{"id":47072257,"url":"https://github.com/gperdrizet/llms-demo","last_synced_at":"2026-04-01T17:21:08.947Z","repository":{"id":343832655,"uuid":"1179319880","full_name":"gperdrizet/llms-demo","owner":"gperdrizet","description":"Demonstration of LLM hosting strategies and framesworks for simple chatbots","archived":false,"fork":false,"pushed_at":"2026-03-26T02:13:07.000Z","size":5767,"stargazers_count":0,"open_issues_count":0,"forks_count":14,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-26T22:18:34.581Z","etag":null,"topics":["chatbot","generative-ai","huggingface-transformers","langchain","llms","ollama"],"latest_commit_sha":null,"homepage":"https://gperdrizet.github.io/llms-demo/","language":"Python","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/gperdrizet.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":"2026-03-11T23:05:22.000Z","updated_at":"2026-03-26T02:13:11.000Z","dependencies_parsed_at":"2026-03-15T09:00:47.670Z","dependency_job_id":null,"html_url":"https://github.com/gperdrizet/llms-demo","commit_stats":null,"previous_names":["gperdrizet/llms-demo"],"tags_count":4,"template":false,"template_full_name":"gperdrizet/deeplearning-GPU","purl":"pkg:github/gperdrizet/llms-demo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gperdrizet%2Fllms-demo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gperdrizet%2Fllms-demo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gperdrizet%2Fllms-demo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gperdrizet%2Fllms-demo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gperdrizet","download_url":"https://codeload.github.com/gperdrizet/llms-demo/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gperdrizet%2Fllms-demo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31013959,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-27T02:58:54.984Z","status":"ssl_error","status_checked_at":"2026-03-27T02:58:46.993Z","response_time":164,"last_error":"SSL_read: 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":["chatbot","generative-ai","huggingface-transformers","langchain","llms","ollama"],"created_at":"2026-03-12T06:08:39.905Z","updated_at":"2026-03-27T03:09:03.599Z","avatar_url":"https://github.com/gperdrizet.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM chatbots demo\n\n[![Build and Deploy Documentation](https://github.com/gperdrizet/llms-demo/actions/workflows/docs.yml/badge.svg)](https://github.com/gperdrizet/llms-demo/actions/workflows/docs.yml)\n![Python](https://img.shields.io/badge/Python-3.11-3776AB?logo=python\u0026logoColor=white)\n![LangChain](https://img.shields.io/badge/LangChain-1.2-1C3C3C?logo=langchain\u0026logoColor=white)\n![HuggingFace](https://img.shields.io/badge/HuggingFace-Transformers-FF6B00?logo=huggingface\u0026logoColor=white)\n![Gradio](https://img.shields.io/badge/Gradio-UI-FF7C00?logo=gradio\u0026logoColor=white)\n![Ollama](https://img.shields.io/badge/Ollama-local%20LLM-black?logo=ollama\u0026logoColor=white)\n![llama.cpp](https://img.shields.io/badge/llama.cpp-GGUF-green)\n![PostgreSQL](https://img.shields.io/badge/pgvector-PostgreSQL-4169E1?logo=postgresql\u0026logoColor=white)\n![ChromaDB](https://img.shields.io/badge/ChromaDB-vector%20store-E8572A)\n\n## Introduction\n\nThis repository provides hands-on examples and learning resources for working with large language models (LLMs) in local development environments.\n\n### Topics covered\n\n- Local inference with Ollama and llama.cpp\n- Direct model loading with HuggingFace Transformers\n- LangChain: prompt templates, output parsers, chains, and agents\n- RAG (Retrieval-Augmented Generation) with pgvector\n- Gradio web interfaces\n- Prompting techniques: zero-shot, few-shot, chain-of-thought, ReAct\n\n### Resources included\n\n- **9 demos**: chatbots, LangChain patterns, agents, RAG knowledge systems, fine-tuning \u0026 evaluation\n- **8 slide decks**: covering deployment, prompting, LangChain, fine-tuning, and evaluation\n- **7 activities**: hands-on exercises building on each demo\n\n---\n\n## Documentation\n\n**Complete documentation:** [https://gperdrizet.github.io/llms-demo](https://gperdrizet.github.io/llms-demo/)\n\nThe documentation covers:\n- Setup and installation\n- Demo usage and concepts\n- Inference server configuration\n- Library reference with code examples\n- Model specifications and serving commands\n- Systemd deployment for production use\n- Slide and activity guides\n\n---\n\n## Quickstart\n\n### 1. Fork and clone\n\n1. Click **Fork** in the top-right corner of this repo on GitHub to create your own copy.\n2. Clone your fork:\n\n   ```bash\n   git clone https://github.com/\u003cyour-username\u003e/llms-demo.git\n   ```\n\n### 2. Open in a dev container\n\n1. Open the cloned folder in VS Code.\n2. When prompted **\"Reopen in Container\"**, click it - or run the command **Dev Containers: Reopen in Container** from the Command Palette (`Ctrl+Shift+P`).\n3. VS Code will build and start the container. This takes a few minutes the first time.\n\n### 3. What happens during container startup\n\nThe dev container is based on the `gperdrizet/llms-gpu` image (NVIDIA GPU-enabled). On first creation, the `postCreateCommand` runs automatically and does the following:\n\n| Step | What it does |\n|------|-------------|\n| `mkdir -p models/hugging_face \u0026\u0026 mkdir -p models/ollama` | Creates local directories for model storage |\n| `pip install -r requirements.txt` | Installs Python dependencies: **bert-score**, **evaluate**, **gradio**, **huggingface-hub**, **langchain-ollama**, **openai**, **peft**, **python-dotenv**, **trl**, **torch**, **transformers** |\n| `bash .devcontainer/install_ollama.sh` | Downloads and installs the Ollama CLI |\n\nThe container also pre-configures the following:\n\n| Setting | Detail |\n|---------|--------|\n| **GPU access** | All host GPUs are passed through (`--gpus all`) |\n| **Python interpreter** | `/usr/bin/python` is set as the default |\n| **`HF_HOME`** | Points to `models/hugging_face` so Hugging Face downloads stay in the repo |\n| **`OLLAMA_MODELS`** | Points to `models/ollama` so Ollama downloads stay in the repo |\n| **Port 7860** | Forwarded automatically for Gradio web UIs |\n| **VS Code extensions** | Python, Jupyter, Code Spell Checker, and Marp (slide viewer) are installed |\n\nOnce the container is ready you can start running the demos - no extra setup needed.\n\n---\n\n## Running the demos\n\nSee the [Demos documentation](https://gperdrizet.github.io/llms-demo/demos.html) for detailed instructions on running each chatbot, including:\n- Concepts covered in each demo\n- Tools and libraries used\n- Step-by-step setup and execution\n\n**Quick example** - Ollama chatbot:\n```bash\n# 1. Start the Ollama server\nollama serve\n\n# 2. Pull a model (in another terminal)\nollama pull qwen2.5:3b\n\n# 3. Run the chatbot\npython demos/chatbots/ollama_chatbot.py\n```\n\nFor complete instructions on all four demos, visit the [documentation](https://gperdrizet.github.io/llms-demo/).\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgperdrizet%2Fllms-demo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgperdrizet%2Fllms-demo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgperdrizet%2Fllms-demo/lists"}