Merge branch 'main' into Ling

Dockerfile

@@ -6,6 +6,18 @@ COPY requirements.txt .
 
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
 COPY . .
 
 CMD ["uvicorn", "src.api:app", "--host", "0.0.0.0", "--port", "7860"]

Documentation.md

@@ -16,11 +16,12 @@ Le corpus est nettoyé avant d'être utilisé pour l'entraînement du LSTM. Seul
 - LSTM réalisé à partir du <a href="https://loicgrobol.github.io//neural-networks/slides/03-transformers/transformers-slides.py.ipynb">cours</a> et de cet <a href="https://www.kaggle.com/code/columbine/seq2seq-pytorch">exemple</a> et de beaucoup d'autres référence en ligne.
 - Fine-tuned transformers modèle lancé et pré-entrainé par Google :<a href="https://huggingface.co/google/mt5-small">google/mt5-small</a>, il s'agit d'une variance du <a href="https://huggingface.co/docs/transformers/v4.16.2/en/model_doc/mt5">mT5</a>. Le model est entrainé pour notre tâche en se basant sur la documentation sur <a href="https://huggingface.co/docs/transformers/tasks/summarization">Summarisation</a> proposé par Huggingface.
 
+
 # La méthodologie
 
 ## Répartition du travail 👥
 Nous avons travaillé avec le logiciel de gestion de version Github en mettant en place une intégration continue envoyant directement les `pull request` sur l'espace Huggingface.
-<strong>'avons pas mis en place ces restrictions à cause de la difficulté à gérer Docker dans Huggingface qui nous a nécessité beaucoup de modification.
+Idéalement, les `pull request` doivent être validées par deux membres du projet avant d'être accéptées afin d'éviter les erreurs en production. Nous n'avons pas mis en place ces restrictions à cause de la difficulté à gérer Docker dans Huggingface qui nous a nécessité beaucoup de modification.
 
 ## Problèmes rencontrés et résolution
 
@@ -142,8 +143,10 @@ Pour ce faire nous nous sommes beaucoup inspirée du kaggle https://www.kaggle.c
 ## Résultats du LSTM
 
 Les résultats du LSTM sont inutilisables mais ont permis au moins de se confronter à la difficulté de mettre en place des réseaux de neurones depuis pas grand chose.
+
 On aurait aimé avoir plus de temps pour aller plus loin et comprendre mieux encore : l'entraîement par batch, pourquoi les résultats sont si mauvais, mettre d'autres stratégies de génération en place, ...
 
 ## Résultat du fine-tuning
 
 Les résumés générés ne sont pas grammaticalement corrects à 100% mais les informations importantes du texte sont bien présentes dans le résumé, et la longeur du résumé correspond bien à notre attente. Cependant les résultats d'évaluation selon ROUGE est très mauvais, malgré une amélioration de 0.007 à 0.06 pour rouge1, il n'ést plus possible d'obtenir de meilleurs scores.
+

README.md

@@ -1,3 +1,10 @@
+---
+title: SummaryProject
+sdk: docker
+app_file: src/api.py
+pinned: false
+---
+
 # Project Deep Learning - Text Summarisation tool and it's application programming interface
 
 As part of the master course "Neural Network",for this university project, our task is about creating a application, a interface or a python library in the use of NLP(Natural Language Processing) with the help of an artificial neural network system.

src/api.py

@@ -1,82 +1,162 @@
 from fastapi import FastAPI, Form, Request
 from fastapi.staticfiles import StaticFiles
 from fastapi.templating import Jinja2Templates
+import re
+
 
 from src.inference_lstm import inference_lstm
 from src.inference_t5 import inference_t5
 
