Revert "test"

This reverts commit 40d04abcae75d05d2a6b787d31dcc68c8828ef6f.

Dockerfile

@@ -1,13 +0,0 @@
-FROM python:3.8
-
-WORKDIR /workspace
-
-ADD . /workspace
-
-RUN pip install -r requirements.txt
-
-CMD [ "python" , "/workspace/app.py" ]
-
-RUN chown -R 42420:42420 /workspace
-
-ENV HOME=/workspace

README.md

@@ -1,231 +1,13 @@
-# AI Deploy - Tutorial - Deploy an app for sentiment analysis with Hugging Face and Flask
-
-> **Note** Access to the full documentation [here](https://docs.ovh.com/gb/en/publiccloud/ai/deploy/tuto-flask-hugging-face-sentiment-analysis/).
-
-**Last updated 3rd November, 2022.**
-
-> **Note**
-> AI Deploy is in `beta`. During the beta-testing phase, the infrastructure’s availability and data longevity are not guaranteed. Please do not use this service for applications that are in production, as this phase is not complete.
->
-> AI Deploy is covered by **[OVHcloud Public Cloud Special Conditions](https://storage.gra.cloud.ovh.net/v1/AUTH_325716a587c64897acbef9a4a4726e38/contracts/d2a208c-Conditions_particulieres_OVH_Stack-WE-9.0.pdf)**.
->
-
-## Objective
-
-The purpose of this tutorial is to show you how to deploy a web service for sentiment analysis on text using Hugging Face pretrained models.<br>
-In order to do this, you will use Flask, an open-source micro framework for web development in Python. You will also learn how to build and use a custom Docker image for a Flask application.
-
-Overview of the app:
-
-![Hugging Face Overview](images/flask-hugging-face-overview.png){.thumbnail}
-
-For more information about Hugging Face, please visit <https://huggingface.co/>.
-
-## Requirements
-
-- Access to the [OVHcloud Control Panel](https://www.ovh.com/auth/?action=gotomanager&from=https://www.ovh.co.uk/&ovhSubsidiary=GB);
-- An AI Deploy project created inside a [Public Cloud project](https://www.ovhcloud.com/en-gb/public-cloud/) in your OVHcloud account;
-- A [user for AI Deploy](https://docs.ovh.com/gb/en/publiccloud/ai/users/);
-- [Docker](https://www.docker.com/get-started) installed on your local computer;
-- Some knowledge about building image and [Dockerfile](https://docs.docker.com/engine/reference/builder/);
-
-We also suggest you do some tests to find out which [Hugging Face model](https://huggingface.co/models) is right for your use case. Find examples on our [GitHub repository](https://github.com/ovh/ai-training-examples/tree/main/notebooks/natural-language-processing/text-classification/hugging-face/sentiment-analysis-twitter).
-
-## Instructions
-
-First, the tree structure of your folder should be as follows:
-
-![Flask tree structure](images/tree-flask-app.png)
-
-Find more information about the Flask application [here](https://flask.palletsprojects.com/en/2.0.x/quickstart/#a-minimal-application) to get ready to use it.
-
-### Write the Flask application
-
-Create a Python file named `app.py`.
-
-Inside that file, import your required modules:
-
-```python
-from flask import Flask, jsonify, render_template, request, make_response
-import transformers
-```
-
-Create Flask app:
-
-```python
-app = Flask(__name__)
-```
-
-Load Hugging Face models:
-
-```python
-# create a python dictionary for your models d = {<key>: <value>, <key>: <value>, ..., <key>: <value>}
-dictOfModels = {"RoBERTa" : transformers.pipeline("sentiment-analysis", model="siebert/sentiment-roberta-large-english"), "BERT" : transformers.pipeline('sentiment-analysis', model="nlptown/bert-base-multilingual-uncased-sentiment")}
-# create a list of keys to use them in the select part of the html code
-listOfKeys = []
-for key in dictOfModels :
-        listOfKeys.append(key)
-```
-
-Write the inference function:
-
-```python
-def get_prediction(message,model):
-    # inference
-    results = model(message)  
-    return results
-```
-
-Define the GET method:
-
-```python
-@app.route('/', methods=['GET'])
-def get():
-    # in the select we will have each key of the list in option
-    return render_template("home.html", len = len(listOfKeys), listOfKeys = listOfKeys)
-```
-
-Define the POST method:
-
-```python
-@app.route('/', methods=['POST'])
-def predict():
-    message = request.form['message']
-    # choice of the model
-    results = get_prediction(message, dictOfModels[request.form.get("model_choice")])
-    print(f'User selected model : {request.form.get("model_choice")}')
-    my_prediction = f'The feeling of this text is {results[0]["label"]} with probability of {results[0]["score"]*100}%.'
-    return render_template('result.html', text = f'{message}', prediction = my_prediction)
-```
-
-Start your app:
-
-```python
-if __name__ == '__main__':
-    # starting app
-    app.run(debug=True,host='0.0.0.0')
-```
-
-### Write the requirements.txt file for the application
-
