Duplicate from os1187/gpt2-chatbot

Co-authored-by: Oleg Seifert <os1187@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+.env
+.git*

Pipfile

@@ -0,0 +1,178 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+gradio = "==3.10.1"
+tensorflow = "==2.11.0"
+transformers = "==4.24.0"
+absl-py = "==1.3.0"
+aiohttp = "==3.8.3"
+aiosignal = "==1.3.1"
+antlr4-python3-runtime = "==4.8"
+anyio = "==3.6.2"
+appdirs = "==1.4.4"
+astunparse = "==1.6.3"
+async-timeout = "==4.0.2"
+attrs = "==22.1.0"
+audioread = "==3.0.0"
+autoflake = "==2.0.0"
+bcrypt = "==4.0.1"
+bitarray = "==2.6.0"
+blis = "==0.7.9"
+cachetools = "==5.2.0"
+catalogue = "==2.0.8"
+certifi = "==2022.9.24"
+cffi = "==1.15.1"
+charset-normalizer = "==2.1.1"
+ci-sdr = "==0.0.2"
+click = "==8.1.3"
+colorama = "==0.4.6"
+confection = "==0.0.3"
+configargparse = "==1.5.3"
+contourpy = "==1.0.6"
+cryptography = "==38.0.3"
+ctc-segmentation = "==1.7.4"
+cycler = "==0.11.0"
+cymem = "==2.0.7"
+cython = "==0.29.32"
+decorator = "==5.1.1"
+distance = "==0.1.3"
+einops = "==0.6.0"
+en-core-web-sm = {file = "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1-py3-none-any.whl"}
+espnet = "==202209"
+espnet-tts-frontend = "==0.0.3"
+fairseq = "==0.12.2"
+fast-bss-eval = "==0.1.3"
+fastapi = "==0.76.0"
+ffmpy = "==0.3.0"
+filelock = "==3.8.0"
+flatbuffers = "==22.10.26"
+fonttools = "==4.38.0"
+frozenlist = "==1.3.3"
+fsspec = "==2022.11.0"
+g2p-en = "==2.1.0"
+gast = "==0.4.0"
+google-auth = "==2.14.1"
+google-auth-oauthlib = "==0.4.6"
+google-pasta = "==0.2.0"
+grpcio = "==1.34.1"
+h11 = "==0.12.0"
+h5py = "==3.1.0"
+httpcore = "==0.15.0"
+httpx = "==0.23.1"
+huggingface-hub = "==0.11.0"
+humanfriendly = "==10.0"
+hydra-core = "==1.0.7"
+idna = "==3.4"
+importlib-metadata = "==4.13.0"
+inflect = "==6.0.2"
+jaconv = "==0.3"
+jamo = "==0.4.1"
+jinja2 = "==3.1.2"
+joblib = "==1.2.0"
+kaldiio = "==2.17.2"
+keras = "==2.11.0"
+keras-nightly = "==2.5.0.dev2021032900"
+keras-preprocessing = "==1.1.2"
+kiwisolver = "==1.4.4"
+langcodes = "==3.3.0"
+libclang = "==14.0.6"
+librosa = "==0.9.2"
+linkify-it-py = "==1.0.3"
+llvmlite = "==0.39.1"
