Main Page: Difference between revisions

From Essential
Jump to navigation Jump to search
(Nettoyage Priorités: suppression des injections GitHub Trending dans Backlog/Agents IA. -52% contenu.)
Tag: Reverted
(Veille tech 2026-09-07: 50 ajouts GitHub trending)
Tag: Reverted
Line 166: Line 166:
* [https://github.com/RasaHQ/rasa '''Rasa'''] — Framework open-source pour chatbots et assistants vocaux
* [https://github.com/RasaHQ/rasa '''Rasa'''] — Framework open-source pour chatbots et assistants vocaux


* [https://github.com/affaan-m/ECC '''ECC'''] (2026-09-07) : The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. (252,232⭐)
* [https://github.com/moeru-ai/airi '''airi'''] (2026-09-07) : 💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported. (48,874⭐)
* [https://github.com/openclaw/openclaw '''openclaw'''] (2026-09-07) : The AI that really does things. Any OS. Any Platform. The lobster way. 🦞  (389,085⭐)
* [https://github.com/NousResearch/hermes-agent '''hermes-agent'''] (2026-09-07) : The agent that grows with you (242,844⭐)
* [https://github.com/earendil-works/pi '''pi'''] (2026-09-07) : AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI (102,620⭐)
* [https://github.com/koala73/worldmonitor '''worldmonitor'''] (2026-09-07) : Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface (85,743⭐)
* [https://github.com/SimplifyJobs/Summer2027-Internships '''Summer2027-Internships'''] (2026-09-07) : Summer 2027 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC. (47,180⭐)
* [https://github.com/rohitg00/ai-engineering-from-scratch '''ai-engineering-from-scratch'''] (2026-09-07) : Learn it. Build it. Ship it for others. (52,701⭐)
* [https://github.com/CherryHQ/cherry-studio '''cherry-studio'''] (2026-09-07) : AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs (51,538⭐)
* [https://github.com/n8n-io/n8n '''n8n'''] (2026-09-07) : Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. (203,618⭐)
* [https://github.com/lobehub/lobehub '''lobehub'''] (2026-09-07) : 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. (82,285⭐)
* [https://github.com/ClickHouse/ClickHouse '''ClickHouse'''] (2026-09-07) : ClickHouse® is a real-time analytics database management system (49,682⭐)
* [https://github.com/crewAIInc/crewAI '''crewAI'''] (2026-09-07) : Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. (58,187⭐)
* [https://github.com/mudler/LocalAI '''LocalAI'''] (2026-09-07) : LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. (48,952⭐)
* [https://github.com/PostHog/posthog '''posthog'''] (2026-09-07) : :hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP. (39,640⭐)
* [https://github.com/Significant-Gravitas/AutoGPT '''AutoGPT'''] (2026-09-07) : AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. (187,178⭐)
* [https://github.com/punkpeye/awesome-mcp-servers '''awesome-mcp-servers'''] (2026-09-07) : A collection of MCP servers. (94,538⭐)
* [https://github.com/multica-ai/multica '''multica'''] (2026-09-07) : Make humans and AI agents work as one team — open-source and self-hostable. (49,117⭐)
* [https://github.com/supabase/supabase '''supabase'''] (2026-09-07) : The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications. (108,924⭐)
* [https://github.com/twentyhq/twenty '''twenty'''] (2026-09-07) : The open alternative to Salesforce, designed for AI. (56,379⭐)
* [https://github.com/code-yeongyu/oh-my-openagent '''oh-my-openagent'''] (2026-09-07) : OmO: Drop your tokens. Ultrawork. Done. (68,775⭐)
* [https://github.com/ggml-org/llama.cpp '''llama.cpp'''] (2026-09-07) : LLM inference in C/C++ (127,340⭐)
* [https://github.com/zhayujie/CowAgent '''CowAgent'''] (2026-09-07) : Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat) (46,802⭐)
* [https://github.com/docling-project/docling '''docling'''] (2026-09-07) : Get your documents ready for gen AI (66,094⭐)
* [https://github.com/BerriAI/litellm '''litellm'''] (2026-09-07) : The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] (58,201⭐)
* [https://github.com/rtk-ai/rtk '''rtk'''] (2026-09-07) : CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies (79,189⭐)
* [https://github.com/danny-avila/LibreChat '''LibreChat'''] (2026-09-07) : Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active (42,883⭐)
* [https://github.com/netdata/netdata '''netdata'''] (2026-09-07) : The fastest path to AI-powered full stack observability, even for lean teams. (80,453⭐)
* [https://github.com/pingcap/tidb '''tidb'''] (2026-09-07) : TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling. (40,495⭐)
* [https://github.com/sgl-project/sglang '''sglang'''] (2026-09-07) : SGLang is a high-performance serving framework for large language models and multimodal models. (35,577⭐)
* [https://github.com/esengine/DeepSeek-Reasonix '''DeepSeek-Reasonix'''] (2026-09-07) : DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running. (35,434⭐)
* [https://github.com/meilisearch/meilisearch '''meilisearch'''] (2026-09-07) : A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications. (59,206⭐)
* [https://github.com/PDFMathTranslate/PDFMathTranslate '''PDFMathTranslate'''] (2026-09-07) : [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero (36,753⭐)
* [https://github.com/bojieli/ai-agent-book '''ai-agent-book'''] (2026-09-07) : 《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码 (45,063⭐)
* [https://github.com/QuantumNous/new-api '''new-api'''] (2026-09-07) : A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. (47,508⭐)
* [https://github.com/1Panel-dev/1Panel '''1Panel'''] (2026-09-07) : 🔥 1Panel is a modern, open-source Linux server management panel and a lightweight AI management platform. (36,823⭐)
* [https://github.com/HKUDS/nanobot '''nanobot'''] (2026-09-07) : Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps (47,833⭐)
* [https://github.com/langfuse/langfuse '''langfuse'''] (2026-09-07) : 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23  (34,288⭐)
* [https://github.com/AstrBotDevs/AstrBot '''AstrBot'''] (2026-09-07) : AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨ (40,145⭐)
* [https://github.com/tinyhumansai/openhuman '''openhuman'''] (2026-09-07) : OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research. (39,489⭐)
* [https://github.com/apache/airflow '''airflow'''] (2026-09-07) : Apache Airflow - A platform to programmatically author, schedule, and monitor workflows (46,764⭐)
* [https://github.com/agentscope-ai/QwenPaw '''QwenPaw'''] (2026-09-07) : Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities. (34,998⭐)
* [https://github.com/pbakaus/impeccable '''impeccable'''] (2026-09-07) : The design language that makes your AI harness better at design. (66,187⭐)
* [https://github.com/qdrant/qdrant '''qdrant'''] (2026-09-07) : Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/ (34,417⭐)
* [https://github.com/vllm-project/vllm '''vllm'''] (2026-09-07) : A high-throughput and memory-efficient inference and serving engine for LLMs (91,148⭐)
=== Audio & TTS ===
=== Audio & TTS ===
* [https://huggingface.co/Supertone/supertonic-3 '''Supertonic-3'''] — TTS léger pour inférence locale, ONNX Runtime, zéro cloud
* [https://huggingface.co/Supertone/supertonic-3 '''Supertonic-3'''] — TTS léger pour inférence locale, ONNX Runtime, zéro cloud
Line 175: Line 220:
* [https://huggingface.co/HiDream-ai/HiDream-O1-Image '''HiDream-O1-Image'''] — Modèle unifié pixel-level (UiT), sans VAE externe — t2i, édition, personnalisation jusqu'à 2048×2048
* [https://huggingface.co/HiDream-ai/HiDream-O1-Image '''HiDream-O1-Image'''] — Modèle unifié pixel-level (UiT), sans VAE externe — t2i, édition, personnalisation jusqu'à 2048×2048


