{"id":48822140,"url":"https://github.com/intersystems-ib/workshop-llm","last_synced_at":"2026-04-14T15:34:32.998Z","repository":{"id":259425261,"uuid":"868875540","full_name":"intersystems-ib/workshop-llm","owner":"intersystems-ib","description":"🧠 Hands-on RAG workshop using InterSystems IRIS \u0026 LLMs - Build PDF Q\u0026A systems, natural language-to-SQL interfaces, and learn AI agent architecture with local/cloud options","archived":false,"fork":false,"pushed_at":"2025-11-06T09:54:30.000Z","size":1936,"stargazers_count":0,"open_issues_count":0,"forks_count":2,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-11-06T11:26:07.489Z","etag":null,"topics":["ai-workshop","intersystems-iris","jupyter-notebooks","langchain","llm","mistral-ai","openai","pdf-qa","python","rag","text-to-sql","transformers","vector-database"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/intersystems-ib.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-10-07T10:40:06.000Z","updated_at":"2025-11-06T09:54:34.000Z","dependencies_parsed_at":"2025-01-07T13:19:05.886Z","dependency_job_id":"7d49bc8e-6a91-4b9e-b30f-83a1de99a51d","html_url":"https://github.com/intersystems-ib/workshop-llm","commit_stats":null,"previous_names":["intersystems-ib/workshop-llm"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/intersystems-ib/workshop-llm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intersystems-ib%2Fworkshop-llm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intersystems-ib%2Fworkshop-llm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intersystems-ib%2Fworkshop-llm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intersystems-ib%2Fworkshop-llm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/intersystems-ib","download_url":"https://codeload.github.com/intersystems-ib/workshop-llm/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/intersystems-ib%2Fworkshop-llm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31803605,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-14T11:13:53.975Z","status":"ssl_error","status_checked_at":"2026-04-14T11:13:53.299Z","response_time":153,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-workshop","intersystems-iris","jupyter-notebooks","langchain","llm","mistral-ai","openai","pdf-qa","python","rag","text-to-sql","transformers","vector-database"],"created_at":"2026-04-14T15:34:32.331Z","updated_at":"2026-04-14T15:34:32.990Z","avatar_url":"https://github.com/intersystems-ib.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 LLM Workshop with InterSystems IRIS\n\nWelcome to the **Retrieval-Augmented Generation (RAG)** workshop! 🚀 This hands-on experience will teach you how to build intelligent AI applications that combine the power of Large Language Models with vector databases using InterSystems IRIS.\n\n## 🎯 What You'll Learn\n\nIn this workshop, you'll become a **RAG wizard** by building three different types of AI applications:\n\n1. **📄 PDF Question-Answering Systems** - Make documents talk! Transform static PDFs into interactive knowledge bases\n2. **🔍 Natural Language to SQL** - Speak to databases in plain English (or Spanish!) and get intelligent responses\n3. **🤖 Complete AI Agent Architecture** - Understand how to build production-ready AI agents\n\nThis workshop is developed in Python 🐍 (Jupyter Notebook) and **InterSystems IRIS** - because why settle for ordinary databases when you can have one that speaks vector? 😉\n\n## 🛠️ Prerequisites \n\nMake sure you have these tools ready for battle:\n\n* [Git](https://git-scm.com/downloads) 📦\n* [Docker](https://www.docker.com/products/docker-desktop) 🐳 (Windows users: enable \"Linux containers\")\n* [Docker Compose](https://docs.docker.com/compose/install/) 🎼\n* [Visual Studio Code](https://code.visualstudio.com/download) + [InterSystems ObjectScript Extension](https://marketplace.visualstudio.com/items?itemName=daimor.vscode-objectscript) 🔧\n\n## 🚀 Setup \u0026 Launch\n\nTime to bring this beast to life! 