BEGIN:VCALENDAR VERSION:2.0 PRODID:-//datacraft - ECPv6.16.3//NONSGML v1.0//EN CALSCALE:GREGORIAN METHOD:PUBLISH X-WR-CALNAME:datacraft X-ORIGINAL-URL:https://datacraft.paris X-WR-CALDESC:Events for datacraft REFRESH-INTERVAL;VALUE=DURATION:PT1H X-Robots-Tag:noindex X-PUBLISHED-TTL:PT1H BEGIN:VTIMEZONE TZID:Europe/Paris BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20230326T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20231029T010000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20240331T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20241027T010000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20250330T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20251026T010000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20260329T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20261025T010000 END:STANDARD BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:20270328T010000 END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:20271031T010000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20260601T170000 DTEND;TZID=Europe/Paris:20260601T200000 DTSTAMP:20260613T032408 CREATED:20260319T110529Z LAST-MODIFIED:20260528T114536Z UID:18749-1780333200-1780344000@datacraft.paris SUMMARY:GraphRAG in Practice: Building Reliable GenAI Applications with Knowledge Graphs DESCRIPTION:S’inscrire à l’événement\n\npar Henry Collie\, concepteur de programmes techniques\, Neo4j \nL’IA générative (GenAI) offre des perspectives immenses… mais elle se heurte encore à des défis majeurs : hallucinations\, manque de contexte métier\, explicabilité limitée et problèmes de gouvernance . \nEt si vous pouviez surmonter ces limitations ? \nDans cet atelier pratique\, découvrez comment GraphRAG combine la recherche vectorielle\, les graphes de connaissances et les techniques de science des données graphiques pour enrichir le contexte\, améliorer la compréhension sémantique et garantir la mise à jour des données. \nRésultat : des applications GenAI plus fiables\, pertinentes et personnalisées . \nOrdre du jour: \n\nUne introduction claire aux limitations actuelles de GenAI\nAnalyse approfondie de l’approche GraphRAG et de ses avantages pratiques\nExemples de code guidés étape par étape pour connecter GenAI aux technologies graphiques\nMise en pratique immédiate\, directement applicable à vos propres projets\n\nÀ la fin de cet atelier\, vous repartirez avec des compétences concrètes et applicables pour concevoir des applications GenAI robustes et contextuelles. \n\nS’inscrire à l’événement URL:https://datacraft.paris/event/graphrag-in-practice-building-reliable-genai-applications-with-knowledge-graphs/ LOCATION:Online CATEGORIES:in English,on-site event ORGANIZER;CN="datacraft":MAILTO:contact@datacraft.paris END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20260520T170000 DTEND;TZID=Europe/Paris:20260520T190000 DTSTAMP:20260613T032408 CREATED:20260420T081104Z LAST-MODIFIED:20260420T081524Z UID:18915-1779296400-1779303600@datacraft.paris SUMMARY:Aligning Data Visualization with Human Cognition: A Novel Approach to Large Numbers. DESCRIPTION:S’inscrire à l’événement\n\npresentation by Katerina Batziakoudi\, PhD in Data Visualization with the AVIZ team at Inria \nDr Batziakoudi’s research is about helping people make sense of very large numbers —like the thousands\, millions\, and billions found in public budgets— because common linear and logarithmic charts make these values hard to compare and understand. \nInstead of treating this only as a visualization problem\, she studies it as a human understanding problem: how people naturally think about large numbers\, and how charts can better match that way of thinking. \nIn particular\, this work builds on psychological findings that people do not perceive large values as purely linear or logarithmic; rather\, we tend to mentally chunk them into groups such as thousands\, millions\, and billions\, and reason linearly within each group\, much as numbers are expressed in language.\nBased on this\, she designed and tested novel visual representations that align with this piecewise linear way of thinking. Across a series of experiments and real-world evaluations\, including work with journalists exploring national budget data\, she shows that these designs can make comparisons easier\, reduce mental effort\, and improve confidence in interpretation. \nMore broadly\, this presentation proposes a design approach for visualizing extreme numerical ranges that is grounded in how people actually reason about numbers. \n\nS’inscrire à l’événement URL:https://datacraft.paris/event/aligning-data-visualization-with-human-cognition-a-novel-approach-to-large-numbers/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20260407T163000 DTEND;TZID=Europe/Paris:20260407T190000 DTSTAMP:20260613T032408 CREATED:20260213T154949Z LAST-MODIFIED:20260407T075545Z UID:18279-1775579400-1775588400@datacraft.paris SUMMARY:REX - Data Provenance and Responsible AI for Social Media Privacy and Workforce Intelligence DESCRIPTION:S’inscrire à l’événement\n\nGuilherme Medeiros Machado\, Associate Professor – ECE\nFaiza Belbachir\, faculty member and researcher – ECE\nSubankhar Chanti\, post-doc researcher – ECE \nREX – Data Provenance and Responsible AI for Social Media Privacy and Workforce Intelligence \nby Guilherme Machado Medeiros\, associate professor & Subhankar Maity\, post-doc