* [https://github.com/unslothai/unsloth '''unsloth'''] (2026-09-07) : Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. (75,748⭐)
=== RAG & Traitement de Documents ===
=== RAG & Traitement de Documents ===
* '''RAG sur PDF avec images'''
* '''RAG sur PDF avec images'''
Line 182: Line 228:
* [https://github.com/meilisearch/meilisearch '''meilisearch'''] — Moteur de recherche full-text
* [https://github.com/meilisearch/meilisearch '''meilisearch'''] — Moteur de recherche full-text


* [https://github.com/volcengine/OpenViking '''OpenViking'''] (2026-09-07) : Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. (35,877⭐)
* [https://github.com/appwrite/appwrite '''appwrite'''] (2026-09-07) : Appwrite® - complete cloud infrastructure for your web, mobile and AI apps. Including Auth, Databases, Storage, Functions, Messaging, Hosting, Realtime and more (57,304⭐)
* [https://github.com/langgenius/dify '''dify'''] (2026-09-07) : Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. (154,709⭐)
* [https://github.com/bytedance/deer-flow '''deer-flow'''] (2026-09-07) : An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. (81,669⭐)
=== APIs à Développer ===
=== APIs à Développer ===
* '''Classificateur IA''' — Classification de contenu
* '''Classificateur IA''' — Classification de contenu

Revision as of 13:05, 7 September 2026

Discover cloud and AI on infocepo.com

infocepo.com – Cloud, AI & Labs

Bienvenue sur le portail infocepo.com.

Ce wiki documente l’écosystème Cloud, IA, automatisation et lab d’Infocepo. Il s’adresse aux :

  • administrateurs systèmes,
  • ingénieurs cloud,
  • développeurs,
  • étudiants,
  • curieux qui veulent apprendre en pratiquant.

