From 7c1b3c7cf9af945c3378b8a6282bfd107ffeb638 Mon Sep 17 00:00:00 2001 From: johnxie Date: Fri, 20 Mar 2026 22:56:06 -0700 Subject: [PATCH] feat: migrate all 61 v1 tutorials to format_version v2 - Add format_version: v2 to frontmatter of all 61 remaining tutorials - Add "Why This Track Matters" section to all 61 (tutorial-specific) - Add "Mental Model" heading above existing mermaid diagrams (42 tutorials) - Fix heading mismatches to pass v2 validator - Add missing "What You Will Learn" sections (8 tutorials) - 191/191 tutorials now pass v2 format validation --- discoverability/query-coverage.json | 6 ++--- discoverability/query-hub.md | 4 +-- discoverability/search-intent-map.md | 12 +++++---- discoverability/tutorial-directory.md | 2 +- discoverability/tutorial-index.json | 25 +++++++++++++------ discoverability/tutorial-itemlist.schema.json | 2 +- llms-full.txt | 4 +-- tutorials/README.md | 2 +- tutorials/ag2-tutorial/README.md | 19 ++++++++++++-- tutorials/agentgpt-tutorial/README.md | 19 ++++++++++++-- tutorials/autogen-tutorial/README.md | 19 ++++++++++++-- tutorials/bentoml-tutorial/README.md | 19 ++++++++++++-- tutorials/botpress-tutorial/README.md | 18 ++++++++++--- tutorials/chatbox-tutorial/README.md | 19 ++++++++++++-- tutorials/chroma-tutorial/README.md | 19 ++++++++++++-- .../claude-task-master-tutorial/README.md | 19 ++++++++++++-- tutorials/clickhouse-tutorial/README.md | 19 ++++++++++++-- tutorials/comfyui-tutorial/README.md | 19 ++++++++++++-- tutorials/copilotkit-tutorial/README.md | 19 ++++++++++++-- tutorials/crewai-tutorial/README.md | 19 ++++++++++++-- tutorials/deer-flow-tutorial/README.md | 18 ++++++++++--- tutorials/dspy-tutorial/README.md | 19 ++++++++++++-- tutorials/elizaos-tutorial/README.md | 22 ++++++++++++++-- tutorials/fabric-tutorial/README.md | 18 ++++++++++--- tutorials/firecrawl-tutorial/README.md | 19 ++++++++++++-- tutorials/gpt-oss-tutorial/README.md | 19 ++++++++++++-- tutorials/haystack-tutorial/README.md | 22 ++++++++++++++-- tutorials/huggingface-tutorial/README.md | 19 ++++++++++++-- tutorials/instructor-tutorial/README.md | 19 ++++++++++++-- tutorials/khoj-tutorial/README.md | 22 ++++++++++++++-- .../kubernetes-operator-patterns/README.md | 19 ++++++++++++-- tutorials/lancedb-tutorial/README.md | 19 ++++++++++++-- .../langchain-architecture-guide/README.md | 23 ++++++++++++++++- tutorials/langchain-tutorial/README.md | 19 ++++++++++++-- tutorials/langgraph-tutorial/README.md | 19 ++++++++++++-- tutorials/letta-tutorial/README.md | 19 ++++++++++++-- tutorials/liveblocks-tutorial/README.md | 22 ++++++++++++++-- tutorials/llama-cpp-tutorial/README.md | 19 ++++++++++++-- tutorials/llama-factory-tutorial/README.md | 19 ++++++++++++-- tutorials/llamaindex-tutorial/README.md | 19 ++++++++++++-- tutorials/lobechat-ai-platform/README.md | 22 ++++++++++++++-- tutorials/localai-tutorial/README.md | 19 ++++++++++++-- tutorials/mcp-python-sdk-tutorial/README.md | 18 ++++++++++--- tutorials/meilisearch-tutorial/README.md | 16 ++++++++++-- tutorials/mem0-tutorial/README.md | 19 ++++++++++++-- tutorials/n8n-ai-tutorial/README.md | 19 ++++++++++++-- tutorials/n8n-mcp-tutorial/README.md | 22 ++++++++++++++-- tutorials/openbb-tutorial/README.md | 18 ++++++++++--- tutorials/openclaw-tutorial/README.md | 22 ++++++++++++++-- tutorials/outlines-tutorial/README.md | 18 ++++++++++--- tutorials/perplexica-tutorial/README.md | 19 ++++++++++++-- tutorials/phidata-tutorial/README.md | 18 ++++++++++--- tutorials/photoprism-tutorial/README.md | 18 ++++++++++--- tutorials/postgresql-query-planner/README.md | 19 ++++++++++++-- tutorials/posthog-tutorial/README.md | 19 ++++++++++++-- tutorials/pydantic-ai-tutorial/README.md | 18 ++++++++++--- tutorials/quivr-tutorial/README.md | 19 ++++++++++++-- tutorials/ragflow-tutorial/README.md | 18 ++++++++++--- tutorials/react-fiber-internals/README.md | 19 ++++++++++++-- tutorials/semantic-kernel-tutorial/README.md | 19 ++++++++++++-- tutorials/sillytavern-tutorial/README.md | 18 ++++++++++--- tutorials/siyuan-tutorial/README.md | 19 ++++++++++++-- tutorials/smolagents-tutorial/README.md | 19 ++++++++++++-- tutorials/supabase-tutorial/README.md | 19 ++++++++++++-- tutorials/superagi-tutorial/README.md | 19 ++++++++++++-- tutorials/swarm-tutorial/README.md | 19 ++++++++++++-- tutorials/turborepo-tutorial/README.md | 19 ++++++++++++-- tutorials/vllm-tutorial/README.md | 19 ++++++++++++-- tutorials/whisper-cpp-tutorial/README.md | 19 ++++++++++++-- 69 files changed, 1072 insertions(+), 155 deletions(-) diff --git a/discoverability/query-coverage.json b/discoverability/query-coverage.json