-The `requirements.txt` file will allow us to write all the modules needed to make our application work. This file will be useful when writing the `Dockerfile`.
-
-```console
-Flask==1.1.2
-transformers==4.4.2
-torch==1.6.0
-```
-
-Here we will mainly discuss how to write the `app.py` code, the `requirements.txt` file and the `Dockerfile`. If you want to see the whole code, please refer to the [GitHub repository](https://github.com/ovh/ai-training-examples/tree/main/apps/flask/sentiment-analysis-hugging-face-app).
-
-### Write the Dockerfile for the application
-
-Your `Dockerfile` should start with the `FROM` instruction indicating the parent image to use. In our case we choose to start from a Python image:
-
-```console
-FROM python:3.8
-```
-
-Create the home directory and add your files to it:
-
-```console
-WORKDIR /workspace
-ADD . /workspace
-```
-
-Install the `requirements.txt` file which contains your needed Python modules using a `pip install ...` command:
-
-```console
-RUN pip install -r requirements.txt
-```
-
-Define your default launching command to start the application:
-
-```console
-CMD [ "python" , "/workspace/app.py" ]
-```
-
-Give correct access rights to **ovhcloud user** (`42420:42420`):
-
-```console
-RUN chown -R 42420:42420 /workspace
-ENV HOME=/workspace
-```
-
-### Build the Docker image from the Dockerfile
-
-Launch the following command from the **Dockerfile** directory to build your application image:
-
-```console
-docker build . -t sentiment_analysis_app:latest
-```
-
-> **Note**
-> The dot `.` argument indicates that your build context (place of the **Dockerfile** and other needed files) is the current directory.
->
-> The `-t` argument allows you to choose the identifier to give to your image. Usually image identifiers are composed of a **name** and a **version tag** `<name>:<version>`. For this example we chose **sentiment_analysis_app:latest**.
->
-
-### Test it locally (optional)
-
-Launch the following **Docker command** to launch your application locally on your computer:
-
-```console
-docker run --rm -it -p 5000:5000 --user=42420:42420 sentiment_analysis_app:latest
-```
-
-> **Note**
-> The `-p 5000:5000` argument indicates that you want to execute a port redirection from the port **5000** of your local machine into the port **5000** of the Docker container. The port **5000** is the default port used by **Flask** applications.
->
-
-> **Warning**
-> Don't forget the `--user=42420:42420` argument if you want to simulate the exact same behaviour that will occur on **AI Deploy apps**. It executes the Docker container as the specific OVHcloud user (user **42420:42420**).
->
-
-Once started, your application should be available on `http://localhost:5000`.
-
-### Push the image into the shared registry
-
-> **Warning**
-> The shared registry of AI Deploy should only be used for testing purposes. Please consider attaching your own Docker registry. More information about this can be found [here](https://docs.ovh.com/gb/en/publiccloud/ai/training/add-private-registry/).
->
-
-Find the adress of your shared registry by launching this command:
-
-```console
-ovhai registry list
-```
-
-Login on the shared registry with your usual OpenStack credentials:
-
-```console
-docker login -u <user> -p <password> <shared-registry-address>
-```
-
-Push the compiled image into the shared registry:
-
-```console
-docker tag sentiment_analysis_app:latest <shared-registry-address>/sentiment_analysis_app:latest
-docker push <shared-registry-address>/sentiment_analysis_app:latest
-```
-
-### Launch the AI Deploy app
-
-The following command starts a new app running your Flask application:
-
-```console
-ovhai app run --default-http-port 5000 --cpu 4 <shared-registry-address>/sentiment_analysis_app:latest
-```
-
-> **Note**
-> `--default-http-port 5000` indicates that the port to reach on the app URL is the `5000`.
->
-> `--cpu 4` indicates that we request 4 CPUs for that app.
->
-> Consider adding the `--unsecure-http` attribute if you want your application to be reachable without any authentication.
->
-
-## Go further
-
-- You can also imagine deploying an Object Detection model with **Flask** in this [tutorial](https://docs.ovh.com/gb/en/publiccloud/ai/deploy/web-service-yolov5/).
-- Discover an other tool to deploy easily AI models: **Gradio**. Refer to this [documentation](https://docs.ovh.com/gb/en/publiccloud/ai/deploy/tuto-gradio-sketch-recognition/).
+---
+title: Journal
+emoji: 💬
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 5.0.1
+app_file: app.py
+pinned: false
+short_description: Journal App
+---
+
+An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,42 +1,61 @@
-# import objects from the Flask model
-from flask import Flask, jsonify, render_template, request, make_response
-import transformers
+from flask import Flask, request, jsonify
+from huggingface_hub import InferenceClient
 