L’objectif est simple : transformer la théorie en scripts réutilisables, schémas, architectures, APIs et laboratoires concrets.

Accès rapide

Portail principal

Assistant IA

Liste des pages du wiki

Vue d’ensemble

Infra architecture overview

Démarrer rapidement

Parcours recommandés

1. Construire un assistant IA privé
  • Déployer une stack type Open WebUI + Ollama + GPU
  • Ajouter un modèle de chat et un modèle de résumé
  • Brancher des données internes via RAG + embeddings
2. Lancer un lab cloud
  • Créer un petit cluster Kubernetes, OpenStack ou bare-metal
  • Mettre en place un pipeline de déploiement (Helm, Ansible, Terraform…)
  • Ajouter un service IA : transcription, résumé, chatbot, OCR…
3. Préparer un audit ou une migration
  • Inventorier les serveurs avec ServerDiff.sh
  • Concevoir l’architecture cible
  • Automatiser la migration avec des scripts reproductibles

Vue d’ensemble du contenu

  • Guides IA & outils : assistants, modèles, évaluation, GPU, RAG
  • Cloud & infrastructure : Kubernetes, OpenStack, HA, HPC, DevSecOps
  • Labs & scripts : audit, migration, automatisation
  • Comparatifs : Kubernetes vs OpenStack vs AWS vs bare-metal, etc.

Vision

The world after automation

Le but à long terme est de construire un environnement où :

  • les assistants IA privés accélèrent la production,
  • les tâches répétitives sont automatisées,
  • les déploiements sont industrialisés,
  • l’infrastructure reste compréhensible, portable et réutilisable.
Main page summary

Catalogue rapide des services

Services principaux
Catégorie Service Rôle
API LLM Modèles de chat, code, RAG, OCR
API STT Transcription audio
API TTS Synthèse vocale
API realtime-ai Temps réel WebSocket / WebRTC
API IMAGE2TXT OCR / VLM via endpoint dédié
API summary Résumé de textes longs
API text2embeddings Embeddings pour RAG
API ChromaDB Base vecteur
API TXT2IMAGE Génération d’images
API diarization Segmentation locuteurs
Observabilité monitoring Dashboards techniques
Observabilité status Disponibilité des services
Observabilité web-stat Statistiques web
Observabilité LLM-stat Vue API / usage
Outils dataLab Environnement de travail hors-production
Outils realtime translation Traduction
Outils Demos Démonstrateurs

Nouveautés

Nouveautés 03/06/2026

  • Agentic RAG : compatibilité Open WebUI avec Agentic RAG.
  • Traduction temps réel : réduction significative des hallucinations lors des silences, diminution de la latence et ajout de la plupart des langues en TTS.
  • TTS Omnivoice : Qualité TTS augmenté et ajout plus global des langues (600).
  • LightRAG : LightRAG est un framework RAG avancé et léger qui combine graphes de connaissances et recherche vectorielle pour une analyse contextuelle profonde et efficace.
  • API reranker.
  • API embedding.
  • privacy-filter : filtrage données personnelles.
  • Un seul fichier CLAUDE.md inspiré d'Andrej Karpathy pour transformer Claude en un vrai ingénieur logiciel.
  • Qwen3.6 : Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
  • Hermes Agent : l'agent qui s'améliore et grandit avec toi.
  • gemma4 STT : API de transcription compatible OpenAI. La qualité est très bonne. Il faut comparer avec Whisper3-turbo. Il est plus gourmand en mémoire. Il ne retourne pas de "timestamp" "sentence".
  • opencode : CLI coder à comparer avec Aider / OpenHands. (⚠️ migration : ancienne URL `github.com/sst/opencode` → redirige vers `anomalyco/opencode`)
  • api-convert2md : extraction de tableaux pour RAG compatible Open WebUI.
  • Mise à jour des paramètres RAG optimisation : bge-m3 (chunk 1200, 100 overlap).
  • Ajout de brains expérimentaux.
  • Ajout de legal-agent.
  • Ajout de ai-security.
  • langextract : démo extraction d'entités. (⚠️ nécessite authentification)
  • sam-audio : séparation audio sémantique. (⚠️ inaccessible depuis l'extérieur — sous-domaine c1 réservé au réseau interne)
  • Ajout de l'API Realtime : WebRTC / WebSocket bidirectionnel basse latence.

Priorités

Top tasks

  • Ajouter Presidio : anonymisation / masquage PII, socle RGPD.
  • Ajouter llm-d : blueprints + charts Kubernetes pour industrialiser les déploiements.
  • Ajouter Dynamo : orchestration inférence multi-nœuds.
  • Ajouter GuideLLM : capacity planning / benchmark réaliste.
  • Ajouter NeMo Guardrails : garde-fous et politiques.