💪\n\n**1. Clone the repository:**\n```bash\ngit clone https://github.com/intersystems-ib/workshop-llm\ncd workshop-llm\n```\n\n**2. Build the image:**\n```bash\ndocker compose build\n```\n\n**3. Launch the containers:**\n```bash\ndocker compose up -d\n```\n\n**4. Access your AI playground:**\n* 🎛️ **InterSystems IRIS Management Portal**: [http://localhost:52774/csp/sys/UtilHome.csp](http://localhost:52774/csp/sys/UtilHome.csp)\n  - Login: `superuser` / `SYS`\n* 📓 **Jupyter Notebook**: [http://localhost:8888](http://localhost:8888)\n\n## 🧪 Workshop Exercises\n\n### 💊 Medicine Leaflet Q\u0026A (PDF RAG Systems)\n\nTransform boring medical documents into an intelligent assistant! Using Spanish medicine leaflets in [./data](./data), you'll build systems that can answer questions like a knowledgeable pharmacist. 💊\n\n**Choose your adventure:**\n\n* **📄 [PDF-RAG-CloudLLM.ipynb](./jupyter/PDF-RAG-CloudLLM.ipynb)** - Cloud-powered RAG using [Mistral AI](https://mistral.ai) \n  - *Perfect for: Production systems, highest accuracy, API-based*\n  \n* **🏠 [PDF-RAG-LocalModels.ipynb](./jupyter/PDF-RAG-LocalModels.ipynb)** - Privacy-first with local models\n  - *Perfect for: Complete privacy, offline operation, no API costs*\n\n![Jupyter Interface](/images/jupyter.png)\n\n### 🍩 Holefoods Text-to-SQL Adventure\n\nMeet **Holefoods** - a quirky company that sells food with holes in it! 🍩 (Creative, right?)\n\nBuild an intelligent SQL assistant that translates natural language into database queries. Ask questions like *\"How many donuts did we sell in Europe last month?\"* and watch the magic happen! ✨\n\n* **🗣️ [NaturalLanguage-to-SQL.ipynb](./jupyter/NaturalLanguage-to-SQL.ipynb)** - Your multilingual database whisperer\n  - *Features: Semantic similarity, few-shot learning, IRIS SQL optimization*\n\n## 🌟 Inspiration: Full AI Agent Demo\n\nWant to see the full power of AI agents in action? Check out this **complete customer support agent** built with **smolagents** and **InterSystems IRIS**:\n\n🔗 **[Customer Support AI Agent Demo](https://github.com/intersystems-ib/customer-support-agent-demo)**\n\n📖 **[Developer Community Article](https://community.intersystems.com/post/build-customer-support-ai-agent-smolagents-intersystems-iris-sql-rag-interoperability)** - Deep dive explanation\n\nThis demo showcases:\n- 🤖 **Autonomous AI agents** that can reason and take actions\n- 📊 **SQL + RAG integration** for comprehensive data access\n- 🔄 **InterSystems IRIS interoperability** for enterprise-grade systems\n- 🎯 **Production-ready architecture** you can actually deploy\n\n## 🛠️ Advanced: Local Development Environment\n\nReady to build your own AI applications? Set up a local Python environment:\n\n**For Mac/Linux users:**\n```bash\ncd python\npython3 -m venv .venv\nsource .venv/bin/activate\npip3 install -r requirements.txt\n```\n\n**For Windows users:**\n```bash\ncd python\npython -m venv .venv\n./.venv/Scripts/Activate.ps1\npip3 install -r requirements.txt\n```\n\n**Create your API keys file:**\n```bash\n# Create .env file\necho 'OPENAI_API_KEY=\"your-openai-key\"' \u003e .env\necho 'MISTRAL_API_KEY=\"your-mistral-key\"' \u003e\u003e .env\n```\n\n### 🌐 Text-to-SQL API Service\nWant to productionize your SQL skills? Try our FastAPI service based on the notebook:\n\n```bash\ncd python/holefoods_text2sql\nfastapi dev main.py\n```\n🌍 **Explore the API**: [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)\n\n### 💬 Streamlit Chatbot Assistant\nExperience a beautiful chat interface:\n\n```bash\ncd python/assistant\nstreamlit run chatbot.py\n```\n🎨 **Chat away**: [http://localhost:8501](http://localhost:8501)\n\n**Challenge:** Can you integrate the medicine leaflet logic into this assistant? 🤔\n\n## 🎓 Learning Resources\n\nWant to dive deeper into the InterSystems universe?\n- 📚 **[InterSystems Learning](https://learning.intersystems.com)** - Your gateway to mastery\n- 🏛️ **[InterSystems IRIS Documentation](https://docs.intersystems.com/iris/)** - The sacred texts\n- 👥 **[Developer Community](https://community.intersystems.com/)** - Where the magic happens\n\n## 🎉 Ready to Build the Future?\n\nYou're now equipped with the knowledge to build:\n- 🔮 **Intelligent document systems** that understand context\n- 🗣️ **Natural language database interfaces** that feel like magic\n- 🤖 **Complete AI agents** that can reason and act autonomously\n\n**Go forth and create amazing AI applications!** The only limit is your imagination! 🚀✨\n\n---","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintersystems-ib%2Fworkshop-llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fintersystems-ib%2Fworkshop-llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fintersystems-ib%2Fworkshop-llm/lists"}