+lxml = "==4.9.1"
+markdown = "==3.4.1"
+markdown-it-py = "==2.1.0"
+markupsafe = "==2.1.1"
+matplotlib = "==3.6.2"
+mdit-py-plugins = "==0.3.1"
+mdurl = "==0.1.2"
+multidict = "==6.0.2"
+murmurhash = "==1.0.9"
+nltk = "==3.7"
+numba = "==0.56.4"
+numpy = "==1.23.5"
+oauthlib = "==3.2.2"
+omegaconf = "==2.0.6"
+opt-einsum = "==3.3.0"
+orjson = "==3.8.2"
+pandas = "==1.4.4"
+paramiko = "==2.12.0"
+pathy = "==0.10.0"
+pillow = "==9.3.0"
+plotly = "==5.11.0"
+pooch = "==1.6.0"
+portalocker = "==2.6.0"
+preshed = "==3.0.8"
+protobuf = "==3.19.6"
+pyasn1 = "==0.4.8"
+pyasn1-modules = "==0.2.8"
+pycparser = "==2.21"
+pycryptodome = "==3.15.0"
+pydantic = "==1.9.2"
+pydub = "==0.25.1"
+pyflakes = "==3.0.1"
+pynacl = "==1.5.0"
+pyparsing = "==3.0.9"
+pypinyin = "==0.44.0"
+python-dateutil = "==2.8.2"
+python-multipart = "==0.0.5"
+pytorch-wpe = "==0.0.1"
+pytz = "==2022.6"
+pyworld = "==0.3.2"
+pyyaml = "==6.0"
+regex = "==2022.10.31"
+requests = "==2.28.1"
+requests-oauthlib = "==1.3.1"
+resampy = "==0.4.2"
+rfc3986 = "==1.5.0"
+rsa = "==4.9"
+sacrebleu = "==2.3.1"
+scikit-learn = "==1.1.3"
+scipy = "==1.9.3"
+sentencepiece = "==0.1.97"
+six = "==1.15.0"
+smart-open = "==5.2.1"
+sniffio = "==1.3.0"
+soundfile = "==0.11.0"
+spacy = "==3.4.3"
+spacy-legacy = "==3.0.10"
+spacy-loggers = "==1.0.3"
+srsly = "==2.4.5"
+starlette = "==0.18.0"
+tabulate = "==0.9.0"
+tenacity = "==8.1.0"
+tensorboard = "==2.11.0"
+tensorboard-data-server = "==0.6.1"
+tensorboard-plugin-wit = "==1.8.1"
+tensorflow-estimator = "==2.11.0"
+tensorflow-io-gcs-filesystem = "==0.28.0"
+termcolor = "==1.1.0"
+thinc = "==8.1.5"
+threadpoolctl = "==3.1.0"
+tokenizers = "==0.13.2"
+tomli = "==2.0.1"
+torch = "==1.13.0"
+torch-complex = "==0.4.3"
+torchaudio = "==0.13.0"
+tqdm = "==4.64.1"
+typeguard = "==2.13.3"
+typer = "==0.7.0"
+typing-extensions = "==4.4.0"
+uc-micro-py = "==1.0.1"
+unidecode = "==1.3.6"
+urllib3 = "==1.26.12"
+uvicorn = "==0.20.0"
+wasabi = "==0.10.1"
+websockets = "==10.4"
+werkzeug = "==2.2.2"
+wrapt = "==1.12.1"
+yarl = "==1.8.1"
+zipp = "==3.10.0"
+
+[dev-packages]
+
+[requires]
+python_version = "3.9"