researcher – ECE \n— Presentation In English — \nAs large language models (LLMs) increasingly power intelligent systems\, from conversational interfaces to code generation\, the need to understand the provenance of their training data has become critical. \nOur guests’ research tackles whether specific data samples contribute to LLM behaviour\, focusing on code repositories and social media content that differ sharply from traditional text datasets. \nThrough data provenance analysis and membership inference attacks\, we deliver measurable transparency into how models learn\, memorise\, and potentially expose sensitive information. The project tests authentic code and social media samples across state-of-the-art LLMs (GPT-5\, Gemini 2.5 Flash\, Mistral 24B\, LLaMA 3.3 70B\, DeepSeek\, etc.). \nWe develop statistical and visual frameworks to detect the presence of training data reliably. \nIn professional environments\, employee-contributed code often feeds LLMs for code assistance\, creating blind spots in workforce capabilities. Our detection reveals when proprietary code influences outputs beyond documented team knowledge\, highlighting specific learning gaps. \nThis drives targeted upskilling programs\, ensuring organisations maintain competitive expertise while protecting intellectual property from unauthorised model memorisation.\nSocial media content creates acute privacy risks when absorbed into LLMs\, as user-generated posts can reveal personal details through model outputs. Our methods allow individuals to flag whether their personal content was used in training\, enabling proactive privacy protection. This user-centric approach demands accountability from AI systems trained on public data\, aligning with GDPR requirements for transparency and data rights. \nThis research converts regulatory challenges into strategic opportunities\n– Privacy-first AI respecting user consent and personal data rights\n– IP protection for proprietary code and internal knowledge assets\n– Workforce analytics linking AI outputs to actionable training needs\n– Market differentiation through transparent\, auditable intelligence systems \n\n\nS’inscrire à l’événement\n\n\ndatacraft* est le club des Data Scientists\, Chercheurs et Ingénieurs en IA. Rejoignez-nous ! URL:https://datacraft.paris/event/rex-data-provenance-and-responsible-ai-for-social-media-privacy-and-workforce-intelligenc/ LOCATION:Le Village By CA –\, 55 rue la Boétie\, 75008 Paris\, 75008\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20260218T183000 DTEND;TZID=Europe/Paris:20260218T210000 DTSTAMP:20260613T032408 CREATED:20251124T131636Z LAST-MODIFIED:20260129T161454Z UID:17633-1771439400-1771448400@datacraft.paris SUMMARY:Neurons & Peppers #3 DESCRIPTION:Neurons & Peppers is THE state of the art AI research meetup in Paris! \nFor this 3rd edition\, we will dive into domain-specific modeling and RAG benchmarking ! \nThe LLM Pro Finance Suite: Multilingual Large Language Models for Financial Applications\nby Raheel Qader\, Head of R&D and Gaëtan Caillaut\, AI Researcher – DragonLLM. \nAbstract: The financial industry’s growing demand for advanced natural language processing (NLP) capabilities has highlighted the limitations of generalist large language models (LLMs) in handling domain-specific financial tasks. To address this gap\, we introduce the LLM Pro Finance Suite\, a collection of five instruction-tuned LLMs (ranging from 8B to 70B parameters) specifically designed for financial applications. Our approach focuses on enhancing generalist instruction-tuned models\, leveraging their existing strengths in instruction following\, reasoning\, and toxicity control\, while fine-tuning them on a curated\, high-quality financial corpus comprising over 50% finance-related data in English\, French\, and German […] \nCheck out the full paper on Arxiv\nCheck out the models on their HuggingFace collections:\n– LLM Open Finance  (open-source)\n– LLM Pro Finance\n \n\n​ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios ​\nby Quentin Macé et Antoine Edy\, data scientists – ILLUIN Technology. \n​Abstract: Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval\, such as interpreting visual elements (tables\, charts\, images)\, synthesizing information across documents\, and providing accurate source grounding. Existing benchmarks fail to capture this complexity\, often focusing on textual data\, single-document comprehension\, or evaluating retrieval and generation in isolation. We introduce ViDoRe v3\, a comprehensive multimodal RAG benchmark featuring multi-type queries over visually rich document corpora. It covers 10 datasets across diverse professional domains\, comprising ~26\,000 document pages paired with 3\,099 human-verified queries\, each available in 6 languages […] \n​Check out the full paper on Arxiv\nTest the benchmark yourself on their HuggingFace Space. \n\n​​Presentations (in english) will be followed by food & drinks 🌶️\n\nYou’re an AI researcher and want to take the stage to tell us about your latest paper ?👇\nFill out the form and let us know about your project !