Backlog / Veille Technologique

Agents IA & Orchestration

  • Paperclip — Orchestrateur open-source pour coordonner et superviser une équipe d'agents IA autonomes
  • OpenClaw
  • OpenHands — Agent IA autonome pour le développement logiciel
  • Dify — Plateforme de développement d'applications IA (LLM Ops)
  • browser-use — Framework pour contrôler les navigateurs via des agents IA
  • LangChain — Framework pour applications basées sur les LLM
  • FlowiseAI — Build LLM apps visually
  • Rasa — Framework open-source pour chatbots et assistants vocaux
  • ECC (2026-09-07) : The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. (252,232⭐)
  • airi (2026-09-07) : 💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported. (48,874⭐)
  • openclaw (2026-09-07) : The AI that really does things. Any OS. Any Platform. The lobster way. 🦞 (389,085⭐)
  • hermes-agent (2026-09-07) : The agent that grows with you (242,844⭐)
  • pi (2026-09-07) : AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI (102,620⭐)
  • worldmonitor (2026-09-07) : Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface (85,743⭐)
  • Summer2027-Internships (2026-09-07) : Summer 2027 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC. (47,180⭐)
  • ai-engineering-from-scratch (2026-09-07) : Learn it. Build it. Ship it for others. (52,701⭐)
  • cherry-studio (2026-09-07) : AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs (51,538⭐)
  • n8n (2026-09-07) : Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations. (203,618⭐)
  • lobehub (2026-09-07) : 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. (82,285⭐)
  • ClickHouse (2026-09-07) : ClickHouse® is a real-time analytics database management system (49,682⭐)
  • crewAI (2026-09-07) : Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. (58,187⭐)
  • LocalAI (2026-09-07) : LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. (48,952⭐)
  • posthog (2026-09-07) : :hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP. (39,640⭐)
  • AutoGPT (2026-09-07) : AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters. (187,178⭐)
  • awesome-mcp-servers (2026-09-07) : A collection of MCP servers. (94,538⭐)
  • multica (2026-09-07) : Make humans and AI agents work as one team — open-source and self-hostable. (49,117⭐)
  • supabase (2026-09-07) : The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications. (108,924⭐)
  • twenty (2026-09-07) : The open alternative to Salesforce, designed for AI. (56,379⭐)
  • oh-my-openagent (2026-09-07) : OmO: Drop your tokens. Ultrawork. Done. (68,775⭐)
  • llama.cpp (2026-09-07) : LLM inference in C/C++ (127,340⭐)
  • CowAgent (2026-09-07) : Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat) (46,802⭐)
  • docling (2026-09-07) : Get your documents ready for gen AI (66,094⭐)
  • litellm (2026-09-07) : The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM] (58,201⭐)
  • rtk (2026-09-07) : CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies (79,189⭐)
  • LibreChat (2026-09-07) : Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active (42,883⭐)
  • netdata (2026-09-07) : The fastest path to AI-powered full stack observability, even for lean teams. (80,453⭐)
  • tidb (2026-09-07) : TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling. (40,495⭐)
  • sglang (2026-09-07) : SGLang is a high-performance serving framework for large language models and multimodal models. (35,577⭐)
  • DeepSeek-Reasonix (2026-09-07) : DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running. (35,434⭐)
  • meilisearch (2026-09-07) : A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications. (59,206⭐)
  • PDFMathTranslate (2026-09-07) : [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero (36,753⭐)
  • ai-agent-book (2026-09-07) : 《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码 (45,063⭐)
  • new-api (2026-09-07) : A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. (47,508⭐)
  • 1Panel (2026-09-07) : 🔥 1Panel is a modern, open-source Linux server management panel and a lightweight AI management platform. (36,823⭐)
  • nanobot (2026-09-07) : Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps (47,833⭐)
  • langfuse (2026-09-07) : 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 (34,288⭐)
  • AstrBot (2026-09-07) : AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨ (40,145⭐)
  • openhuman (2026-09-07) : OpenHuman is an open source personal AI for Mac, Windows and Linux — local-first memory, agent orchestration, and deep research. (39,489⭐)
  • airflow (2026-09-07) : Apache Airflow - A platform to programmatically author, schedule, and monitor workflows (46,764⭐)
  • QwenPaw (2026-09-07) : Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities. (34,998⭐)
  • impeccable (2026-09-07) : The design language that makes your AI harness better at design. (66,187⭐)
  • qdrant (2026-09-07) : Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/ (34,417⭐)
  • vllm (2026-09-07) : A high-throughput and memory-efficient inference and serving engine for LLMs (91,148⭐)

Audio & TTS

  • Supertonic-3 — TTS léger pour inférence locale, ONNX Runtime, zéro cloud
  • faster-whisper (mutualisé) — Transcription speech-to-text optimisée
  • Qwen3-Omni-30B-A3B-Instruct — Modèle multimodal Qwen (audio + texte + image)
  • nemotron-3.5-asr-streaming-0.6b — Modèle ASR streaming NVIDIA, faible latence pour transcription temps réel

