Spaces:
Build error
Build error
Update app.py
Browse files
app.py
CHANGED
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import TFAutoModelForCausalLM, AutoTokenizer
|
2 |
+
import tensorflow as tf
|
3 |
+
import gradio as gr
|
4 |
+
from transformers import TFAutoModelForSequenceClassification
|
5 |
+
from transformers import AutoTokenizer
|
6 |
+
import plotly.express as px
|
7 |
+
import plotly.io as pio
|
8 |
+
|
9 |
+
# configuration params
|
10 |
+
pio.templates.default = "plotly_dark"
|
11 |
+
|
12 |
+
# setting up the text in the page
|
13 |
+
TITLE = "<center><h1>Talk with an AI</h1></center>"
|
14 |
+
DESCRIPTION = r"""<center>This application allows you to talk with a machine/robot with state-of-the-art technology!!<br>
|
15 |
+
In the back-end is using the Elapt1c/ElapticAI-1a model. One of the best models in text generation and comprehension.<br>
|
16 |
+
Language processing is done using RoBERTa for sentiment-analysis and spaCy for named-entity recognition and dependency plotting.<br>
|
17 |
+
The AI thinks he is a human, so please treat him as such, else he migh get angry!<br>
|
18 |
+
"""
|
19 |
+
EXAMPLES = [
|
20 |
+
["What is your favorite videogame?"],
|
21 |
+
["What gets you really sad?"],
|
22 |
+
["How can I make you really angry? "],
|
23 |
+
["What do you do for work?"],
|
24 |
+
["What are your hobbies?"],
|
25 |
+
["What is your favorite food?"],
|
26 |
+
]
|
27 |
+
ARTICLE = r"""<center>
|
28 |
+
Done by dr. Gabriel Lopez<br>
|
29 |
+
For more please visit: <a href='https://sites.google.com/view/dr-gabriel-lopez/home'>My Page</a><br>
|
30 |
+
For info about the chat-bot model can also see the <a href="https://arxiv.org/abs/1911.00536">ArXiv paper</a><br>
|
31 |
+
</center>"""
|
32 |
+
|
33 |
+
# Loading necessary NLP models
|
34 |
+
# dialog
|
35 |
+
checkpoint = "elapt1c/ElapticAI-1a" # tf
|
36 |
+
model_gtp2 = TFAutoModelForCausalLM.from_pretrained(checkpoint)
|
37 |
+
tokenizer_gtp2 = AutoTokenizer.from_pretrained(checkpoint)
|
38 |
+
# sentiment
|
39 |
+
checkpoint = f"cardiffnlp/twitter-roberta-base-emotion"
|
40 |
+
model_roberta = TFAutoModelForSequenceClassification.from_pretrained(checkpoint)
|
41 |
+
tokenizer_roberta = AutoTokenizer.from_pretrained(checkpoint)
|
42 |
+
# NER & Dependency
|
43 |
+
nlp = spacy.load("en_core_web_sm")
|
44 |
+
|
45 |
+
# test-to-test : chatting function -- GPT2
|
46 |
+
def chat_with_bot(user_input, chat_history_and_input=[]):
|
47 |
+
"""Text generation using GPT2"""
|
48 |
+
emb_user_input = tokenizer_gtp2.encode(
|
49 |
+
user_input + tokenizer_gtp2.eos_token, return_tensors="tf"
|
50 |
+
)
|
51 |
+
if chat_history_and_input == []:
|
52 |
+
bot_input_ids = emb_user_input # first iteration
|
53 |
+
else:
|
54 |
+
bot_input_ids = tf.concat(
|
55 |
+
[chat_history_and_input, emb_user_input], axis=-1
|
56 |
+
) # other iterations
|
57 |
+
chat_history_and_input = model_gtp2.generate(
|
58 |
+
bot_input_ids, max_length=1000, pad_token_id=tokenizer_gtp2.eos_token_id
|
59 |
+
).numpy()
|
60 |
+
# print
|
61 |
+
bot_response = tokenizer_gtp2.decode(
|
62 |
+
chat_history_and_input[:, bot_input_ids.shape[-1] :][0],
|
63 |
+
skip_special_tokens=True,
|
64 |
+
)
|
65 |
+
return bot_response, chat_history_and_input
|
66 |
+
|
67 |
+
|
68 |
+
# text-to-sentiment
|
69 |
+
def text_to_sentiment(text_input):
|
70 |
+
"""Sentiment analysis using RoBERTa"""
|
71 |
+
labels = ["anger", "joy", "optimism", "sadness"]
|
72 |
+
encoded_input = tokenizer_roberta(text_input, return_tensors="tf")
|
73 |
+
output = model_roberta(encoded_input)
|
74 |
+
scores = output[0][0].numpy()
|
75 |
+
scores = softmax(scores)
|
76 |
+
return px.histogram(x=labels, y=scores, height=200)
|
77 |
+
|
78 |
+
|
79 |
+
# text_to_semantics
|
80 |
+
def text_to_semantics(text_input):
|
81 |
+
"""NER and Dependency plot using Spacy"""
|
82 |
+
processed_text = nlp(text_input)
|
83 |
+
# Dependency
|
84 |
+
html_dep = displacy.render(
|
85 |
+
processed_text,
|
86 |
+
style="dep",
|
87 |
+
options={"compact": True, "color": "white", "bg": "light-black"},
|
88 |
+
page=False,
|
89 |
+
)
|
90 |
+
html_dep = "" + html_dep + ""
|
91 |
+
# NER
|
92 |
+
pos_tokens = []
|
93 |
+
for token in processed_text:
|
94 |
+
pos_tokens.extend([(token.text, token.pos_), (" ", None)])
|
95 |
+
# html_ner = ("" + html_ner + "")s
|
96 |
+
return pos_tokens, html_dep
|
97 |
+
|
98 |
+
|
99 |
+
# gradio interface
|
100 |
+
blocks = gr.Blocks()
|
101 |
+
with blocks:
|
102 |
+
# physical elements
|
103 |
+
session_state = gr.State([])
|
104 |
+
gr.Markdown(TITLE)
|
105 |
+
gr.Mark
|