\n\n\n\nRegistration URL:https://datacraft.paris/event/neurons-peppers-3/ LOCATION:Accuracy –\, 16 avenue Matignon\, Paris\, 75005\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20251210T183000 DTEND;TZID=Europe/Paris:20251210T203000 DTSTAMP:20260613T032408 CREATED:20251020T160942Z LAST-MODIFIED:20251201T155904Z UID:17280-1765391400-1765398600@datacraft.paris SUMMARY:Cybersecurity for the agentic age DESCRIPTION:As GenAI transforms enterprise operations\, security leaders face unprecedented challenges: 20% of jailbreaks succeed in just 42 seconds\, and 46% of experts believe AI integration increases vulnerability to cyberattacks. This technical session addresses the critical security gap threatening your AI investments. Join us for a deep dive into AI red teaming\, covering the latest OWASP LLM and Agentic risk frameworks (2025 update)\, real-world attack scenarios including prompt injection and tool misuse\, and practical defense strategies.\nThe session includes a live demonstration\, showcasing how enterprises are protecting their GenAI deployments. You’ll also get hands-on experience testing AI vulnerabilities through an interactive demo.\n\n\n\n  \nKey Takeaways:\n\nUnderstanding new AI threat models and attack vectors\nImplementing OWASP-based security frameworks across the AI lifecycle\nDeploying real-time protection for agentic AI systems\nMoving from reactive to proactive AI assurance\n\n  \nDesigned for CISOs\, security architects\, and technical leaders navigating the security challenges of enterprise AI adoption.\n  \nRegister on Luma URL:https://datacraft.paris/event/automated-llm-testing-and-evaluation/ LOCATION:Le Village By CA –\, 55 rue la Boétie\, 75008 Paris\, 75008\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20251112T183000 DTEND;TZID=Europe/Paris:20251112T203000 DTSTAMP:20260613T032408 CREATED:20251013T135424Z LAST-MODIFIED:20251104T105243Z UID:17209-1762972200-1762979400@datacraft.paris SUMMARY:Neurons & Peppers #2 DESCRIPTION:Vincent Coyette\, Research Engineer in Applied AI @ InstaDeep – Jean Lelong\, data scientist and Annabelle Blangero\, lead of Responsible AI @ Ekimetrics. \n\nNeurons & Peppers is THE State of the art AI Research meetup\nin Paris! 🇫🇷 \nFor this second edition of N&P hosted by Ekimetrics\, we will dive into the following papers : \nAgentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World Applications\nby Jean Lelong\, data scientist and Annabelle Blangero\, lead of Responsible AI @ Ekimetrics. \nReinforcement Learning-based Train Rescheduling on Event Graphs\nby Vincent Coyette\, Research Engineer in Applied AI @ InstaDeep. \n​​Presentations (in english) will be followed by food & drinks 🌶️ \nRegistration on Luma URL:https://datacraft.paris/event/neurons-peppers-2/ LOCATION:Ekimetrics Paris –\, 36 Rue La Fayette\, Paris\, 75009\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20251001T183000 DTEND;TZID=Europe/Paris:20251001T203000 DTSTAMP:20260613T032408 CREATED:20250710T100429Z LAST-MODIFIED:20250917T161351Z UID:15544-1759343400-1759350600@datacraft.paris SUMMARY:Machine Learning on tabular data using LLMs DESCRIPTION:2509-Tinypred-LLMforFrugalAI \n \n\n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nErwan Bigan\, co-founder at TinyPred \nMachine Learning (ML) on tabular data mostly relies upon conventional algorithms like Logistic Regression\, Random Forest\, or gradient-boosted decision trees. \nAlthough there is no golden rule to determine how much data is actually required to train robust ML models\, it is generally believed that at least several hundreds or thousands of samples are needed for most practical applications\, thus restricting possible use cases. \nTinyPred has came up with a different approach : the use of Large Language Models for ML on tabular data. This method can require up to 5-10x fewer training data than traditional ML\, for the same predictive strength. The reason for better performance is that\, beyond inferring statistical patterns just like machine learning\, they benefit from their general knowledge expertise\, which allows them to interpret the data. \nIn this workshop\, we will :\n– Discuss new industrial use cases enabled by this LLM-based ML approach;\n– Present results obtained on published datasets\, which confirm the performance advantage for open source as well as proprietary LLMs;\n– Position this LLM-based ML approach in the broader context of foundational models for tabular ML: new pre-trained numerical deep learning models (e.g.\, TabICL\, TabPFN) have also been shown to deliver superior performance\, but for train sizes of several thousands of samples. URL:https://datacraft.paris/event/machine-learning-on-tabular-data-using-llms/ LOCATION:Scaleway –\, 11bis Rue Roquépine\, Paris\, 75008\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250923T150000 DTEND;TZID=Europe/Paris:20250923T180000 DTSTAMP:20260613T032408 CREATED:20250721T080055Z LAST-MODIFIED:20250916T100545Z UID:15838-1758639600-1758650400@datacraft.paris SUMMARY:Introduction to Rust for Python: Speed Up Your Code with PyO3 Rust Bindings DESCRIPTION:2509-datacraft-Rust4Python \n \n\n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nFonction*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n  \nRecently\, Rust has gained more and more popularity as a Programming Language for two reasons:\n– Rust is really fast (comparable to C++)\n– Rust is secure (safer than C++) \nBut more importantly\, there is one Rust feature that made it a clear game-changer for us\, data experts: It is highly integrated within the Python ecosystem\, thanks to PyO3\, which is called a Rust binding for Python.