Génération & Édition d'Images

  • HiDream-O1-Image — Modèle unifié pixel-level (UiT), sans VAE externe — t2i, édition, personnalisation jusqu'à 2048×2048
  • unsloth (2026-09-07) : Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. (75,748⭐)

RAG & Traitement de Documents

  • RAG sur PDF avec images
  • granite-docling-258M — Parsing structuré de documents IBM Granite
  • Haystack — Framework RAG end-to-end (deepset)
  • Mem0 — Mémorie à long terme pour agents IA
  • meilisearch — Moteur de recherche full-text
  • OpenViking (2026-09-07) : Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. (35,877⭐)
  • appwrite (2026-09-07) : Appwrite® - complete cloud infrastructure for your web, mobile and AI apps. Including Auth, Databases, Storage, Functions, Messaging, Hosting, Realtime and more (57,304⭐)
  • dify (2026-09-07) : Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack. (154,709⭐)
  • deer-flow (2026-09-07) : An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours. (81,669⭐)

APIs à Développer

  • Classificateur IA — Classification de contenu
  • Résumé mutualisé — API de résumé de texte partagée
  • NER — Reconnaissance d'entités nommées
  • Compressor — Compression de contenu

Infrastructure & Backend

  • Temporal — Orchestration de workflows critiques
  • Semantic Router — Routage sémantique de requêtes vLLM
  • Supabase — Alternative open-source Firebase (PostgreSQL, Auth, etc.)
  • Metabase — Analytics et dashboards open-source
  • N8N — Workflow automation open-source

Outils Dev

  • Aider — Assistant de codage IA en ligne de commande
  • Continue — Extension IDE IA (VS Code, JetBrains)
  • MCP LLM — Modèle de langage via Model Context Protocol

Assistants IA & outils cloud

Assistants IA

ChatGPT
  • ChatGPT – Assistant conversationnel public, utile pour exploration, rédaction, expérimentation rapide.
Assistants IA auto-hébergés
Stack typique pour assistant privé, API OpenAI-compatible et expérimentation locale.
Outil de résumé local, rapide et hors ligne.

Développement, modèles & veille

Découverte de modèles
Évaluation & benchmarks
Outils de développement & fine-tuning

Matériel IA & GPU

API Realtime AI (DEV)

Statut : environnement DEV, remplaçante prévue de l’API OpenAI pour les cas temps réel.

Configuration

Variable Valeur
OPENAI_API_BASE wss://api-realtime-ai.ailab.infocepo.com:wait-2026-06/v1
OPENAI_API_KEY sk-XXXXX

Dépôt GitHub

Page de test

  • external-test/half-duplex.html — annulation d’écho + mode half-duplex.

Compatibilité

Remplacer l’URL OpenAI par $OPENAI_API_BASE pour tester compatibilité et performances.

API LLM (OpenAI compatible)

Liste des modèles

curl -X GET \
  'https://api.ailab.infocepo.com:wait-2026-06/v1/models' \
  -H 'Authorization: Bearer sk-XXXXX' \
  -H 'accept: application/json' \
  | jq | sed -rn 's#^.*id.*: "(.*)".*$#* \1#p' | sort -u

Modèles ouverts & endpoints internes

Dernière mise à jour : 2026-04-20

Les modèles ci-dessous correspondent à des endpoints logiques exposés derrière une passerelle.

Endpoint Description / usage principal
ai-multilingual qwen3.6 fp8 en mode nothink – multilingual
ai-tools qwen3.6 fp8 – tâches agentiques et outils
ai-thinking qwen3.6 fp8 – thinking
ai-vision qwen3.6 fp8 en mode nothink – vision/OCR
ai-embedding bge-m3 – recherche sémantique
ai-stt whisper3-turbo – transcription vocale multilingual
ai-tts OmniVoice – TTS multilingual
ai-image OpenDalle – image génération

Exemple bash

export OPENAI_API_MODEL="ai-chat"
export OPENAI_API_BASE="https://api.ailab.infocepo.com:wait-2026-06/v1"
export OPENAI_API_KEY="sk-XXXXX"

promptValue="Quel est ton nom ?"
jsonValue='{
  "model": "'${OPENAI_API_MODEL}'",
  "messages": [{"role": "user", "content": "'${promptValue}'"}],
  "temperature": 0
}'

curl -k ${OPENAI_API_BASE}/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d "${jsonValue}" 2>/dev/null | jq '.choices[0].message.content'

Vue infra LLM

File:Litellm-proxy-mermaid-diagram-2024-03-24-205202.png

DEV (au choix)