 
-# ------ INFERENCE MODEL --------------------------------------------------------------
-# appel de la fonction inference, adaptee pour une entree txt
 def summarize(text: str):
-    if choisir_modele.var == "lstm":
-        return " ".join(inference_lstm(text))
-    elif choisir_modele.var == "fineTunedT5":
+    """
+    Returns the summary of an input text.
+    Parameter
+    ---------
+    text : str
+        A text to summarize.
+    Returns
+    -------
+    :str
+        The summary of the input text.
+    """
+    if global_choose_model.var == "lstm":
+        text = " ".join(inference_lstm(text))
+        return re.sub("^1|1$|<start>|<end>", "", text)
+    elif global_choose_model.var == "fineTunedT5":
         text = inference_t5(text)
-
-
-# ----------------------------------------------------------------------------------
-
-
-def choisir_modele(choixModele):
-    print("ON A RECUP LE CHOIX MODELE")
-    if choixModele == "lstm":
-        choisir_modele.var = "lstm"
-    elif choixModele == "fineTunedT5":
-        choisir_modele.var = "fineTunedT5"
-    else:
-        "le modele n'est pas defini"
-
-
-# -------- API ---------------------------------------------------------------------
+        return re.sub("<extra_id_0> ", "", text)
+    elif global_choose_model.var == "":
+        return "You have not chosen a model."
+
+
+def global_choose_model(model_choice):
+    """This function allows to connect the choice of the
+    model and the summary function by defining global variables.
+    The aime is to access a variable outside of a function."""
+    if model_choice == "lstm":
+        global_choose_model.var = "lstm"
+    elif model_choice == "fineTunedT5":
+        global_choose_model.var = "fineTunedT5"
+    elif model_choice == "  ---  ":
+        global_choose_model.var = ""
+
+
+# definition of the main elements used in the script
+model_list = [
+    {"model": "  ---  ", "name": "  ---  "},
+    {"model": "lstm", "name": "LSTM"},
+    {"model": "fineTunedT5", "name": "Fine-tuned T5"},
+]
+selected_model = "  ---  "
+model_choice = ""
+
+
+# -------- API ---------------------------------------------------------------
 app = FastAPI()
 
-# static files pour envoi du css au navigateur
+# static files to send the css
 templates = Jinja2Templates(directory="templates")
 app.mount("/templates", StaticFiles(directory="templates"), name="templates")
 
 
 @app.get("/")
 async def index(request: Request):
-    return templates.TemplateResponse("index.html.jinja", {"request": request})
+    """This function is used to create an endpoint for the
+    index page of the app."""
+    return templates.TemplateResponse(
+        "index.html.jinja",
+        {
+            "request": request,
+            "current_route": "/",
+            "model_list": model_list,
+            "selected_model": selected_model,
+        },
+    )
 
 
 @app.get("/model")
-async def index(request: Request):
-    return templates.TemplateResponse("index.html.jinja", {"request": request})
+async def get_model(request: Request):
+    """This function is used to create an endpoint for
+    the model page of the app."""
+    return templates.TemplateResponse(
+        "index.html.jinja",
+        {
+            "request": request,
+            "current_route": "/model",
+            "model_list": model_list,
+            "selected_model": selected_model,
+        },
+    )
 
 
 @app.get("/predict")
-async def index(request: Request):
-    return templates.TemplateResponse("index.html.jinja", {"request": request})
+async def get_prediction(request: Request):
+    """This function is used to create an endpoint for
+    the predict page of the app."""
+    return templates.TemplateResponse(
+        "index.html.jinja", {"request": request, "current_route": "/predict"}
+    )
 
 
 @app.post("/model")
-async def choix_model(request: Request, choixModel: str = Form(None)):
-    print(choixModel)
-    if not choixModel:
-        erreur_modele = "Merci de saisir un modèle."
+async def choose_model(request: Request, model_choice: str = Form(None)):
+    """This functions allows to retrieve the model chosen by the user. Then, it
+    can end to an error message if it not defined or it is sent to the
+    global_choose_model function which connects the user choice to the
+    use of a model."""
+    selected_model = model_choice
+    # print(selected_model)
+    if not model_choice:
+        model_error = "Please select a model."
         return templates.TemplateResponse(
-            "index.html.jinja", {"request": request, "text": erreur_modele}
+            "index.html.jinja",
+            {
+                "request": request,
+                "text": model_error,
+                "model_list": model_list,
+                "selected_model": selected_model,
+            },
         )
     else:
-        choisir_modele(choixModel)
-        print("C'est bon on utilise le modèle demandé")
-        return templates.TemplateResponse("index.html.jinja", {"request": request})
+        global_choose_model(model_choice)
+        return templates.TemplateResponse(
+            "index.html.jinja",
+            {
+                "request": request,
+                "model_list": model_list,
+                "selected_model": selected_model,
+            },
+        )
 