\nEssentially\, PyO3 allows developers to easily compile and import Rust code as Python modules. \nIn this workshop\, we will introduce you to:\n1. Basics of Rust – Understanding the language essentials (30-40 min)\n2. Usage of Cargo – Rust’s package manager (10 min)\n3. Usage of PyO3 to compile Rust code and use it in a Python script (20-30 min)\n4. Follow-along full working example: finding the nearest neighbors of a large number of polygons (100x speedup compared to naive python) – (40-60 min)\n5. Additional demos on ML algorithms: KMeans\, Multi-Label Stratification.. (30-40 min) \nResources:\n– https://msrc.microsoft.com/blog/2019/07/a-proactive-approach-to-more-secure-code/\n– https://benchmarksgame-team.pages.debian.net/benchmarksgame/fastest/rust.html URL:https://datacraft.paris/event/introduction-to-rust-for-python-speed-up-your-code-with-pyo3-rust-bindings/ LOCATION:Zenika –\, 53 rue de Châteaudun\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250826T150000 DTEND;TZID=Europe/Paris:20250826T180000 DTSTAMP:20260613T032408 CREATED:20250623T131149Z LAST-MODIFIED:20250718T131741Z UID:15264-1756220400-1756231200@datacraft.paris SUMMARY:Workshop GenAI - Building AI Agents and MCP Servers DESCRIPTION:2508-datacraft-AIAgents \n \n\n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nDuring this hands-on workshop where we’ll explore how to build AI agents using the open-source smolagents library.\nYou’ll learn how to structure agentic workflows\, connect tools and APIs\, and orchestrate decision-making using lightweight\, composable components.\nWe’ll also discover how to build our own MCP servers with custom tools\, and integrate them within Agentic workflows.\nWhether you’re curious about agent systems or eager to implement your own\, this session is the perfect place to start experimenting and building. URL:https://datacraft.paris/event/workshop-genai-building-ai-agents-with-smolagents/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250819T150000 DTEND;TZID=Europe/Paris:20250819T180000 DTSTAMP:20260613T032408 CREATED:20250623T130426Z LAST-MODIFIED:20250623T131951Z UID:15260-1755615600-1755626400@datacraft.paris SUMMARY:Workshop Trustable AI - Model Calibration: Reliable Model Probabilities DESCRIPTION:2508-datacraft-ModelCalibration \n \n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nIn this hands-on session\, we’ll discover the often overlooked but essential topic of model calibration in machine learning.\nYou will explore what it means for a model to be calibrated\, why it matters in real-world applications\, and how to evaluate and improve calibration using practical tools and techniques.\nThrough collaborative coding and experimentation\, we’ll compare calibrated and non-calibrated models to see the impact on decision-making and performance. URL:https://datacraft.paris/event/workshop-trustable-ai-model-calibration-reliable-model-probabilities/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250709T150000 DTEND;TZID=Europe/Paris:20250709T180000 DTSTAMP:20260613T032408 CREATED:20250623T124729Z LAST-MODIFIED:20250630T120502Z UID:15256-1752073200-1752084000@datacraft.paris SUMMARY:Workshop Pydantic - Data Validation using Python Type Hints DESCRIPTION:2507-datacraft-Pydantic \n \n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nIn this workshop\, we’ll work with Pydantic\, a powerful Python library for data validation and schema management. \nPydantic is what you need if you’re tired of writing classes the old way in Python: you’ll learn how to close the gap with production-ready code that you don’t fear to put into production. URL:https://datacraft.paris/event/workshop-pydantic-data-validation-using-python-type-hints/ LOCATION:Le Village By CA –\, 55 rue la Boétie\, 75008 Paris\, 75008\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250625T150000 DTEND;TZID=Europe/Paris:20250625T170000 DTSTAMP:20260613T032408 CREATED:20250401T133857Z LAST-MODIFIED:20250612T093205Z UID:14776-1750863600-1750870800@datacraft.paris SUMMARY:Workshop Vendee Globe: Build your async API & live dashboard DESCRIPTION:2506-Fran6-VendeeGlobe \n \n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nFrancis Wolinski\, Freelance Data Scientist & Jeanne Gautier\, Data Scientist at datacraft \nReady to set sail around the world… with code? 🚤 \nIn this hands-on technical workshop inspired by the Vendée Globe\, you’ll build an asynchronous API capable of collecting\, processing\, and broadcasting real-time skipper positions. You’ll learn how to design a robust architecture using FastAPI\, handle background tasks with async/await\, and expose data through a REST API. \nBut that’s not all! You’ll also create a real-time dashboard to visualize the boat race live\, using HTTP requests. This immersive workshop blends modern backend development\, dynamic visualization\, and real-time architecture. \nWhat you’ll learn:\n • Asynchronous API with FastAPI\n • Background tasks & event handling\n • HTTP requests\n • Real-time data display via an interactive dashboard \nWho it’s for: backend or fullstack developers\, data engineers\, data scientists and anyone curious about real-time applications. URL:https://datacraft.paris/event/workshop-vendee-globe-build-your-async-api-live-dashboard/ LOCATION:Le Village By CA –\, 55 rue la Boétie\, 75008 Paris\, 75008\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250618T173000 DTEND;TZID=Europe/Paris:20250618T183000 DTSTAMP:20260613T032409 CREATED:20250401T074158Z LAST-MODIFIED:20250611T103618Z UID:14766-1750267800-1750271400@datacraft.paris SUMMARY:Paper Reading Group #2 DESCRIPTION:2504-datacraft-PaperReadingGroup \n \n\n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nLooking for speakers\, reach out at tech@datacraft.paris \nWe are happy to announce a new episode of our Paper Reading Group! \nFor this session\, we are looking for people willing to present a paper of their choice.