index 02d9118..cae7e8b 100644 --- a/discoverability/query-coverage.json +++ b/discoverability/query-coverage.json @@ -457,12 +457,12 @@ "title": "Fireproof Tutorial: Local-First Document Database for AI-Native Apps" }, { - "file_url": "https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md", + "file_url": "https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/comfyui-tutorial/README.md", "intent_signals": [ "general-learning" ], - "slug": "botpress-tutorial", - "title": "Botpress Tutorial: Open Source Conversational AI Platform" + "slug": "comfyui-tutorial", + "title": "ComfyUI Tutorial: Mastering AI Image Generation Workflows" } ] }, diff --git a/discoverability/query-hub.md b/discoverability/query-hub.md index 18a03cc..11da2c0 100644 --- a/discoverability/query-hub.md +++ b/discoverability/query-hub.md @@ -157,8 +157,8 @@ Recommended tutorials: - Learn how to use activepieces/activepieces to build, run, and govern production automation workflows with open-source extensibility, piece development, API control, and self-hosted operations. - [Fireproof Tutorial: Local-First Document Database for AI-Native Apps](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/fireproof-tutorial/README.md) - Learn how to use fireproof-storage/fireproof to build local-first, encrypted, sync-capable applications with a unified browser/Node/Deno API and React hooks. -- [Botpress Tutorial: Open Source Conversational AI Platform](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md) - - This comprehensive tutorial will guide you through Botpress, a powerful open source platform for building conversational AI applications +- [ComfyUI Tutorial: Mastering AI Image Generation Workflows](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/comfyui-tutorial/README.md) + - A deep technical walkthrough of ComfyUI covering Mastering AI Image Generation Workflows. ## Taskade AI, Genesis, and MCP Workflows diff --git a/discoverability/search-intent-map.md b/discoverability/search-intent-map.md index 87f42f9..320ad07 100644 --- a/discoverability/search-intent-map.md +++ b/discoverability/search-intent-map.md @@ -8,14 +8,12 @@ Auto-generated topical clusters to strengthen internal linking and query-to-tuto ## ai-app-frameworks -- tutorial_count: **27** +- tutorial_count: **26** - [Activepieces Tutorial: Open-Source Automation, Pieces, and AI-Ready Workflow Operations](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/activepieces-tutorial/README.md) - intents: production-operations - [BentoML Tutorial: Building Production-Ready ML Services](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/bentoml-tutorial/README.md) - intents: production-operations -- [Botpress Tutorial: Open Source Conversational AI Platform](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md) - - intents: general-learning - [Chatbox Tutorial: Building Modern AI Chat Interfaces](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/chatbox-tutorial/README.md) - intents: general-learning - [ComfyUI Tutorial: Mastering AI Image Generation Workflows](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/comfyui-tutorial/README.md) @@ -60,7 +58,9 @@ Auto-generated topical clusters to strengthen internal linking and query-to-tuto - intents: general-learning - [Turborepo Tutorial: High-Performance Monorepo Build System](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/turborepo-tutorial/README.md) - intents: general-learning -- ... plus 2 more tutorials in this cluster +- [Vercel AI SDK Tutorial: Production TypeScript AI Apps and Agents](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/vercel-ai-tutorial/README.md) + - intents: production-operations +- ... plus 1 more tutorials in this cluster ## ai-coding-agents @@ -141,8 +141,10 @@ Auto-generated topical clusters to strengthen internal linking and query-to-tuto ## general-software -- tutorial_count: **16** +- tutorial_count: **17** +- [Botpress Tutorial: Open Source Conversational AI Platform](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md) + - intents: production-operations - [Claude Task Master Tutorial: AI-Powered Task Management for Developers](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/claude-task-master-tutorial/README.md) - intents: general-learning - [DSPy Tutorial: Programming Language Models](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/dspy-tutorial/README.md) diff --git a/discoverability/tutorial-directory.md b/discoverability/tutorial-directory.md index defff98..1428d04 100644 --- a/discoverability/tutorial-directory.md +++ b/discoverability/tutorial-directory.md @@ -53,7 +53,7 @@ This page is auto-generated from the tutorial index and is intended as a fast br - [bolt.diy Tutorial: Build and Operate an Open Source AI App Builder](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/bolt-diy-tutorial/README.md) - A production-focused deep dive into stackblitz-labs/bolt.diy: architecture, provider routing, safe edit loops, MCP integrations, deployment choices, and operational governance. - [Botpress Tutorial: Open Source Conversational AI Platform](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md) - - This comprehensive tutorial will guide you through Botpress, a powerful open source platform for building conversational AI applications + - Important Notice (2025): Botpress v12 has been sunset and is no longer available for new deployments. However, existing customers with active v12 subscriptions remain fully supported. - [Browser Use Tutorial: AI-Powered Web Automation Agents](https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/browser-use-tutorial/README.md) - Learn how to use browser-use/browser-use to build agents that can navigate websites, execute workflows, and run reliable browser automation in production. diff --git a/discoverability/tutorial-index.json b/discoverability/tutorial-index.json index 569018e..bf75445 100644 --- a/discoverability/tutorial-index.json +++ b/discoverability/tutorial-index.json @@ -662,27 +662,36 @@ "title": "bolt.diy Tutorial: Build and Operate an Open Source AI App Builder" }, { - "cluster": "ai-app-frameworks", + "cluster": "general-software", "file_url": "https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md", "index_path": "tutorials/botpress-tutorial/README.md", "intent_signals": [ - "general-learning" + "production-operations" ], "keywords": [ "botpress", "open", "source", "conversational", - "comprehensive", - "will", - "powerful", - "building", - "applications" + "important", + "notice", + "v12", + "has", + "been", + "sunset", + "longer", + "available", + "new", + "deployments", + "however", + "existing", + "customers", + "active" ], "path": "tutorials/botpress-tutorial", "repo_url": "https://github.com/johnxie/awesome-code-docs/tree/main/tutorials/botpress-tutorial", "slug": "botpress-tutorial", - "summary": "This comprehensive tutorial will guide you through Botpress, a powerful open source platform for building conversational AI applications", + "summary": "Important Notice (2025): Botpress v12 has been sunset and is no longer available for new deployments. However, existing customers with active v12 subscriptions remain fully supported.", "title": "Botpress Tutorial: Open Source Conversational AI Platform" }, { diff --git a/discoverability/tutorial-itemlist.schema.json b/discoverability/tutorial-itemlist.schema.json index 1de5b4d..ebaf152 100644 --- a/discoverability/tutorial-itemlist.schema.json +++ b/discoverability/tutorial-itemlist.schema.json @@ -158,7 +158,7 @@ }, { "@type": "ListItem", - "description": "This comprehensive tutorial will guide you through Botpress, a powerful open source platform for building conversational AI applications", + "description": "Important Notice (2025): Botpress v12 has been sunset and is no longer available for new deployments. However, existing customers with active v12 subscriptions remain fully supported.", "name": "Botpress Tutorial: Open Source Conversational AI Platform", "position": 23, "url": "https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md" diff --git a/llms-full.txt b/llms-full.txt index ab23e83..0820bb4 100644 --- a/llms-full.txt +++ b/llms-full.txt @@ -138,8 +138,8 @@ Main repository: ## Botpress Tutorial: Open Source Conversational AI Platform - Path: tutorials/botpress-tutorial - Index: https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/botpress-tutorial/README.md -- Summary: This comprehensive tutorial will guide you through Botpress, a powerful open source platform for building conversational AI applications -- Keywords: botpress, open, source, conversational, comprehensive, will, powerful, building, applications +- Summary: Important Notice (2025): Botpress v12 has been sunset and is no longer available for new deployments. However, existing customers with active v12 subscriptions remain fully supported. +- Keywords: botpress, open, source, conversational, important, notice, v12, has, been, sunset, longer, available, new, deployments, however, existing, customers, active ## Browser Use Tutorial: AI-Powered Web Automation Agents - Path: tutorials/browser-use-tutorial diff --git a/tutorials/README.md b/tutorials/README.md