Merge branch 'main' into draft-public-cloud-lb-aan

Author: scraly

.github/pull_request_template.md

@@ -0,0 +1,22 @@
+<!-- Please set a comprehensive title for your pull request. -->
+<!-- Please fill, if applicable, the following sections. -->
+
+## Kind of the Pull Request
+
+ - [ ] ✨ New demos ✨
+ - [ ] 🐛 Bug 🐛
+ - [ ] 🌟 Enhancement 🌟
+ - [ ] 📝 Documentation 📝
+
+## Products targeted
+
+ - [ ] 🧠 AI 🧠
+ - [ ] 💿 DBaaS 💿
+ - [ ] ⎈ Managed Kubernetes Service / Managed Private Registry / Managed Rancher Service ⎈
+ - [ ] 🏗️ IaC 🏗️ 
+
+## Purpose of this Pull Request
+
+<!-- Describe here what is the purpose of your pull request. -->
+
+ - [ ] detailed README provided

.github/release.yml

@@ -0,0 +1,13 @@
+changelog:
+  categories:
+    - title: ✨ Features ✨
+      labels:
+        - '✨ New demos ✨'
+        - '🌟 Enhancement 🌟'
+        - '📝 Documentation 📝'
+    - title: 🐛 Bug 🐛
+      labels:
+        - '🐛 Bug 🐛'
+    - title: 🤷‍♂️ Other Changes 🤷‍♂️
+      labels:
+        - "*"        

.gitignore

@@ -16,3 +16,48 @@ basics/utils/vars.csv
 containers-orchestration/managed-kubernetes/create-cluster-with-tf/my_kube_cluster.yml
 containers-orchestration/managed-private-registry/create-registry-with-pulumi/ovhcloud-registry-go/Pulumi.dev.yaml
 .DS_Store
+
+*.tfvars
+kubeconfig.yml
+.quarkus/
+containers-orchestration/managed-kubernetes/create-cluster-with-cdktf-and-go/kubeconfig.yaml
+containers-orchestration/managed-kubernetes/create-cluster-with-cdktf-and-go/generated
+containers-orchestration/managed-kubernetes/create-cluster-with-cdktf-and-go/cdktf.out
+.vscode/settings.json
+
+# Python 
+venv/
+.venv/
+__pycache__/
+.rock-paper-scisors
+
+
+# JS
+node_modules/
+
+# Java
+target/
+
+# Never commit your credentials
+**/ca.pem
+**/service.cert
+**/service.key
+ai/ai-endpoints/java-langchain4j-chatbot/target/test-classes/com/ovhcloud/examples/aiendpoints/AppTest.class
+
+# IDEs
+.idea/
+.vscode/
+
+# Dot env files
+.env
+use-cases/kubeflow/ovhrc.sh
+use-cases/kubeflow/kubeconfig
+my_kube_cluster.yaml
+kustomize
+containers-orchestration/managed-rancher/create-rancher-with-tf/variables.tf
+use-cases/create-and-use-object-storage-as-tf-backend/my-app/backend.tf
+use-cases/create-and-use-object-storage-as-tf-backend/object-storage-tf/variables.tf
+
+# LLM Fine Tune data
+ai/llm-fine-tune/dataset/docs/*
+ai/llm-fine-tune/dataset/generated/*

README.md

@@ -1,6 +1,19 @@
 # Public cloud examples
 
-![Work in progess](./docs/assets/wip.jpg)
+<table>
+  <tr>
+    <td>
+      <p align="center">
+        <img src="./docs/assets/wip.jpg"/>
+      </p>
+    </td>
+    <td>
+      <b style="font-size:24px">⚠️ This code is only for demonstration purposes </br>and should not be used in production. ⚠️ </b>
+    </td>
+  </tr>
+</table>
+
+
 
 Here is a list of examples which use multiple OVHcloud [Public Cloud products](https://www.ovhcloud.com/fr/public-cloud/).
 