\nOne or two papers will be presented during this session. \nThe guidelines for the presentations are the following:\n– short\, light\, simple and straight to the point\n– In English\n– interactive\n– 20-min long (excluding questions) \nWork presented in this edition:\n– Biomni: A General-Purpose Biomedical AI Agent\, by Guillaume de Luca\, Head of Data @ ZebraMed \nIf you’re interested in presenting a paper for the first edition\, reach out at tech@datacraft.paris URL:https://datacraft.paris/event/paper-reading-group-2/ LOCATION:Le Village By CA –\, 55 rue la Boétie\, 75008 Paris\, 75008\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250604T140000 DTEND;TZID=Europe/Paris:20250604T170000 DTSTAMP:20260613T032409 CREATED:20250307T085814Z LAST-MODIFIED:20250528T110142Z UID:14591-1749045600-1749056400@datacraft.paris SUMMARY:Workshop: measure your models uncertainty thanks to MAPIE\, the conformal predictions library DESCRIPTION:2506-Capgemini-MAPIE \n \n\n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecte\nJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\n\nPrénom*\n\nEmail*\n\nMétier*\n\nEntreprise*\n\nLinkedIn\n\nComment connaissez vous datacraft ?\n\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading…\n \nVous êtes bien inscrit !\nNous vous avons envoyé un save-the-date par email. \n\n \nValentin Laurent\, MAPIE lead developer\, Capgemini Invent – Grégoire Martinon\, MAPIE co-founder\, Capgemini Invent. \nLearn how measure your models uncertainty by computing prediction intervals (regression) and prediction sets (classification)\, using conformal predictions. \nDuring this workshop\, you will: \n\nLearn practical skills in conformal predictions thanks to MAPIE\, with a deep dive on a regression use-case\nBe able to discuss your use cases\, and potentially schedule in-depth follow-ups\nGet an exclusive preview of the upcoming MAPIE v1\n\nAgenda: \n\nIntroduction to the MAPIE project\nHands-on tutorial\nHands-on use case\nWrap-up\nDedicated discussion time URL:https://datacraft.paris/event/workshop-measure-your-models-uncertainty-thanks-to-mapie-the-conformal-predictions-library/ LOCATION::probabl. –\, 33 avenue du Maine\, 75015 Paris\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250424T183000 DTEND;TZID=Europe/Paris:20250424T210000 DTSTAMP:20260613T032409 CREATED:20250312T103100Z LAST-MODIFIED:20250401T075059Z UID:14609-1745519400-1745528400@datacraft.paris SUMMARY:neurons & peppers #1 DESCRIPTION:Neurons & Peppers is THE State of the art AI meetup \nFor the meetup launch\, we gathered two top-notch speakers:\n– ​Manuel Faysse\, PhD Candidate & Research Scientist at Illuin Technologies; ColPali: Efficient Document Retrieval with Vision Language Models\n– ​Pierre Fernandez\, Research Scientist at Meta; WAM: Watermark Anything with Localized Messages\n​Presentations will be followed by drinks & food 🌶️ \nInscription URL:https://datacraft.paris/event/neurons-peppers-1/ CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250407T190000 DTEND;TZID=Europe/Paris:20250407T200000 DTSTAMP:20260613T032409 CREATED:20250219T150934Z LAST-MODIFIED:20250403T074701Z UID:14369-1744052400-1744056000@datacraft.paris SUMMARY:Architecture of a multi-agent system for a conversational assistant DESCRIPTION:2504-Maret-AgenticECommerce \n \n\n \nInscription\n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\nPrésentiel\nDistanciel\n\nValider inscription \n\n \nJe suis membre\, je me connecteJe ne suis pas membre mais souhaite quand même participer\n \n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n\n\nNom*\nPrénom*\nEmail*\nMétier*\nEntreprise*\nLinkedIn\nComment connaissez vous datacraft ?\n\nSouhaitez-vous participer en présentiel ou distanciel ? \nPrésentiel\nDistanciel\n\n\nValider inscription \n\nLoading… \nVous êtes bien inscrit !Nous vous avons envoyé un save-the-date par email. \n\n \nAdrien Maret and Luca Marchesini\, LLM Engineers at Spiriit \nReproducing the flexibility of human behaviors with LLMs while maintaining a good level of accuracy requires working with a system composed of several specialized agents. \nIn this REX\, we will see how the use of LangGraph provides the formalism necessary to create and maintain a robust multi-agent system in the context of a consumer e-commerce Assistant. URL:https://datacraft.paris/event/architecture-of-a-multi-agent-system-for-a-conversational-assistant/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250319T173000 DTEND;TZID=Europe/Paris:20250319T183000 DTSTAMP:20260613T032409 CREATED:20250124T090059Z LAST-MODIFIED:20250306T091439Z UID:13943-1742405400-1742409000@datacraft.paris SUMMARY:Paper Reading Group #1 DESCRIPTION:nomenclature \n \n\n \n\n Inscription\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n\n Présentiel\n \n\n Distanciel\n \n\n Valider inscription\n \n \n\n Je suis membre\, je me connecte\n Je ne suis pas membre mais souhaite quand même participer\n \n \n\n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n \n\n\n\n Nom\n \n \n\n Prénom\n \n \n\n Email\n \n \n\n Métier\n \n \n\n Entreprise*\n \n \n\n LinkedIn\n \n \n\n Comment connaissez vous datacraft ?