  • A. LiteLLM → vLLM/SgLang : tests perf / compatibilité
  • B. LiteLLM → Ollama : simple, rapide à itérer
  • C. Ollama direct : POC ultra-léger

DEV – modèle FR / résumé

  • LiteLLM → Ollama /v1

PROD

  • Standard : LiteLLM → vLLM/SgLang
  • Pont DEV→PROD : LiteLLM (DEV) → LiteLLM (PROD) → vLLM/SgLang

Notes :

  • LiteLLM = passerelle unique (clés, quotas, logs)
  • vLLM/SgLang = performance / stabilité en charge
  • Ollama = simplicité de prototypage

API Image to Text

  • Utilise l’API LLM avec un endpoint adapté à l’OCR / VLM.
  • Modèle recommandé : ai-vision

Exemple bash

OPENAI_API_KEY=sk-XXXXX

base64 -w0 "/path/to/image.png" > img.b64

jq -n --rawfile img img.b64 \
'{
  model: "ai-vision",
  messages: [
    {
      role: "user",
      content: [
        { "type": "text", "text": "Décris cette image." },
        {
          "type": "image_url",
          "image_url": { "url": ("data:image/png;base64," + ($img | rtrimstr("\n"))) }
        }
      ]
    }
  ]
}' > payload.json

curl https://api.ailab.infocepo.com:wait-2026-06/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @payload.json

Exemple Python

import base64
import json
import requests
import os

API_KEY = os.getenv("OPENAI_API_KEY")
MODEL = "ai-vision"
IMG_PATH = "/path/to/image.png"
API_URL = "https://api.ailab.infocepo.com:wait-2026-06/v1/chat/completions"

with open(IMG_PATH, "rb") as f:
    img_b64 = base64.b64encode(f.read()).decode("utf-8")

payload = {
    "model": MODEL,
    "messages": [
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Décris cette image."},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{img_b64}"}
                }
            ]
        }
    ]
}

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json"
}

response = requests.post(API_URL, headers=headers, data=json.dumps(payload))

if response.ok:
    print(json.dumps(response.json(), indent=2, ensure_ascii=False))
else:
    print(f"Erreur {response.status_code}: {response.text}")

API STT

Exemple Python

import requests

OPENAI_API_KEY = 'sk-XXXXX'

url = 'https://api-audio2txt.ailab.infocepo.com/v1/audio/transcriptions'
headers = {
    'Authorization': f'Bearer {OPENAI_API_KEY}',
}
files = {
    'file': ('file.opus', open('/path/to/file.opus', 'rb')),
    'model': (None, 'whisper-1')
}

response = requests.post(url, headers=headers, files=files)
print(response.json())

Exemple curl

[ ! -f /tmp/test.ogg ] && wget "https://upload.wikimedia.org/wikipedia/commons/1/17/Fables_de_La_Fontaine_Livre_1_01.ogg" -O /tmp/test.ogg

export OPENAI_API_KEY=sk-XXXXX

curl https://api-audio2txt.ailab.infocepo.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -F model="whisper-1" \
  -F file="@/tmp/test.ogg"

Notes

  • Plusieurs formats audio sont acceptés.
  • Le flux final est normalisé en 16 kHz mono.
  • Pour une qualité optimale : privilégier OPUS 16 kHz mono.

UI

API TTS

Exemple

export OPENAI_API_KEY=sk-XXXXX

curl https://api-tts-omnivoice.ailab.infocepo.com/v1/audio/speech \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "Bonjour, ceci est un test de synthèse vocale.",
    "voice": "coral",
    "instructions": "Speak in a cheerful and positive tone.",
    "response_format": "opus"
  }' | ffplay -i -

API Text to Image

Exemple

export OPENAI_API_KEY=EMPTY

curl https://api-txt2image.ailab.infocepo.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "prompt": "a photo of a happy corgi puppy sitting and facing forward, studio light, longshot",
    "n": 1,
    "size": "1024x1024"
  }'

API Diarization

Exemple

wget "https://upload.wikimedia.org/wikipedia/commons/6/60/Mike_Peters_on_Politics_and_Emotion_%28Interview_1984%29.mp3" -O /tmp/test.mp3

curl -X POST "https://api-diarization.ailab.infocepo.com/upload-audio/" \
  -H "Authorization: Bearer token1" \
  -F "file=@/tmp/test.mp3"

API Summary

Exemple

text="The tower is 324 metres tall and is one of the most recognizable monuments in the world."

json_payload=$(jq -nc --arg text "$text" '{"text": $text}')

curl -X POST https://api-summary.ailab.infocepo.com:wait-2026-06/summary/ \
  -H "Content-Type: application/json" \
  -d "$json_payload"

API Text Embeddings

Exemple

curl -k https://text-embeddings.ailab.infocepo.com:wait-2026-06/embed \
  -X POST \
  -d '{"inputs":"What is Deep Learning?"}' \
  -H 'Content-Type: application/json'