 
-# retourner le texte, les predictions et message d'erreur si formulaire envoye vide
 @app.post("/predict")
 async def prediction(request: Request, text: str = Form(None)):
+    """This function allows to retrieve the input text of the user.
+    Then, it can end to an error message or it can be sent to
+    the summarize function."""
     if not text:
-        error = "Merci de saisir votre texte."
+        text_error = "Please enter your text."
         return templates.TemplateResponse(
-            "index.html.jinja", {"request": request, "text": error}
+            "index.html.jinja",
+            {
+                "request": request,
+                "text": text_error,
+                "model_list": model_list,
+                "selected_model": selected_model,
+            },
         )
     else:
         summary = summarize(text)
         return templates.TemplateResponse(
-            "index.html.jinja", {"request": request, "text": text, "summary": summary}
+            "index.html.jinja",
+            {
+                "request": request,
+                "text": text,
+                "summary": summary,
+                "model_list": model_list,
+                "selected_model": selected_model,
+            },
         )
 
 

src/dataloader.py

@@ -38,8 +38,6 @@ class Data(torch.utils.data.Dataset):
         <end> tokens depending on the text_type
     get_words()
         get the dataset vocabulary
-    make_dataset()
-        create a dataset with cleaned data
     """
 
     def __init__(self, path: str, transform=None) -> None:

src/fine_tune_T5.py

@@ -159,7 +159,9 @@ if __name__ == '__main__':
     # définition de device
     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
     # faire appel au model à entrainer
-    tokenizer = AutoTokenizer.from_pretrained('google/mt5-small')
+
+    hf_token = "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"
+    tokenizer = AutoTokenizer.from_pretrained('google/mt5-small', use_auth_token=hf_token )
 
     mt5_config = AutoConfig.from_pretrained(
         "google/mt5-small",
@@ -167,6 +169,7 @@ if __name__ == '__main__':
         length_penalty=0.6,
         no_repeat_ngram_size=2,
         num_beams=15,
+        use_auth_token=hf_token
     )
 
     model = (AutoModelForSeq2SeqLM
@@ -242,7 +245,7 @@ if __name__ == '__main__':
 
     # faire appel au model en local
     model = (AutoModelForSeq2SeqLM
-             .from_pretrained("t5_summary")
+             .from_pretrained("t5_summary", use_auth_token=hf_token )
              .to(device))
 
 

src/inference_t5.py

@@ -3,6 +3,8 @@
 """
 import re
 import string
+import os
+os.environ['TRANSFORMERS_CACHE'] = './.cache'
 
 import contractions
 import torch
@@ -32,11 +34,11 @@ def inference_t5(text: str) -> str:
     # On défini les paramètres d'entrée pour le modèle
     text = clean_text(text)
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-    tokenizer = (AutoTokenizer.from_pretrained("Linggg/t5_summary",use_auth_token=True))
+    hf_token = "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"
+    tokenizer = AutoTokenizer.from_pretrained("Linggg/t5_summary", use_auth_token=hf_token )
     # load local model
     model = (AutoModelForSeq2SeqLM
-             .from_pretrained("Linggg/t5_summary",use_auth_token=True)
+             .from_pretrained("Linggg/t5_summary", use_auth_token = hf_token )
              .to(device))
 
 