\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n Présentiel\n \n\n Distanciel\n \n \n\n Valider inscription\n \n Loading…\n \nVous êtes bien inscrit !\n Nous vous avons envoyé un save-the-date par email. \n \n \nWe are happy to launch our Paper Reading Group! \nFor this first session\, we are looking for people willing to present a paper of their choice. \nOne or two papers will be presented during this session. \nThe guidelines for the presentations are the following:\n– short\, light\, simple and straight to the point\n– In English\n– interactive\n– 20-min long (excluding questions) \nHere’s the lineup for the first edition:\n– MemGPT\, presented by Mohamed DHIFALLAH\, Masters student at Paris Dauphine University \nIf you’re interested in presenting a paper for the first edition\, reach out at tech@datacraft.paris \nHere are some GenAI papers suggestions one can tackle for example: https://www.latent.space/p/2025-papers URL:https://datacraft.paris/event/paper-reading-group-1/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250313T093000 DTEND;TZID=Europe/Paris:20250313T180000 DTSTAMP:20260613T032409 CREATED:20250114T174120Z LAST-MODIFIED:20250306T091316Z UID:13874-1741858200-1741888800@datacraft.paris SUMMARY:Workshop: Forecast Parking Fraud High-Risk Areas DESCRIPTION:nomenclature \n \n\n \n\n Inscription\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n\n Présentiel\n \n\n Distanciel\n \n\n Valider inscription\n \n \n\n Je suis membre\, je me connecte\n Je ne suis pas membre mais souhaite quand même participer\n \n \n\n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n \n\n\n\n Nom\n \n \n\n Prénom\n \n \n\n Email\n \n \n\n Métier\n \n \n\n Entreprise\n \n \n\n LinkedIn\n \n \n\n Comment connaissez vous datacraft ?\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n Présentiel\n \n\n Distanciel\n \n \n\n Valider inscription\n \n Loading…\n \nVous êtes bien inscrit !\n Nous vous avons envoyé un save-the-date par email. \n \n \nEgis and datacraft collaborated to propose a challenge to the challenge data ENS platform: https://challengedata.ens.fr/challenges/163 \nIn this workshop\, participants will work on this challenge and try to propose a machine learning model able to accurately predict the parking fraud rate in a specific area\, at a specific time. \nThe participants will build models incorporating data such as weather data\, past fraud rate for the specific zone and its neighbors\, as well as date features. \nBy the end of this workshop\, participants will be able to make their first contribution to the leaderboard of this challenge\, share their approach as well as being able to ask questions to the challenge organizers. URL:https://datacraft.paris/event/workshop-forecast-parking-fraud-high-risk-areas/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250310T170000 DTEND;TZID=Europe/Paris:20250310T190000 DTSTAMP:20260613T032409 CREATED:20250117T150008Z LAST-MODIFIED:20250306T091259Z UID:13888-1741626000-1741633200@datacraft.paris SUMMARY:Workshop: Building a text processing engine with MAIF open-source tools DESCRIPTION:nomenclature \n \n\n \n\n Inscription\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n\n Présentiel\n \n\n Distanciel\n \n\n Valider inscription\n \n \n\n Je suis membre\, je me connecte\n Je ne suis pas membre mais souhaite quand même participer\n \n \n\n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n \n\n\n\n Nom\n \n \n\n Prénom\n \n \n\n Email\n \n \n\n Métier\n \n \n\n Entreprise\n \n \n\n LinkedIn\n \n \n\n Comment connaissez vous datacraft ?\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n Présentiel\n \n\n Distanciel\n \n \n\n Valider inscription\n \n Loading…\n \nVous êtes bien inscrit !\n Nous vous avons envoyé un save-the-date par email. \n \n \nIn this workshop\, you will discover two of MAIF’s open source projects and learn how to use them. \nFirst\, you will play with Melusine (https://github.com/MAIF/melusine) and build a processing pipeline from scratch to extract insights from emails.\nThen\, you will use Arta (https://github.com/MAIF/arta)  and business rules to refine them into actionable business data.\n_ _\nThis workshop is 100% Python code and will be animated by the repos’ maintainers. Packages like pandas and Pydantic will be used. URL:https://datacraft.paris/event/workshop-building-a-text-processing-engine-with-maif-open-source-tools/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250220T093000 DTEND;TZID=Europe/Paris:20250220T120000 DTSTAMP:20260613T032409 CREATED:20241210T145314Z LAST-MODIFIED:20250211T132538Z UID:13628-1740043800-1740052800@datacraft.paris SUMMARY:Workshop: Hands-on LLM Watermarking DESCRIPTION:Inscription\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n\n Présentiel\n \n\n Distanciel\n \n\n Valider inscription\n \n \n\n Je suis membre\, je me connecte\n Je ne suis pas membre mais souhaite quand même participer\n \n \n\n \n Connectez-vous pour vous inscrire à cet atelier. \n \n Email *Password / Mot de passe *J’ai oublié mon mot de passe Remember MeLogin / Se connecter\n J’ai oublié mon mot de passe \n Votre mot de passe vous a été envoyé par mail lors de votre\n inscription au club. Vous pouvez le réinitialiser en cliquant sur le lien\n ci-dessous :\n Réinitialiser son mot de passe\n \n \n \n \n \n \n\n\n\n Nom\n \n \n\n Prénom\n \n \n\n Email\n \n \n\n Métier\n \n \n\n Entreprise\n \n \n\n LinkedIn\n \n \n\n Comment connaissez vous datacraft ?