index 944a5d7..a098653 100644 --- a/tutorials/README.md +++ b/tutorials/README.md @@ -16,7 +16,7 @@ Use this guide to navigate all tutorial tracks, understand structure rules, and |:-------|:------| | Tutorial directories | 191 | | Tutorial markdown files | 1722 | -| Tutorial markdown lines | 1,048,148 | +| Tutorial markdown lines | 1,049,054 | ## Source Verification Snapshot diff --git a/tutorials/ag2-tutorial/README.md b/tutorials/ag2-tutorial/README.md index 515ecba..6d9e91b 100644 --- a/tutorials/ag2-tutorial/README.md +++ b/tutorials/ag2-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "AG2 Tutorial" nav_order: 73 has_children: true +format_version: v2 --- # AG2 Tutorial: Next-Generation Multi-Agent Framework @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +AG2 is increasingly relevant for developers working with modern AI/ML infrastructure. Build collaborative AI agent systems with AG2, the community-driven successor to AutoGen, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Create Conversational Agents** that collaborate through natural dialogue +- **Implement Code Execution** safely with Docker sandboxing +- **Build Multi-Agent Systems** with group chat coordination +- **Integrate External Tools** through function calling + ## 🎯 What is AG2? **AG2**[View Repo](https://github.com/ag2ai/ag2) is the community-driven successor to Microsoft's AutoGen framework. It provides a powerful, open-source platform for building AI agents that can collaborate to solve complex tasks through natural conversation. @@ -35,6 +47,9 @@ has_children: true > **Note**: The original AutoGen creators transitioned to AG2 to promote open governance. Microsoft continues developing AutoGen as part of their Agent Framework. + +## Mental Model + ```mermaid flowchart TD A[User Task] --> B[AssistantAgent] @@ -91,7 +106,7 @@ flowchart TD - **Group Chat** - Multiple agents collaborating - **Nested Chat** - Hierarchical agent structures -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and your first AG2 agents 2. **[Chapter 2: Agent Types](02-agent-types.md)** - Understanding and configuring different agents @@ -103,7 +118,7 @@ flowchart TD 8. **[Chapter 8: Production Deployment](08-production.md)** - Scaling, monitoring, and best practices 9. **[Chapter 9: Enterprise Operations](09-enterprise-operations.md)** - Governance, evals, safety, and cost/perf tuning -## What You'll Learn +## What You Will Learn - **Create Conversational Agents** that collaborate through natural dialogue - **Implement Code Execution** safely with Docker sandboxing diff --git a/tutorials/agentgpt-tutorial/README.md b/tutorials/agentgpt-tutorial/README.md index 4cafa01..a9b14c4 100644 --- a/tutorials/agentgpt-tutorial/README.md +++ b/tutorials/agentgpt-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "AgentGPT Tutorial" nav_order: 14 has_children: true +format_version: v2 --- # AgentGPT Tutorial: Building Autonomous AI Agents @@ -18,6 +19,9 @@ AgentGPT[View Repo](https://github.com/reworkd/AgentGPT) is a platfor AgentGPT shows how to build AI systems that can break down complex objectives into manageable tasks, use various tools and APIs, and execute plans autonomously while maintaining safety and reliability. + +## Mental Model + ```mermaid flowchart TD A[User Goal] --> B[Task Planning] @@ -44,7 +48,18 @@ flowchart TD class K,L learning ``` -## Tutorial Chapters +## Why This Track Matters + +AgentGPT is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of AgentGPT covering Building Autonomous AI Agents, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with agentgpt +- understanding agent architecture & design +- understanding task planning & goal setting +- understanding tool integration & apis + +## Chapter Guide Welcome to your journey through autonomous AI agent development! This tutorial explores how to build intelligent agents that can plan, execute, and learn autonomously. @@ -64,7 +79,7 @@ Welcome to your journey through autonomous AI agent development! This tutorial e - latest release: [`v.1.0.0`](https://github.com/reworkd/AgentGPT/releases/tag/v.1.0.0) (published 2023-11-02) - status: **archived** -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/autogen-tutorial/README.md b/tutorials/autogen-tutorial/README.md index 0154dff..6eeae9e 100644 --- a/tutorials/autogen-tutorial/README.md +++ b/tutorials/autogen-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Microsoft AutoGen Tutorial" nav_order: 21 has_children: true +format_version: v2 --- # Microsoft AutoGen Tutorial: Building Multi-Agent AI Systems @@ -18,6 +19,9 @@ Microsoft