-# creating flask app
+# Initialize Flask app and Hugging Face client
 app = Flask(__name__)
-
-# create a python dictionary for your models d = {<key>: <value>, <key>: <value>, ..., <key>: <value>}
-dictOfModels = {"BERT" : transformers.pipeline('sentiment-analysis', model="nlptown/bert-base-multilingual-uncased-sentiment")} # feel free to add several models
-
-listOfKeys = []
-for key in dictOfModels :
-        listOfKeys.append(key) 
-
-# inference fonction
-def get_prediction(message,model):
-    # inference
-    results = model(message)  
-    return results
-
-# get method
-@app.route('/', methods=['GET'])
-def get():
-    # in the select we will have each key of the list in option
-    return render_template("home.html", len = len(listOfKeys), listOfKeys = listOfKeys)
-
-
-# post method
-@app.route('/', methods=['POST'])
-def predict():
-    message = request.form['message']
-    
-    # choice of the model
-    results = get_prediction(message, dictOfModels[request.form.get("model_choice")])
-    print(f'User selected model : {request.form.get("model_choice")}')
-    my_prediction = f'The feeling of this text is {results[0]["label"]} with probability of {results[0]["score"]*100}%.'
- 
-    return render_template('result.html', text = f'{message}', prediction = my_prediction)
-
-if __name__ == '__main__':
-    # starting app
-    app.run(debug=True,host='0.0.0.0')
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# Helper function to generate a response from the AI model
+def generate_response(message, history, system_message, max_tokens, temperature, top_p):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+    response = ""
+
+    # Streaming response from the Hugging Face model
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+        response += token
+
+    return response
+
+@app.route("/chat", methods=["POST"])
+def home():
+    return "Hi!"
+# API endpoint to handle requests
+@app.route("/chat", methods=["POST"])
+def chat():
+    try:
+        data = request.json
+        message = data.get("message", "")
+        history = data.get("history", [])
+        system_message = data.get("system_message", "You are a friendly chatbot.")
+        max_tokens = data.get("max_tokens", 512)
+        temperature = data.get("temperature", 0.7)
+        top_p = data.get("top_p", 0.95)
+
+        # Validate inputs
+        if not isinstance(history, list) or not all(isinstance(pair, list) for pair in history):
+            return jsonify({"error": "Invalid history format. It should be a list of [message, response] pairs."}), 400
+
+        # Generate AI response
+        response = generate_response(message, history, system_message, max_tokens, temperature, top_p)
+
+        return jsonify({"response": response})
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+if __name__ == "__main__":
+    app.run(debug=True)

requirements.txt

@@ -1,5 +1,2 @@
-Flask==2.1.0
-
-transformers==4.24.0
-
-torch==1.6.0
+huggingface_hub==0.25.2
+flask==3.1.0

static/style.css

@@ -1,33 +0,0 @@
-html,
-body {
-  height: 100%;
-}
-
-body {
-  text-align: left;
-  margin: 0px;
-  padding: 0px;
-  background-color: #ffffff;
-}
-
-form {
-  text-align: left;
-  height: 100%;
-}
-
-.container {
-  padding: 10px;
-}
-
-.text_bottom {
-  bottom: 0;
-}
-
-#demo {
-  color: #111;
-  font-family: 'Helvetica Neue', sans-serif;
-  font-size: 22px;
-  line-height: 24px;
-  margin: 0 0 24px;
-  text-justify: inter-word;
-}