API DB Vectors (ChromaDB)

Production

Lab

export CHROMA_HOST=https://chromadb.c1.ailab.infocepo.com:wait-2026-06
export CHROMA_PORT=443
export CHROMA_TOKEN=XXXX

Exemple curl

curl -v "${CHROMA_HOST}"/api/v1/collections \
  -H "Authorization: Bearer ${CHROMA_TOKEN}"

Exemple Python

import chromadb
from chromadb.config import Settings

def chroma_http(host, port=80, token=None):
    return chromadb.HttpClient(
        host=host,
        port=port,
        ssl=host.startswith('https') or port == 443,
        settings=(
            Settings(
                chroma_client_auth_provider='chromadb.auth.token.TokenAuthClientProvider',
                chroma_client_auth_credentials=token,
            ) if token else Settings()
        )
    )

client = chroma_http(CHROMA_HOST, CHROMA_PORT, CHROMA_TOKEN)
collections = client.list_collections()
print(collections)

Déployer sa propre instance

export nameSpace=your_namespace
domainRoot=ailab.infocepo.com

helm repo add chroma https://amikos-tech.github.io/chromadb-chart/
helm repo update

helm upgrade --install chromadb chroma/chromadb -n ${nameSpace} \
  --set chromadb.apiVersion="0.4.24" \
  --set ingress.enabled=true \
  --set ingress.hosts[0].host="${nameSpace}-chromadb.${domainRoot}" \
  --set ingress.hosts[0].paths[0].path=/ \
  --set ingress.hosts[0].paths[0].pathType=ImplementationSpecific \
  --set ingress.annotations."cert-manager\.io/cluster-issuer"=letsencrypt-prod \
  --set ingress.tls[0].secretName=${nameSpace}-chromadb.${domainRoot}-tls \
  --set ingress.tls[0].hosts[0]="${nameSpace}-chromadb.${domainRoot}"

kubectl -n ${nameSpace} patch ingress/chromadb --type=json \
  -p '[{"op":"add","path":"/metadata/annotations/nginx.ingress.kubernetes.io~1proxy-body-size","value":"0"}]'

Récupérer le token

kubectl --namespace ${nameSpace} get secret chromadb-auth \
  -o jsonpath="{.data.token}" | base64 --decode && echo

Registry

Exemple

curl -u "user:XXXXX" https://registry.ailab.infocepo.com:wait-2026-06/v2/_catalog

Exemple K8S

deploymentName=
nameSpace=

kubectl -n ${nameSpace} create secret docker-registry pull-secret \
  --docker-server=registry.ailab.infocepo.com:wait-2026-06 \
  --docker-username=user \
  --docker-password=XXXXX \
  --docker-email=contact@example.com

kubectl -n ${nameSpace} patch deployment ${deploymentName} \
  -p '{"spec":{"template":{"spec":{"imagePullSecrets":[{"name":"pull-secret"}]}}}}'

Stockage objet externe (S3)

Un bucket nommé ORG a été créé pour stocker des documents de démonstration.

RAG optimisation

  • Embeddings : BAAI/bge-m3
  • chunk_size=1200
  • chunk_overlap=100
  • LLM : qwen3.6
  • Pour les PDF mixtes : PDF → image → OCR / VLM peut améliorer les résultats.

Processus usine IA

Étape Description Outils utilisés Responsable(s)
1 Idée - Équipe projet
2 Développement Environnement Onyxia / lab Équipe projet
3 Déploiement CI/CD, GitHub, Kubernetes Équipe DevOps
4 Surveillance Uptime-Kuma, dashboards Équipe DevOps
5 Alertes Mattermost Équipe DevOps
6 Support infrastructure - Équipe SRE
7 Support applicatif - Équipe applicative

Environnements

Hors production

  • Utiliser datalab
  • Support : canal Mattermost Offre IA
  • Le pseudo utilisateur doit respecter la convention interne
  • Demander si besoin un accès Linux + Kubernetes

Production (best-effort)

  • Publier le code applicatif, les secrets (format SOPS), le Dockerfile et le code infra (Helm ou manifests K8S) sur Git
  • Demander un namespace
  • Lire la documentation de surveillance associée

Limites de l’infrastructure

  • Les charges GPU sont intentionnellement limitées en journée.

Cloud Lab & projets d’audit

Cloud Lab reference diagram

Le Cloud Lab fournit des scénarios reproductibles : audit d’infrastructure, migration cloud, automatisation, haute disponibilité.

Projet d’audit

ServerDiff.sh

Script Bash d’audit permettant de :

  • détecter les dérives de configuration,
  • comparer plusieurs environnements,
  • préparer un plan de migration ou de remédiation.