@@ -18,15 +31,19 @@ All examples are organized depending on the main used product (Network, AI, ...)
 Here is the several topics:
 ```bash
 .
-├── ai-machine-learning             ## Here you find demos about AI Products: AI Notebooks, AI Training and AI Deploy
-├── containers-orchestration        ## Here you find demos about Kubernetes, Rancher and Harbor
+├── ai                              ## Here you find demos about AI Products: AI Notebooks, AI Training, AI Deploy, AI Endpoints...
+│   ├── ai-endpoints
+│   ├── deploy
+│   ├── notebooks
+│   └── training
+├── containers-orchestration        ## Here you find demos about Kubernetes, Rancher & Harbor
 │   ├── managed-kubernetes
-│   └── managed-private-registry
+│   ├── managed-private-registry
+│   └── managed-rancher
 ├── databases-analytics             ## Here you find demo about databases, data streaming, data integration, ...
-│   └── databases
 ├── iam                             ## Here you find demo about IAM (roles, identity, ...)
-├── network                         ## Here you find demo about network (private network, load balancer, gateway, ...)
-│   ├── private-network
+├── network                         ## Here you find demo about network (private network, load balancer, gateway, VPS ...)
+├── storage                         ## Here you find demo about storage (object storage, block storage, ...)
 └── use-cases                       ## Here you find use cases (examples using several services: kubernetes, databases...)
 ```
 

ai/ai-endpoints/README.md

@@ -0,0 +1,41 @@
+## AI Endpoints demos
+
+Here you find all demos using AI endpoints.
+Each demo uses a specific language (Python, Java, JS, ...) and illustrate a specific notion (streaming chatbot, RAG, ...).
+
+Don't hesitate to use the source code and give us feedback.
+
+### 🛠️ Prerequisites / links 🔗
+
+ - 🔗 AI Endpoints: https://endpoints.ai.cloud.ovh.net/
+ - 🔗 LangChain: https://www.langchain.com/
+ - 🔗 LangChain4j: https://docs.langchain4j.dev/intro/
+ - 🔗 Quarkus: https://quarkus.io/
+ - 💬 Discord dedicated [channel](https://discord.com/channels/850031577277792286/1217892323640344626)
+
+### ☕️ Java demos ☕️
+
+  - [MCP server / client](./mcp-quarkus-langchain4j)
+  - [Function calling with LangChain4J](./function-calling-langchain4j)
+  - [Simple Structured Output](./structured-output-langchain4j/)
+  - [Natural Language Processing](./java-nlp)
+  - [Chatbot with LangChain4j](./java-langchain4j-chatbot/): blocking mode, streaming mode and RAG mode.
+  - [Blocking chatbot](./quarkus-langchain4j/) with LangChain4j and Quarkus
+  - [Streaming chatbot](./quarkus-langchain4j-streaming/) with langChain4j and Quarkus.
+
+### 🐍 Python 🐍
+
+  - [Podcast audio transcript](./podcast-transcript-whisper/python/)
+  - [Chatbot with LangChain](./python-langchain-chatbot/): blocking mode, streaming mode, RAG mode.
+  - [Streaming chatbot](./python-langchain-chatbot/) with LangChain
+  - [Audio Summarizer Assistant](./audio-summarizer-assistant/) by connecting Speech-To-Text and LLM
+  - [Audio Virtual Assistant](./audio-virtual-assistant/) by putting ASR, LLM and TTS working together
+  - [Conversational Memory for chatbot](./python-langchain-conversational-memory/) by using Mistral7B and LangChain Memory module
+  - [Video Translator](./speech-ai-video-translator) with ASR, NMT and TTS to subtitle and dub video voices
+  - [ASR features](./asr-features) to better understand how Automatic Speech Recognition models work
+  - [TTS features](./tts-features) to be able to use all Text To Speech models easily
+  - [Car Damage Verification with VLM](./car-damage-verification-using-vlm/) - Interactive fact-checking using Vision Language Models to verify car claims against photos
+
+### 🕸️ Javascript 🕸️
+
+  - [Streaming chatbot](./js-langchain-chatbot/) with LangChain

ai/ai-endpoints/asr-features/asr_diarization_tutorial.png

@@ -0,0 +1,17 @@
+This project illustrate how to use Automatic Speech Recognition (ASR) and Large Language Models (LLM) to build an **Audio Summarizer Assistant** with [AI Endpoints](https://endpoints.ai.cloud.ovh.net/).
+
+## How to use the project
+
+- install the required dependencies: `pip install -r requirements.txt`
+- install `ffmpeg` and `ffprob`
+
+- create the `.env` file:
+```
+ASR_AI_ENDPOINT=https://nvr-asr-en-gb.endpoints.kepler.ai.cloud.ovh.net/api/v1/asr/recognize
+LLM_AI_ENDPOINT=https://mixtral-8x7b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1
+OVH_AI_ENDPOINTS_ACCESS_TOKEN=<ai-endpoints-api-token>
+```  
+
+- launch the Gradio app: `python audio-summarizer-app.py`
+
+![image](audio-summarizer-web-app.png)