templates/index.html.jinja

@@ -1,35 +1,19 @@
 <!DOCTYPE html>
-<html lang="fr">
+<html lang="en">
     <head>
         <title>Text summarization API</title>
         <meta charset="utf-8" />
 		<meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no" />
-		<link rel="stylesheet" href="{{ url_for('templates', path='templates/site_style/css/main.css') }}" />
+		<style>html, body, div, h1, h2, p, blockquote,a, code, em, img, strong, u, ul, li,label, legend, caption, tr, th, td,header, menu, nav, section, summary{margin: 0;padding: 0;border: 0;font-size: 100%;font: inherit;vertical-align: baseline}header, menu, nav, section{display: block}div{margin-bottom: 20px}body{line-height: 1}ul{list-style: none}body{-webkit-text-size-adjust: none}input::-moz-focus-inner{border: 0;padding: 0}html{box-sizing: border-box}*, *:before, *:after{box-sizing: inherit}body{color: #5b5b5b;font-size: 15pt;line-height: 1.85em;font-family: 'Source Sans Pro', sans-serif;font-weight: 300;background-image: url("templates/site_style/images/background.jpg");background-size: cover;background-position: center center;background-attachment: fixed}h1, h2, h3{font-weight: 400;color: #483949;line-height: 1.25em}h1 a, h2 a, h3 a{color: inherit;text-decoration: none;border-bottom-color: transparent}h1 strong, h2 strong, h3 strong{font-weight: 600}h2{font-size: 2.85em}h3{font-size: 1.25em}strong, b{font-weight: 400;color: #483949}em, i{font-style: italic}a{color: inherit;border-bottom: solid 1px rgba(128, 128, 128, 0.15);text-decoration: none;-moz-transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out;-webkit-transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out;-ms-transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out;transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out}a:hover{color: #ef8376;border-bottom-color: transparent}p, ul{margin-bottom: 1em}p{text-align: justify}hr{position: relative;display: block;border: 0;top: 4.5em;margin-bottom: 9em;height: 6px;border-top: solid 1px rgba(128, 128, 128, 0.2);border-bottom: solid 1px rgba(128, 128, 128, 0.2)}hr:before, hr:after{content: '';position: absolute;top: -8px;display: block;width: 1px;height: 21px;background: rgba(128, 128, 128, 0.2)}hr:before{left: -1px}hr:after{right: -1px}ul{list-style: disc;padding-left: 1em}ul li{padding-left: 0.5em;font-size: 85%;list-style: none}textarea{border-radius: 10px;resize: none;padding: 10px;line-height: 20px;word-spacing: 1px;font-size: 16px;width: 85%;height: 100%}::-webkit-input-placeholder{font-size: 17px;word-spacing: 1px}table{width: 100%}table.default{width: 100%}table.default tbody tr:first-child{border-top: 0}table.default tbody tr:nth-child(2n 1){background: #fafafa}table.default th{text-align: left;font-weight: 400;padding: 0.5em 1em 0.5em 1em}input[type="button"],input[type="submit"],input[type="reset"],button,.button{position: relative;display: inline-block;background: #df7366;color: #fff;text-align: center;border-radius: 0.5em;text-decoration: none;padding: 0.65em 3em 0.65em 3em;border: 0;cursor: pointer;outline: 0;font-weight: 300;-moz-transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out;-webkit-transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out;-ms-transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out;transition: background-color 0.35s ease-in-out, color 0.35s ease-in-out, border-bottom-color 0.35s ease-in-out}input[type="button"]:hover,input[type="submit"]:hover,input[type="reset"]:hover,button:hover,.button:hover{color: #fff;background: #ef8376}input[type="button"].alt,input[type="submit"].alt,input[type="reset"].alt,button.alt,.button.alt{background: #2B252C}input[type="button"].alt:hover,input[type="submit"].alt:hover,input[type="reset"].alt:hover,button.alt:hover,.button.alt:hover{background: #3B353C}#header{position: relative;background-size: cover;background-position: center center;background-attachment: fixed;color: #fff;text-align: center;padding: 5em 0 2em 0;cursor: default;height: 100%}#header:before{content: '';display: inline-block;vertical-align: middle;height: 100%}#header .inner{position: relative;z-index: 1;margin: 0;display: inline-block;vertical-align: middle}#header header{display: inline-block}#header header > p{font-size: 1.25em;margin: 0}#header h1{color: #fff;font-size: 3em;line-height: 1em}#header h1 a{color: inherit}#header .button{display: inline-block;border-radius: 100%;width: 4.5em;height: 4.5em;line-height: 4.5em;text-align: center;font-size: 1.25em;padding: 0}#header hr{top: 1.5em;margin-bottom: 3em;border-bottom-color: rgba(192, 192, 192, 0.35);box-shadow: inset 0 1px 0 0 rgba(192, 192, 192, 0.35)}#header hr:before, #header hr:after{background: rgba(192, 192, 192, 0.35)}#nav{position: absolute;top: 0;left: 0;width: 100%;text-align: center;padding: 1.5em 0 1.5em 0;z-index: 1;overflow: hidden}#nav > hr{top: 0.5em;margin-bottom: 6em}.copyright{margin-top: 50px}@media screen and (max-width: 1680px){body, input, select{font-size: 14pt;line-height: 1.75em}}@media screen and (max-width: 1280px){body, input, select{font-size: 12pt;line-height: 1.5em}#header{background-attachment: scroll}#header .inner{padding-left: 2em;padding-right: 2em}}@media screen and (max-width: 840px){body, input, select{font-size: 13pt;line-height: 1.65em}}#navPanel, #titleBar{display: none}@media screen and (max-width: 736px){html, body{overflow-x: hidden}body, input, select{font-size: 12.5pt;line-height: 1.5em}h2{font-size: 1.75em}h3{font-size: 1.25em}hr{top: 3em;margin-bottom: 6em}#header{background-attachment: scroll;padding: 2.5em 0 0 0}#header .inner{padding-top: 1.5em;padding-left: 1em;padding-right: 1em}#header header > p{font-size: 1em}#header h1{font-size: 1.75em}#header hr{top: 1em;margin-bottom: 2.5em}#nav{display: none}#main > header{text-align: center}div.copyright{margin-top: 10px}label, textarea{font-size: 0.8rem;letter-spacing: 1px;font-family: Georgia, 'Times New Roman', Times, serif}.buttons{display: flex;flex-direction: row;justify-content: center;margin-top: 20px}}
+        </style>
         <script>
             function customReset()
             {
-                document.getElementById("my_form").value = "";
+                document.getElementById("text_form").value = "";
                 document.getElementById("text").value = "";
                 document.getElementById("summary").value = "";
             }
         </script>
-        <script>
-        function submitBothForms()
-            {
-            document.getElementById("my_form").submit();
-            document.getElementById("choixModel").submit();
-            }
-        </script>
-        <script>
-            function getValue() {
-                var e = document.getElementById("choixModel");
-                var value = e.value;
-                var text = e.options[e.selectedIndex].text;
-                return text}
-        </script>
-        <script type="text/javascript">
-            document.getElementById('choixModel').value = "<?php echo $_GET['choixModel'];?>";
-        </script>
     </head>
     <body>
         <div id="header">
@@ -44,22 +28,29 @@
             <hr/>
             </nav>
 
