{"id":29084640,"url":"https://github.com/readytensor/rt-agentic-ai-cert-week2","last_synced_at":"2025-08-02T15:42:07.865Z","repository":{"id":295500854,"uuid":"990205146","full_name":"readytensor/rt-agentic-ai-cert-week2","owner":"readytensor","description":"Practical code for Week 2 of Ready Tensor's Agentic AI Certification: modular prompt engineering and advanced reasoning techniques (Chain of Thought, ReAct, Self-Ask).","archived":false,"fork":false,"pushed_at":"2025-06-22T21:25:05.000Z","size":4772,"stargazers_count":2,"open_issues_count":1,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-06-22T21:28:04.323Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/readytensor.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}},"created_at":"2025-05-25T17:58:40.000Z","updated_at":"2025-06-22T21:25:09.000Z","dependencies_parsed_at":"2025-05-25T22:40:36.199Z","dependency_job_id":null,"html_url":"https://github.com/readytensor/rt-agentic-ai-cert-week2","commit_stats":null,"previous_names":["readytensor/rt-agentic-ai-cert-week2"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/readytensor/rt-agentic-ai-cert-week2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/readytensor%2Frt-agentic-ai-cert-week2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/readytensor%2Frt-agentic-ai-cert-week2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/readytensor%2Frt-agentic-ai-cert-week2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/readytensor%2Frt-agentic-ai-cert-week2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/readytensor","download_url":"https://codeload.github.com/readytensor/rt-agentic-ai-cert-week2/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/readytensor%2Frt-agentic-ai-cert-week2/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262341643,"owners_count":23296072,"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":[],"created_at":"2025-06-27T22:10:51.808Z","updated_at":"2025-06-27T22:10:52.244Z","avatar_url":"https://github.com/readytensor.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Ready Tensor Agentic AI Certification - Week 2\n\nThis repository contains the lessons, practical code and exercises for **Week 2** of the [Agentic AI Developer Certification Program](https://app.readytensor.ai/publications/HrJ0xWtLzLNt) by Ready Tensor, covering foundational prompt engineering concepts that are essential for building effective agentic AI systems.\n\n## What You'll Learn\n\n- How to build **modular prompts** for better clarity and reuse\n- When and how to apply **reasoning techniques** like CoT, ReAct, and Self-Ask\n- Strategies for **structured output parsing**\n- Principles of **function chaining** in AI workflows\n- How **vector databases** enable semantic search\n- Foundations of **Retrieval-Augmented Generation (RAG)**\n\n---\n\n## Lessons in This Repository\n\n### 1a. Building Prompts for Agentic AI Systems\n\nLearn how to design effective prompts using modular components — instruction, tone, role, constraints — and how to iteratively refine prompts for clarity and consistency.\n\n### 1b. Prompt Engineering: Advanced Reasoning Techniques\n\nCovers three powerful techniques — **Chain of Thought**, **ReAct**, and **Self-Ask** — and shows how to incorporate them into your modular prompt framework.\n\n### 2. From Text to Data: Hands-On LLM Output Parsing\n\nExplore structured output generation from LLMs using prompt formatting and model-native methods, with tools like **Pydantic** and **LangChain**.\n\n### 3. Function Chaining for Intelligent Pipelines\n\nUnderstand how breaking down tasks into smaller functions enables composable, robust AI systems, and how to structure chains for clarity and reliability.\n\n### 4a. Vector Databases: Finding Meaning, Not Just Keywords\n\nGet introduced to vector search and how embeddings power semantic retrieval in intelligent systems.\n\n### 4b. Vector Databases: Building a Semantic Retrieval System\n\nBuild a working pipeline with **ChromaDB**, embeddings, and chunked documents — the foundation of modern RAG workflows.\n\n### 5. Introduction to RAG (Retrieval Augmented Generation)\n\nLearn why RAG outperforms fine-tuning for most real-world scenarios, and how it enables domain-specific, knowledge-grounded assistants.\n\n## Repository Structure\n\n```\nrt-agentic-ai-cert-week2/\n├── code/\n│   ├── config/\n│   │   ├── config.yaml          # App config with reasoning strategies\n│   │   └── prompt_config.yaml   # Prompt configurations for examples\n│   ├── lesson_1a_and_ab.py      # Main script for lesson 1\n│   ├── lesson_2.py      # Main script for lesson 2\n│   ├── paths.py                 # File path configurations\n│   ├── prompt_builder.py        # Modular prompt construction functions\n│   └── utils.py                 # Utility functions\n├── data/\n│   └── vae-publication.md       # Sample publication for exercises\n├── lessons/\n│   └── lesson-wk2-*             # Markdown files and visuals for each lesson\n├── outputs/                     # Generated prompts and LLM responses\n├── .env.template                # Environment variables template\n├── requirements.txt             # Python dependencies\n└── README.md\n```\n\n## Installation \u0026 Setup\n\n1. **Clone the repository:**\n\n   ```bash\n   git clone https://github.com/readytensor/rt-agentic-ai-cert-week2.git\n   cd rt-agentic-ai-cert-week2\n   ```\n\n2. **Install dependencies:**\n\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. **Set up your OpenAI API key:**\n\n   Create a .env file in the root directory and add your OpenAI API key.\n   See [.env.example](https://github.com/readytensor/rt-agentic-ai-cert-week2/blob/main/.env.example) file.\n\n   ```\n   OPENAI_API_KEY=your-api-key-here\n   ```\n\n   You can get your API key from [OpenAI](https://platform.openai.com/api-keys).\n\n4. **Run the examples:**\n   ```bash\n   cd code\n   python lesson_1_and_2.py\n   ```\n   **Customize your experiments:** Edit the `prompt_cfg_key` variable in `lesson_1_and_2.py` (near the bottom of the script) to test different prompt configurations (e.g., `summarization_prompt_cfg1` through `summarization_prompt_cfg6`). You can also create new configurations in `config/prompt_config.yaml` to experiment with your own prompt designs.\n\n## Key Features\n\n- 🧩 **Modular Prompt Builder**\n  Construct prompts from reusable components like role, constraints, tone, and goals.\n\n- 🧠 **Reasoning Techniques**\n  Integrate CoT, ReAct, and Self-Ask patterns into your prompts with a single config line.\n\n- 🛠️ **Hands-On Output Parsing**\n  Generate and validate structured output using both prompt-based and model-native methods.\n\n- 🔗 **Function Chaining Framework**\n  Chain modular steps to build robust, maintainable AI pipelines.\n\n- 🔍 **Vector Search Implementation**\n  Build a retrieval system using real embeddings and ChromaDB.\n\n* 🔍 **Intro to RAG**\n  Introduction to Retrieval-Augmented Generation.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Contact\n\n**Ready Tensor, Inc.**\n\n- Email: contact at readytensor dot com\n- Issues \u0026 Contributions: Open an issue or pull request on this repository\n- Website: [Ready Tensor](https://readytensor.ai)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freadytensor%2Frt-agentic-ai-cert-week2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freadytensor%2Frt-agentic-ai-cert-week2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freadytensor%2Frt-agentic-ai-cert-week2/lists"}