ai/ai-endpoints/asr-features/audio_asr_diarization.wav

@@ -0,0 +1,142 @@
+import gradio as gr
+import io
+import os
+import requests
+from pydub import AudioSegment
+from dotenv import load_dotenv
+from openai import OpenAI
+
+
+# access the environment variables from the .env file
+load_dotenv()
+asr_ai_endpoint_url = os.environ.get('ASR_AI_ENDPOINT') 
+llm_ai_endpoint_url = os.getenv("LLM_AI_ENDPOINT")
+ai_endpoint_token = os.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN")
+
+
+# automatic speech recognition
+def asr_transcription(audio):
+    
+    if audio is None:
+        return " "
+
+    else:
+        # preprocess audio 
+        processed_audio = "/tmp/my_audio.wav"
+        audio_input = AudioSegment.from_file(audio, "mp3")
+        process_audio_to_wav = audio_input.set_channels(1)
+        process_audio_to_wav = process_audio_to_wav.set_frame_rate(16000)
+        process_audio_to_wav.export(processed_audio, format="wav")
+    
+        # headers
+        headers = headers = {
+            'accept': 'application/json',
+            "Authorization": f"Bearer {ai_endpoint_token}",
+        }
+
+        # put processed audio file as endpoint input
+        files = [
+            ('audio', open(processed_audio, 'rb')),
+        ]
+
+        # get response from endpoint
+        response = requests.post(
+            asr_ai_endpoint_url, 
+            files=files, 
+            headers=headers
+        )
+
+        # return complete transcription
+        if response.status_code == 200:
+            # Handle response
+            response_data = response.json()
+            resp=''
+            for alternative in response_data:
+                resp+=alternative['alternatives'][0]['transcript']
+        else:
+            print("Error:", response.status_code)
+            
+        return resp
+
+
+# ask Mixtral 8x22b for summarization
+def chat_completion(new_message):
+
+    if new_message==" ":
+        return "Please, send an input audio to get its summary!"
+    
+    else:
+        # auth
+        client = OpenAI(
+            base_url=llm_ai_endpoint_url,
+            api_key=ai_endpoint_token
+        )
+
+        # prompt
+        history_openai_format = [{"role": "user", "content": f"Summarize the following text in a few words: {new_message}"}]
+        # return summary
+        return client.chat.completions.create(
+            model="Mixtral-8x7B-Instruct-v0.1",
+            messages=history_openai_format,
+            temperature=0,
+            max_tokens=1024
+        ).choices.pop().message.content
+
+
+# gradio
+with gr.Blocks(theme=gr.themes.Default(primary_hue="blue"), fill_height=True) as demo:
+
+    # add title and description
+    with gr.Row():
+        gr.HTML(
+            """
+            <div align="center">
+                <h1>Welcome on Audio Summarizer web app 💬!</h1>
+                <i>Transcribe and summarize your broadcast, meetings, conversations, potcasts and much more...</i>
+            </div>
+            <br>
+            """
+        )
+        
+    # audio zone for user question
+    gr.Markdown("## Upload your audio file 📢")
+    with gr.Row():
+        inp_audio = gr.Audio(
+            label = "Audio file in .wav or .mp3 format:",
+            sources = ['upload'],
+            type = "filepath",
+        )
+
+    # written transcription of user question
+    with gr.Row():
+        inp_text = gr.Textbox(
+            label = "Audio transcription into text:",
+        )
+        
+    # chabot answer
+    gr.Markdown("## Chatbot summarization 🤖")
+    with gr.Row():
+        out_resp = gr.Textbox(
+            label = "Get a summary of your audio:",
+        )
+
+    with gr.Row():
+        
+        # clear inputs
+        clear = gr.ClearButton([inp_audio, inp_text, out_resp])
+  
+    # update functions
+    inp_audio.change(
+        fn = asr_transcription,
+        inputs = inp_audio,
+        outputs = inp_text
+      )
+    inp_text.change(
+        fn = chat_completion,
+        inputs = inp_text,
+        outputs = out_resp
+      )
+    
+if __name__ == '__main__':
+ 
+    demo.launch(server_name="0.0.0.0", server_port=8000)