File size: 5,185 Bytes
c18db37
 
 
 
08af166
 
 
 
 
 
 
 
 
6266cf4
 
de6d7ec
9b06b1e
 
 
 
 
 
 
 
6266cf4
9b06b1e
 
 
 
 
 
 
 
 
 
 
 
 
10c450b
9b06b1e
 
 
 
 
 
 
de6d7ec
9b06b1e
 
08af166
c18db37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b06b1e
dd5e8e8
 
f60697c
c18db37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b06b1e
 
 
 
 
 
 
c18db37
 
9b06b1e
 
c18db37
 
 
 
 
 
 
 
9b06b1e
 
6ca51ed
f60697c
9b06b1e
5816dc1
4414bb8
0aa9192
 
 
 
 
 
 
 
 
 
4414bb8
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
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


# -------------------------------------------- For Memory - you will need to set up a dataset and HF_TOKEN ---------
UseMemory=True

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

if UseMemory: 
   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 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 ""

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 = "💬ChatBack🧠💾"
description = """Chatbot With persistent memory dataset allowing multiagent system AI to access a shared dataset as memory pool with stored interactions. 
 Current Best SOTA Chatbot:  https://huggingface.co/facebook/blenderbot-400M-distill?text=Hey+my+name+is+ChatBack%21+Are+you+ready+to+rock%3F  """

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]))

    # AGI semantic and episodic memory here we come....
    
    store_message(message, response) # Save to dataset  -- uncomment with code above, create a dataset to store and add your HF_TOKEN from profile to this repo to use.
    
    # ....
    
    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 memory dataset for saves is [{DATASET_REPO_URL}]({DATASET_REPO_URL}) 🦃Thanks!🦃 Check out HF Datasets: https://huggingface.co/spaces/awacke1/FreddysDatasetViewer  SOTA papers code and datasets on chat are here: https://paperswithcode.com/datasets?q=chat&v=lst&o=newest"

    ).launch(debug=True)
        
#demo = gr.Blocks()
#with demo:
#    audio_file = gr.inputs.Audio(source="microphone", type="filepath")
#    text = gr.Textbox(label="Speech to Text")
#    TTSchoice = gr.inputs.Radio( label="Pick a Text to Speech Model", choices=MODEL_NAMES,   )
#    audio = gr.Audio(label="Output", interactive=False)
#    b1 = gr.Button("Recognize Speech")
#    b5 = gr.Button("Read It Back Aloud")
#    b1.click(speech_to_text, inputs=audio_file, outputs=text)
#    b5.click(tts,  inputs=[text,TTSchoice], outputs=audio)    
#demo.launch(share=True)