-            <div class="choixModel">
-                <form id="choixModel" method="post" action="/model">
+            <div class="model_choice">
+                <form id="model_choice" method="post" action="/model">
                     <label for="selectModel">Choose a model :</label>
-                    <select name="choixModel" class="selectModel" id="choixModel">
-                        <option value="lstm">LSTM</option>
-                        <option value="fineTunedT5">Fine-tuned T5</option>
+                    <select name="model_choice" class="selectModel" id="model_choice">
+                        <!--A for jinja loop to retrieve option buttons from the api
+                        and to keep them selected when a choice is made. -->
+                        {% for x in model_list %}
+                            {%if selected_model == x.model%}
+                                <option value="{{x.model}}" selected>{{x.name}}</option>
+                            {%else%}
+                                <option value="{{x.model}}">{{x.name}}</option>
+                            {%endif%}
+                        {%endfor%}
                     </select>
                 </form>
-                <button form ="choixModel" class='search_bn' type="submit" class="btn btn-primary btn-block btn-large" rows="1" cols="50">Select model</button>
+                <button form ="model_choice" class='search_bn' type="submit" class="btn btn-primary btn-block btn-large" rows="1" cols="50">Select model</button>
             </div>
 
             <div>
                 <table>
                     <tr>
                         <td>
-                            <form id = "my_form" action="/predict"  method="post" class="formulaire">
+                            <form id = "text_form" action="/predict"  method="post" class="formulaire">
                                 <textarea id="text" name="text" placeholder="Enter your text here!" rows="15" cols="75">{{text}}</textarea>
                                 <input type="hidden" name="textarea_value" value="{{ text }}">
                             </form>
@@ -71,9 +62,13 @@
                 </table>
             </div>
             <div class="buttons">
-                <!-- <button id="submit" type="submit" onclick=submitBothForms()>SUBMIT</button> -->
-                <button form ="my_form" class='search_bn' type="submit" class="btn btn-primary btn-block btn-large" rows="1" cols="50">Go !</button>
-                <button form ="my_form" type="button" value="Reset" onclick="customReset();">Reset</button>
+                <!--A if loop to disable Go and Reset button for the index page.-->
+                {% if current_route == "/" %}
+                <button>Please select a model</button>
+                {% else %}
+                <button form ="text_form" class='search_bn' type="submit" class="btn btn-primary btn-block btn-large" rows="1" cols="50">Go !</button>
+                <button form ="text_form" type="button" value="Reset" onclick="customReset();">Reset</button>
+                {% endif %}
             </div>
 
             <div class="copyright">
@@ -81,7 +76,7 @@
                         <li>&copy; Untitled. All rights reserved.</li>
                     </ul>
                     <ul>
-                        <li>Projet mené dans le cadre des cours du master 2 TAL (Traitement Automatique des Langues)</li>
+                        <li>University project as part of the NLP (Natural Language Processing) Master's program</li>
                         <li>Lingyun GAO -- Estelle SALMON -- Eve SAUVAGE</li>
                     </ul>
             </div>

templates/site_style/css/main.css

@@ -246,6 +246,7 @@ textarea {
 				background: #3B353C;
 			}
 
+
 /* Header */
 
 	#header {
@@ -469,4 +470,5 @@ textarea {
 		justify-content: center;
 		margin-top: 20px;
 	  }
+
 	}