templates/home.html

@@ -1,49 +0,0 @@
-<!doctype html>
-<html lang="en">
-	<head>
-		<meta charset="utf-8">
-		<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
-		<link rel="stylesheet" href="//stackpath.bootstrapcdn.com/bootstrap/4.2.1/css/bootstrap.min.css" integrity="sha384-GJzZqFGwb1QTTN6wy59ffF1BuGJpLSa9DkKMp0DgiMDm4iYMj70gZWKYbI706tWS" crossorigin="anonymous">
-		<style>
-			.bd-placeholder-img {
-				font-size: 1.125rem;
-				text-anchor: start;
-			}
-
-			@media (min-width: 768px) {
-				.bd-placeholder-img-lg {
-					font-size: 150%;
-				}
-			}
-		</style>
-		<link rel="stylesheet" href="/static/style.css">
-		<title>Sentiment analysis on Tweets using Hugging Face</title>
-	</head>
-	<body>
-		<form method=post enctype=multipart/form-data>
-			<img src="static/flag.png" width="100%">
-			<div style="height:80px"></div>
-			<div class="container">
-				<h3 style= "color:#030d9b"><i>OVHcloud - Sentiment analysis on Tweets using Hugging Face</i></h3>
-				<hr>
-				<div style="height:50px"></div>
-				<h5>Write your text (in english): </h5>
-				<textarea name="message" rows="4" cols="50"></textarea>
-				<br/>
-				<div style= "height:40px"></div>
-				<h5>Select Hugging Face model: </h5>
-				<select name="model_choice">
-				{%for i in range(0, len)%}
-			  		<option>{{listOfKeys[i]}}</option>
-				{%endfor%}
-				</select>
-				<div style= "height:50px"></div>
-				<button class="btn btn-lg btn-primary btn-block" type="submit">Submit</button>
-				<div style= "height:100px"></div>
-				<p align="center">If you want to know more about AI Training, go <a href="https://www.ovhcloud.com/fr/public-cloud/ai-training/">here</a>.</p>
-    </form>
-		<script src="//code.jquery.com/jquery-3.3.1.slim.min.js" integrity="sha384-q8i/X+965DzO0rT7abK41JStQIAqVgRVzpbzo5smXKp4YfRvH+8abtTE1Pi6jizo" crossorigin="anonymous"></script>
-		<script src="//cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.6/umd/popper.min.js" integrity="sha384-wHAiFfRlMFy6i5SRaxvfOCifBUQy1xHdJ/yoi7FRNXMRBu5WHdZYu1hA6ZOblgut" crossorigin="anonymous"></script>
-		<script src="//stackpath.bootstrapcdn.com/bootstrap/4.2.1/js/bootstrap.min.js" integrity="sha384-B0UglyR+jN6CkvvICOB2joaf5I4l3gm9GU6Hc1og6Ls7i6U/mkkaduKaBhlAXv9k" crossorigin="anonymous"></script>
-	</body>
-</html>

templates/result.html

@@ -1,43 +0,0 @@
-<!doctype html>
-<html lang="en">
-	<head>
-		<meta charset="utf-8">
-		<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
-		<link rel="stylesheet" href="//stackpath.bootstrapcdn.com/bootstrap/4.2.1/css/bootstrap.min.css" integrity="sha384-GJzZqFGwb1QTTN6wy59ffF1BuGJpLSa9DkKMp0DgiMDm4iYMj70gZWKYbI706tWS" crossorigin="anonymous">
-		<style>
-			.bd-placeholder-img {
-				font-size: 1.125rem;
-				text-anchor: start;
-			}
-
-			@media (min-width: 768px) {
-				.bd-placeholder-img-lg {
-					font-size: 150%;
-				}
-			}
-		</style>
-		<link rel="stylesheet" href="/static/style.css">
-		<title>Sentiment analysis on Tweets using Hugging Face</title>
-	</head>
-	<body>
-		<form method=post enctype=multipart/form-data>
-			<img src="static/flag.png" width="100%">
-			<div style="height:80px"></div>
-			<div class="container">
-				<h3 style= "color:#030d9b"><i>OVHcloud - Sentiment analysis on Tweets using Hugging Face</i></h3>
-				<hr>
-				<div style="height:50px"></div>
-				<h4 style= "color:#030d9b">Your text:</h4>
-				<p id="demo">{{ text }}</p>
-				<div style="height:50px"></div>
-				<h4 style= "color:#030d9b">Result:</h4>
-				<p id="demo">{{ prediction }}</p>
-			</div>
-			<div style= "height:200px"></div>
-      <p align="center">If you want to know more about AI Training, go <a href="https://www.ovhcloud.com/fr/public-cloud/ai-training/">here</a>.</p>
-    </form>
-		<script src="//code.jquery.com/jquery-3.3.1.slim.min.js" integrity="sha384-q8i/X+965DzO0rT7abK41JStQIAqVgRVzpbzo5smXKp4YfRvH+8abtTE1Pi6jizo" crossorigin="anonymous"></script>
-		<script src="//cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.6/umd/popper.min.js" integrity="sha384-wHAiFfRlMFy6i5SRaxvfOCifBUQy1xHdJ/yoi7FRNXMRBu5WHdZYu1hA6ZOblgut" crossorigin="anonymous"></script>
-		<script src="//stackpath.bootstrapcdn.com/bootstrap/4.2.1/js/bootstrap.min.js" integrity="sha384-B0UglyR+jN6CkvvICOB2joaf5I4l3gm9GU6Hc1og6Ls7i6U/mkkaduKaBhlAXv9k" crossorigin="anonymous"></script>
-	</body>
-</html>