need to add a access token called "HF_TOKEN" to your profile, then create a secret for your repo with the access code naming it "HF_TOKEN"  For the CSV as well you can copy the header and first few lines to your own then update the paths above which should work to save to your own repository for datasets.    
        #commit_url = repo.push_to_hub()
    return ""
    
iface = gr.Interface(
    store_message,
    [
        inputs.Textbox(placeholder="Your name"),
        inputs.Textbox(placeholder="Your message", lines=2),
    ],
    "html",
    css="""
    .message {background-color:cornflowerblue;color:white; padding:4px;margin:4px;border-radius:4px; }
    """,
    title="Reading/writing to a HuggingFace dataset repo from Spaces",
    description=f"This is a demo of how to do simple *shared data persistence* in a Gradio Space, backed by a dataset repo.",
    article=f"The dataset repo is [{DATASET_REPO_URL}]({DATASET_REPO_URL})",
)


mname = "facebook/blenderbot-400M-distill"
model = BlenderbotForConditionalGeneration.from_pretrained(mname)
tokenizer = BlenderbotTokenizer.from_pretrained(mname)

def take_last_tokens(inputs, note_history, history):
    """Filter the last 128 tokens"""
    if inputs['input_ids'].shape[1] > 128:
        inputs['input_ids'] = torch.tensor([inputs['input_ids'][0][-128:].tolist()])
        inputs['attention_mask'] = torch.tensor([inputs['attention_mask'][0][-128:].tolist()])
        note_history = ['</s> <s>'.join(note_history[0].split('</s> <s>')[2:])]
        history = history[1:]
    return inputs, note_history, history

def add_note_to_history(note, note_history):
    """Add a note to the historical information"""
    note_history.append(note)
    note_history = '</s> <s>'.join(note_history)
    return [note_history]

title = "Chatbot State of the Art now with Memory Saved to Dataset"
description = """Chatbot With Memory"""

def chat(message, history):
    history = history or []
    if history: 
        history_useful = ['</s> <s>'.join([str(a[0])+'</s> <s>'+str(a[1]) for a in history])]
    else:
        history_useful = []
    history_useful = add_note_to_history(message, history_useful)
    inputs = tokenizer(history_useful, return_tensors="pt")
    inputs, history_useful, history = take_last_tokens(inputs, history_useful, history)
    reply_ids = model.generate(**inputs)
    response = tokenizer.batch_decode(reply_ids, skip_special_tokens=True)[0]
    history_useful = add_note_to_history(response, history_useful)
    list_history = history_useful[0].split('</s> <s>')
    history.append((list_history[-2], list_history[-1]))
#    store_message(message, response) # Save to dataset
    return history, history

gr.Interface(
    fn=chat,
    theme="huggingface",
    css=".footer {display:none !important}",
    inputs=["text", "state"],
    outputs=["chatbot", "state"],
    title=title,
    allow_flagging="never",
    description=f"Gradio chatbot backed by memory in a dataset repository.",
    article=f"The dataset repo is [{DATASET_REPO_URL}]({DATASET_REPO_URL})"
    ).launch()