\n \n \n\nSouhaitez-vous participer en présentiel ou distanciel ? \n\n Présentiel\n \n\n Distanciel\n \n \n\n Valider inscription\n \n Loading…\n \nVous êtes bien inscrit !\n Nous vous avons envoyé un save-the-date par email. \n \n \nThis event is reserved for our members\, but we still have a few places available for those who would like to discover the club.\nDon’t hesitate to sign up – you’ll be put on a waiting list and we’ll confirm your place a days before the event. \nPierre Fernandez\, Research Scientist at Meta \nIn this workshop\, we will (re)-discover LLM watermarking\, this time in practice. Pierre Fernandez (Research Scientist at Meta) will:\n– help you better understand the difference between passive and active detectors through a demonstration of passive detection tools.\n– guide you through the implementation of the greenlist/redlist watermarking technique\, which is employed by LLM providers to watermark outputs.\n– accompany you into the development of an interactive web app\, which will showcase the active detector you built before. \nAt the end of this workshop\, you’ll have gained insights into:\n– how passive/active detectors work and their robustness\, differences\, limitations..\n– understanding how LLM watermarking is performed in practice. URL:https://datacraft.paris/event/workshop-hands-on-llm-watermarking/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250205T193000 DTEND;TZID=Europe/Paris:20250205T213000 DTSTAMP:20260613T032409 CREATED:20250130T085350Z LAST-MODIFIED:20250130T090108Z UID:14069-1738783800-1738791000@datacraft.paris SUMMARY:Open and Trusted AI: What Do We Need to Make it Real? DESCRIPTION:Click here to register to this networking event hosted in Meta’s Paris office: luma event \n​About the Open Trusted Data Initiative (OTDI)\nJoin The AI Alliance\, Open Trusted Data Initiative (OTDI)\, where our mission is to create a comprehensive\, widely-sourced catalog of datasets with clear licenses for use\, explicit provenance guarantees\, and governed transformations\, intended for AI model training\, tuning\, and application patterns like RAG (retrieval augmented generation) and agents. In our context trusted data means the provenance and governance of the dataset is clear and unambiguous. The metadata about the dataset provides clarity about its intended purposes\, safety\, and other considerations\, along with any filtering and other processing steps that were done on the dataset.\n​About the AI Alliance\nThe AI Alliance is an international community of researchers\, developers and organizational leaders committed to support and enhance open innovation across the AI technology landscape to accelerate progress\, improve safety\, security and trust in AI\, and maximize benefits to people and society everywhere. Members of the AI Alliance believe that open innovation is essential to develop and achieve safe and responsible AI that benefit society rather than benefit a select few big players. URL:https://datacraft.paris/event/open-and-trusted-ai-what-do-we-need-to-make-it-real/ LOCATION:Meta –\, 6 rue Ménars\, Paris\, 75002\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250204T080000 DTEND;TZID=Europe/Paris:20250205T200000 DTSTAMP:20260613T032409 CREATED:20250128T132623Z LAST-MODIFIED:20250128T133149Z UID:14012-1738656000-1738785600@datacraft.paris SUMMARY:GeoAI Hack DESCRIPTION:Take part in the GeoAI Hack challenge on 4 and 5 February\, co-organised by datacraft and InstaDeep as part of the AI Convergence Challenge at the AI Action Summit. 🚀 \nThe challenge will take place at Agence Française du Développement\, 3\, Place Louis Armand – Paris 75012. \nThis will be an opportunity to work with satellite images to address issues such as detecting the location of desert locust nesting sites in Africa\, mapping flood damage\, etc. \nSkills that are good to have to participate: data science\, computer vision\, geospatial machine learning // web development to build a demonstrator // knowledge on food security issues and natural disasters in Africa is a big plus 🌍✨ \n🌟 The winning team will be presented in the official programme of the AI Action Summit on 10 February at the Grand Palais. \nVisit our site: https://geoaihack.com/ URL:https://datacraft.paris/event/geo-ai-hack/ LOCATION:Agence Française du Développement –\, 3 Place Louis Armand\, Paris\, 75012\, France CATEGORIES:in English,on-site event END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20250115T183000 DTEND;TZID=Europe/Paris:20250115T193000 DTSTAMP:20260613T032409 CREATED:20241022T143320Z LAST-MODIFIED:20250108T162547Z UID:13258-1736965800-1736969400@datacraft.paris SUMMARY:REX: How to monitor GenAI tools in production DESCRIPTION:2411-phospho-Observability\n \n\n \n\n\n \n \n Inscription\n \n \n \nDiscover through real use cases the best practices to monitor LLM apps in production. URL:https://datacraft.paris/event/rex-how-to-monitor-genai-tools-in-production/ LOCATION:Le Village By CA –\, 55 rue la Boétie\, 75008 Paris\, 75008\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20241210T140000 