README.md

@@ -0,0 +1,14 @@
+---
+title: Funny Chatbot
+emoji: 🌖
+colorFrom: yellow
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.9.1
+app_file: app.py
+pinned: false
+license: cc-by-nc-sa-4.0
+duplicated_from: os1187/gpt2-chatbot
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,139 @@
+from transformers import TFAutoModelForCausalLM, AutoTokenizer
+import tensorflow as tf
+import gradio as gr
+import spacy
+from spacy import displacy
+from transformers import TFAutoModelForSequenceClassification
+from transformers import AutoTokenizer
+from scipy.special import softmax
+import plotly.express as px
+import plotly.io as pio
+
+# configuration params
+pio.templates.default = "plotly_dark"
+
+# setting up the text in the page
+TITLE = "<center><h1>Talk with an AI</h1></center>"
+DESCRIPTION = r"""<center>This application allows you to talk with a machine/robot with state-of-the-art technology!!<br>
+                 In the back-end is using the GPT2 model from OpenAI. One of the best models in text generation and comprehension.<br>
+                 Language processing is done using RoBERTa for sentiment-analysis and spaCy for named-entity recognition and dependency plotting.<br>
+                 The AI thinks he is a human, so please treat him as such, else he migh get angry!<br>
+                 """
+EXAMPLES = [
+    ["What is your favorite videogame?"],
+    ["What gets you really sad?"],
+    ["How can I make you really angry? "],
+    ["What do you do for work?"],
+    ["What are your hobbies?"],
+    ["What is your favorite food?"],
+]
+ARTICLE = r"""<center>
+              Done by dr. Gabriel Lopez<br>
+              For more please visit: <a href='https://sites.google.com/view/dr-gabriel-lopez/home'>My Page</a><br>
+              For info about the chat-bot model can also see the <a href="https://arxiv.org/abs/1911.00536">ArXiv paper</a><br>
+              </center>"""
+
+# Loading necessary NLP models
+# dialog
+checkpoint = "microsoft/DialoGPT-medium"  # tf
+model_gtp2 = TFAutoModelForCausalLM.from_pretrained(checkpoint)
+tokenizer_gtp2 = AutoTokenizer.from_pretrained(checkpoint)
+# sentiment
+checkpoint = f"cardiffnlp/twitter-roberta-base-emotion"
+model_roberta = TFAutoModelForSequenceClassification.from_pretrained(checkpoint)
+tokenizer_roberta = AutoTokenizer.from_pretrained(checkpoint)
+# NER & Dependency
+nlp = spacy.load("en_core_web_sm")
+
+# test-to-test : chatting function -- GPT2
+def chat_with_bot(user_input, chat_history_and_input=[]):
+    """Text generation using GPT2"""
+    emb_user_input = tokenizer_gtp2.encode(
+        user_input + tokenizer_gtp2.eos_token, return_tensors="tf"
+    )
+    if chat_history_and_input == []:
+        bot_input_ids = emb_user_input  # first iteration
+    else:
+        bot_input_ids = tf.concat(
+            [chat_history_and_input, emb_user_input], axis=-1
+        )  # other iterations
+    chat_history_and_input = model_gtp2.generate(
+        bot_input_ids, max_length=1000, pad_token_id=tokenizer_gtp2.eos_token_id
+    ).numpy()
+    # print
+    bot_response = tokenizer_gtp2.decode(
+        chat_history_and_input[:, bot_input_ids.shape[-1] :][0],
+        skip_special_tokens=True,
+    )
+    return bot_response, chat_history_and_input
+
+
+# text-to-sentiment
+def text_to_sentiment(text_input):
+    """Sentiment analysis using RoBERTa"""
+    labels = ["anger", "joy", "optimism", "sadness"]
+    encoded_input = tokenizer_roberta(text_input, return_tensors="tf")
+    output = model_roberta(encoded_input)
+    scores = output[0][0].numpy()
+    scores = softmax(scores)
+    return px.histogram(x=labels, y=scores, height=200)
+
+
+# text_to_semantics
+def text_to_semantics(text_input):
+    """NER and Dependency plot using Spacy"""
+    processed_text = nlp(text_input)
+    # Dependency
+    html_dep = displacy.render(
+        processed_text,
+        style="dep",
+        options={"compact": True, "color": "white", "bg": "light-black"},
+        page=False,
+    )
+    html_dep = "" + html_dep + ""
+    # NER
+    pos_tokens = []
+    for token in processed_text:
+        pos_tokens.extend([(token.text, token.pos_), (" ", None)])
+    # html_ner = ("" + html_ner + "")s
+    return pos_tokens, html_dep
+
+
+# gradio interface
+blocks = gr.Blocks()
+with blocks:
+    # physical elements
+    session_state = gr.State([])
+    gr.Markdown(TITLE)
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+        with gr.Column():
+            in_text = gr.Textbox(value="How was the class?", label="Start chatting!")
+            submit_button = gr.Button("Submit")
+            gr.Examples(inputs=in_text, examples=EXAMPLES)
+        with gr.Column():
+            response_text = gr.Textbox(value="", label="GPT2 response:")
+            sentiment_plot = gr.Plot(
+                label="How is GPT2 feeling about your conversation?:", visible=True
+            )
+            ner_response = gr.Highlight(
+                label="Named Entity Recognition (NER) over response"
+            )
+            dependency_plot = gr.HTML(label="Dependency plot of response")
+    gr.Markdown(ARTICLE)
+    # event listeners
+    submit_button.click(
+        inputs=[in_text, session_state],
+        outputs=[response_text, session_state],
+        fn=chat_with_bot,
+    )
+    response_text.change(
+        inputs=response_text, outputs=sentiment_plot, fn=text_to_sentiment
+    )
+    response_text.change(
+        inputs=response_text,
+        outputs=[ner_response, dependency_plot],
+        fn=text_to_semantics,
+    )
+
+blocks.launch()

requirements.txt

@@ -0,0 +1,9 @@
+gradio==3.12.0
+plotly==5.11.0
+scipy==1.5.4
+spacy==3.4.3
+tensorflow==2.5.0
+transformers==4.24.0
+
+# spacy internal nlp model
+https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1.tar.gz