{"id":26686780,"url":"https://github.com/mlane/llm-getting-started","last_synced_at":"2026-04-10T01:07:47.926Z","repository":{"id":284455310,"uuid":"954986776","full_name":"mlane/llm-getting-started","owner":"mlane","description":"Practical, beginner-friendly LLM projects using Python, LangChain, and LangSmith. Modular, reusable, and easy to run.","archived":false,"fork":false,"pushed_at":"2025-03-26T00:45:31.000Z","size":3,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-26T01:32:03.970Z","etag":null,"topics":["agent","agents","ai-examples","ai-getting-started","ai-projects","beginner-friendly","chatgpt","gpt","langchain","langchain-examples","llm","llm-apps","llm-examples","ollama","openai","prompt-engineering","python","python-llm","python3","text-generation"],"latest_commit_sha":null,"homepage":"","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/mlane.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}},"created_at":"2025-03-25T23:37:12.000Z","updated_at":"2025-03-26T00:45:35.000Z","dependencies_parsed_at":"2025-03-26T01:32:07.386Z","dependency_job_id":null,"html_url":"https://github.com/mlane/llm-getting-started","commit_stats":null,"previous_names":["mlane/llm-getting-started"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlane%2Fllm-getting-started","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlane%2Fllm-getting-started/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlane%2Fllm-getting-started/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlane%2Fllm-getting-started/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlane","download_url":"https://codeload.github.com/mlane/llm-getting-started/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245650484,"owners_count":20650105,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["agent","agents","ai-examples","ai-getting-started","ai-projects","beginner-friendly","chatgpt","gpt","langchain","langchain-examples","llm","llm-apps","llm-examples","ollama","openai","prompt-engineering","python","python-llm","python3","text-generation"],"created_at":"2025-03-26T12:14:29.808Z","updated_at":"2025-12-30T23:24:53.332Z","avatar_url":"https://github.com/mlane.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM Getting Started\n\nA growing collection of practical, beginner-friendly projects using **Python**, **LangChain**, and **LangSmith** to explore modern LLM patterns.\n\n\u003e Inspired by the [LLM Engineering Cheatsheet](https://github.com/mlane/llm-engineering-cheatsheet)\n\n---\n\n## Quick Start\n\n```bash\ngit clone https://github.com/mlane/llm-getting-started.git\ncd llm-getting-started\n\npython3.11 -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt\n\ncp .env.sample .env\n# Fill in your OpenAI / LangSmith API keys\n\n# Run an example project\npython3.11 projects/debate_agent.py\n\n# Set up pre-commit hooks\npre-commit install  # (run once per machine)\n```\n\n---\n\n## Python Standards\n\n- **Python version**: 3.11+\n- **Formatter**: [`black`](https://github.com/psf/black)\n- **Linter**: [`ruff`](https://github.com/astral-sh/ruff)\n\n```bash\n# Format code\nblack .\n\n# Lint code\nruff check .\n```\n\n---\n\n## Project Roadmap \u0026 Learning Path\n\nThis repo will grow over time. Projects are grouped by complexity to help you build intuition as LLM concepts evolve from simple to advanced.\n\n✅ = Implemented \u0026 ready to run\n💡 = Planned or conceptual for now\n\n| Level           | Project                         | Concepts Practiced                     | Status |\n| --------------- | ------------------------------- | -------------------------------------- | ------ |\n| 🟢 Beginner     | Simple ChatBot with Memory      | Interactive session, short-term memory | ✅     |\n| 🟢 Beginner     | Zero/Few-Shot Prompt Playground | Prompt patterns, zero-shot thinking    | 💡     |\n| 🟡 Intermediate | LLM Agent Debate                | System prompts, disagreement modeling  | ✅     |\n| 🟡 Intermediate | Role-Based Support Assistant    | Formatting, role control               | 💡     |\n| 🔴 Advanced     | Retrieval QA from Local Docs    | Vectorstores, retrieval chain          | 💡     |\n| 🔴 Advanced     | Multi-Agent Task Planner        | LangGraph, agent chaining              | 💡     |\n\n---\n\n## Concept Glossary\n\nEach script lists one or more of the following **concepts** it demonstrates:\n\n### LLM Behaviors (Descriptive)\n\n| Behavior                             | Concept                                 |\n| ------------------------------------ | --------------------------------------- |\n| No examples given                    | zero-shot reasoning                     |\n| Examples in prompt                   | few-shot prompting                      |\n| Explicit persona or tone             | persona control, system prompts         |\n| Responds to previous turns           | conversation history, short-term memory |\n| Simulates disagreement or debate     | agent disagreement                      |\n| Builds on previous answers           | turn-based dialogue                     |\n| Explains steps                       | chain of thought                        |\n| Uses external data for context       | RAG (Retrieval Augmented Generation)    |\n| Uses retrieved data to augment model | document retrieval, model augmentation  |\n\n### Interaction Patterns\n\n| Structure/Flow                       | Concept                                            |\n| ------------------------------------ | -------------------------------------------------- |\n| Live user input loop                 | interactive session                                |\n| Two or more agents taking turns      | multi-agent interaction                            |\n| Message-based prompt passing         | conversational flow                                |\n| Uses tools or actions                | tool execution                                     |\n| Semantic search for relevant context | document retrieval, semantic search, vectorization |\n\nUse these as a reference when reading or extending scripts.\n\n---\n\n## Philosophy\n\nWe believe the best way to learn LLMs is by **doing** — each script is small, focused, and teaches a core idea.\n\nThis repo is built to be:\n\n- Modular\n- Beginner-friendly\n- Focused on **thinking**, not just syntax\n- Updated as the LLM ecosystem evolves\n\n---\n\n## License\n\n[MIT](./LICENSE)\n\nPRs welcome. Please keep things clean, consistent, and low-dependency.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlane%2Fllm-getting-started","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlane%2Fllm-getting-started","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlane%2Fllm-getting-started/lists"}