DTEND;TZID=Europe/Paris:20241210T180000 DTSTAMP:20260613T032409 CREATED:20240910T081234Z LAST-MODIFIED:20241204T141636Z UID:12756-1733839200-1733853600@datacraft.paris SUMMARY:Get insights from LLM chat data and monitor semantic drift DESCRIPTION:2406-Bunka-Bunka \n \n\n \n\n\n \n \n Inscription\n \n \n \nDescription \n\nIn the rapidly growing landscape of ChatGPT-like applications\, Retrieval-Augmented Generation (RAG) solutions are gaining significant traction. However\, analyzing the user-generated data from these applications to extract meaningful insights and adapt to emerging trends is a complex challenge. \nThis workshop introduces Bunka\, an open-source library designed for intuitive exploration and visualization of unstructured datasets. Using Bunka\, participants will explore embeddings in simplified projections\, empowering them to uncover hidden patterns and track semantic drift effectively. \nWe will work with a unique\, anonymized dataset of recently leaked chat channels from Andrew Tate’s private community\, tackling real-world challenges to extract actionable insights. The session will focus on techniques to:• Analyze user behavior and emerging trends in chat data.• Monitor semantic drift and its impact on application performance.• Adaptively predict and respond to new themes and trends. \nBy the end of this hands-on workshop\, you’ll gain practical experience with embedding-based analysis and actionable insights into leveraging semantic monitoring to enhance your LLM-driven applications. \n\nJoin us by registering now ! URL:https://datacraft.paris/event/exploring-filtering-datasets-for-llm-fine-tuning/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English ORGANIZER;CN="datacraft":MAILTO:contact@datacraft.paris END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20241204T090000 DTEND;TZID=Europe/Paris:20241204T180000 DTSTAMP:20260613T032409 CREATED:20241008T132124Z LAST-MODIFIED:20241104T143320Z UID:12994-1733302800-1733335200@datacraft.paris SUMMARY:Unlocking Vector Databases : Search and RAG with Vespa DESCRIPTION:Inscription\n \n \n \n2412-Vespa-VectorSearch \nIn this workshop\, we will dive in Vector Databases using Vespa\, an open-source search engine and vector/tensor DB used in various major projects such as Spotify or Vinted recommandation system. The objective is to give participants tools to work on various use-cases form E-commerce search to recommendations and RAG. \nThe workshop is made of 6 main chapters : \n\nIntroduction: 10km view of the use-cases and anti-use-cases for Vespa and why. Lab will be centered around CRUD\nLexical Search: query syntax\, boolean clauses\, ranking for product search\nGrouping: facets for data exploration on sales data and result diversification\nTensors: use tensor math for recommendations and vector search on an E-commerce dataset\nHybrid Search: generate embeddings on the fly; use RRF; implement RAG\nPerformance and scaling: intro to how Vespa scales; typical performance bottlenecks\n\nEach chapter is composed of : \n\n a short introduction to the topic\na lab that will be solved in small groups\, working on a pre-defined dataset\na debriefing with the large group\nshort wrap-up\n\nWarning : Even though online attendance is opened for this event\, we highly encourage participants to attend on site to get the most out of this event (participants will form groups and work together during the workshop). URL:https://datacraft.paris/event/unlocking-vector-databases-search-and-rag-with-vespa/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT BEGIN:VEVENT DTSTART;TZID=Europe/Paris:20241115T150000 DTEND;TZID=Europe/Paris:20241115T170000 DTSTAMP:20260613T032409 CREATED:20241016T152153Z LAST-MODIFIED:20241016T170520Z UID:13195-1731682800-1731690000@datacraft.paris SUMMARY:Responsible Prompting – Real-Time Prompt Recommendation DESCRIPTION:2411-IBM-ResponsiblePrompting\n \n\n \n\n\n \n \n Inscription\n \n \n \n\nJoin us for a demo and a hands-on exercise with this open-source tool called Responsible Prompting\, developed by the Responsible Tech Team\, IBM Research. This tool supports your LLM users in crafting more responsible prompts by recommending good practices and preventing harmful prompts by leveraging the semantics mapping provided by sentence transformers. The recommendations are provided in prompting-time\, i.e.\, before users send the prompt to an LLM. Hence\, for many tasks\, it has the potential to speed up prompting tasks\, improve the quality of prompts\, and even reduce costs. The tool was designed to be easy to customize to different business cases. And it’s even possible go even further by fine-tuning the backbone sentence transformers models.We will go through the following steps:\n– Quick demo of the tool (10 min)\n– Deep dive into the project history and underlying model (sentence transformers) (20 min)\n– Discussion on how it can help businesses (esp. big companies) support their users and diminish the misuses of these technologies. (10 min)\n– Conclusion\, question and discussion with the attendees (10-20 min)(optional) Bonus: a hands-on exercise for customizing the tool (60 minutes).\nThis event will be in English and in hybrid format. URL:https://datacraft.paris/event/responsible-prompting-real-time-prompt-recommendation/ LOCATION:datacraft –\, 3 rue Rossini\, 75009 Paris\, France CATEGORIES:Hybrid event,in English END:VEVENT END:VCALENDAR