Exemple de migration cloud

Cloud migration diagram

Tâche Description Durée (jours)
Audit infrastructure 82 services, audit automatisé via ServerDiff.sh 1.5
Diagramme d’architecture Conception visuelle et documentation 1.5
Contrôles de conformité 2 clouds, 6 hyperviseurs, 6 To RAM 1.5
Installation plateforme cloud Déploiement des environnements cibles 1.0
Vérification de stabilité Premiers tests fonctionnels 0.5
Étude d’automatisation Identification des tâches répétitives 1.5
Développement des templates 6 templates, 8 environnements, 2 clouds / OS 1.5
Diagramme de migration Illustration du processus 1.0
Écriture du code de migration 138 lignes (voir MigrationApp.sh) 1.5
Stabilisation Validation de la reproductibilité 1.5
Benchmark cloud Comparaison vs legacy 1.5
Réglage des temps d’arrêt Calcul du downtime 0.5
Chargement VM 82 VMs : OS, code, 2 IP par VM 0.1
Total 15 jours.homme

Vérifications de stabilité (HA minimale)

Action Résultat attendu
Extinction d’un nœud Tous les services redémarrent automatiquement sur les autres nœuds
Extinction / redémarrage simultané de tous les nœuds Les services repartent correctement après reboot

Architecture web & bonnes pratiques

Reference web architecture

Principes de conception :

  • privilégier une infrastructure simple, modulaire et flexible,
  • rapprocher le contenu du client (GDNS ou équivalent),
  • utiliser des load balancers réseau (LVS, IPVS),
  • comparer les coûts et éviter le vendor lock-in,
  • pour TLS :
    • HAProxy pour les frontends rapides,
    • Envoy pour les cas avancés (mTLS, HTTP/2/3),
  • pour le cache :
    • Varnish, Apache Traffic Server,
  • favoriser les stacks open-source,
  • utiliser files, buffers, queues et quotas pour lisser les pics.

Références

Comparatif des grandes plateformes cloud

Fonctionnalité Kubernetes OpenStack AWS Bare-metal HPC CRM oVirt
Outils de déploiement Helm, YAML, ArgoCD, Juju Ansible, Terraform, Juju CloudFormation, Terraform, Juju Ansible, Shell xCAT, Clush Ansible, Shell Ansible, Python
Méthode de bootstrap API API, PXE API PXE, IPMI PXE, IPMI PXE, IPMI PXE, API
Contrôle routeur Kube-router Router/Subnet API Route Table / Subnet API Linux, OVS xCAT Linux API
Contrôle firewall Istio, NetworkPolicy Security Groups API Security Group API Linux firewall Linux firewall Linux firewall API
Virtualisation réseau VLAN, VxLAN VPC VPC OVS, Linux xCAT Linux API
DNS CoreDNS DNS-Nameserver Route 53 GDNS xCAT Linux API
Load balancer Kube-proxy, LVS LVS Network Load Balancer LVS SLURM Ldirectord N/A
Stockage Local, cloud, PVC Swift, Cinder, Nova S3, EFS, EBS, FSx Swift, XFS, EXT4, RAID10 GPFS SAN NFS, SAN

Cette table sert de point de départ pour choisir la bonne stack selon :

  • le niveau de contrôle souhaité,
  • le contexte (on-prem, cloud public, HPC…),
  • les outils d’automatisation existants.

Haute disponibilité, HPC & DevSecOps

Haute disponibilité avec Corosync & Pacemaker

HA cluster architecture

Principes :

  • clusters multi-nœuds ou multi-sites,
  • fencing via IPMI,
  • provisioning PXE / NTP / DNS / TFTP,
  • pour 2 nœuds : attention au split-brain,
  • 3 nœuds ou plus recommandés en production.

Ressources fréquentes

  • multipath, LUNs, LVM, NFS,
  • processus applicatifs,
  • IP virtuelles, DNS, listeners réseau.

HPC

Overview of an HPC cluster

  • orchestration de jobs (SLURM ou équivalent),
  • stockage partagé haute performance,
  • intégration possible avec des workloads IA.

DevSecOps

DevSecOps reference design

  • CI/CD avec contrôles de sécurité intégrés,
  • observabilité dès la conception,
  • scans de vulnérabilité,
  • gestion des secrets,
  • policy-as-code.

News & trends

Formation & apprentissage

Liens cloud & IT utiles

Outils collaboratifs

Dépôts de code

Base de connaissance

  • ce wiki

Messagerie

  • contact interne / support selon les projets

SSO

MLflow

À propos & contributions

Suggestions de corrections, améliorations de schémas, retours d’expérience ou nouveaux labs bienvenus.

Ce wiki a vocation à rester un laboratoire vivant pour l’IA, le cloud et l’automatisation.

Retrieved from "https://infocepo.com/wiki/index.php?title=Main_Page&oldid=2187"