AutoGen[View Repo](https://github.com/microsoft/autogen) is AutoGen provides a flexible architecture for creating agent-based systems that can work together to accomplish tasks that would be difficult or impossible for a single AI model. + +## Mental Model + ```mermaid flowchart TD A[User Request] --> B[Task Analysis] @@ -45,7 +49,18 @@ flowchart TD class F output ``` -## Tutorial Chapters +## Why This Track Matters + +Microsoft AutoGen is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Microsoft AutoGen covering Building Multi-Agent AI Systems, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with microsoft autogen +- understanding agent architecture & roles +- understanding agent communication +- understanding tool integration + +## Chapter Guide Welcome to your journey through multi-agent AI systems! This tutorial explores how to build collaborative AI agents that can work together to solve complex problems. @@ -64,7 +79,7 @@ Welcome to your journey through multi-agent AI systems! This tutorial explores h - stars: about **55.7k** - latest release: [`python-v0.7.5`](https://github.com/microsoft/autogen/releases/tag/python-v0.7.5) (published 2025-09-30) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/bentoml-tutorial/README.md b/tutorials/bentoml-tutorial/README.md index 26b2cea..9b55efe 100644 --- a/tutorials/bentoml-tutorial/README.md +++ b/tutorials/bentoml-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "BentoML Tutorial" nav_order: 22 has_children: true +format_version: v2 --- # BentoML Tutorial: Building Production-Ready ML Services @@ -18,6 +19,9 @@ BentoML[View Repo](https://github.com/bentoml/BentoML) is the unified BentoML simplifies the ML deployment process by providing tools for model packaging, API serving, monitoring, and scaling, making it easy to take models from development to production. + +## Mental Model + ```mermaid flowchart TD A[ML Model] --> B[BentoML Service] @@ -49,7 +53,18 @@ flowchart TD class F output ``` -## Tutorial Chapters +## Why This Track Matters + +BentoML is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of BentoML covering Building Production-Ready ML Services, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with bentoml +- understanding model packaging & services +- understanding api development +- understanding framework integration + +## Chapter Guide Welcome to your journey through production ML deployment! This tutorial explores how to build, deploy, and manage machine learning models at scale with BentoML. @@ -68,7 +83,7 @@ Welcome to your journey through production ML deployment! This tutorial explores - stars: about **8.5k** - latest release: [`v1.4.36`](https://github.com/bentoml/BentoML/releases/tag/v1.4.36) (published 2026-03-06) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/botpress-tutorial/README.md b/tutorials/botpress-tutorial/README.md index a6034bf..c78814e 100644 --- a/tutorials/botpress-tutorial/README.md +++ b/tutorials/botpress-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Botpress Tutorial" nav_order: 24 has_children: true +format_version: v2 --- # Botpress Tutorial: Open Source Conversational AI Platform @@ -17,7 +18,18 @@ has_children: true --- -## 🎯 What You'll Learn +## Why This Track Matters + +Botpress is increasingly relevant for developers working with modern AI/ML infrastructure. **Important Notice (2025)**: Botpress v12 has been sunset and is no longer available for new deployments. However, existing customers with active v12 subscriptions remain fully supported, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with botpress +- understanding visual flow builder +- understanding natural language understanding +- understanding custom actions & code + +## What You Will Learn This comprehensive tutorial will guide you through Botpress, a powerful open source platform for building conversational AI applications: @@ -60,7 +72,7 @@ cd my-first-bot bp dev ``` -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -167,7 +179,7 @@ By the end of this tutorial, you'll be able to: *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with Botpress](01-getting-started.md) 2. [Chapter 2: Visual Flow Builder](02-visual-flow-builder.md) diff --git a/tutorials/chatbox-tutorial/README.md b/tutorials/chatbox-tutorial/README.md index 1a20022..ca072f5 100644 --- a/tutorials/chatbox-tutorial/README.md +++ b/tutorials/chatbox-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Chatbox Tutorial" nav_order: 13 has_children: true +format_version: v2 --- # Chatbox Tutorial: Building Modern AI Chat Interfaces @@ -18,6 +19,9 @@ Chatbox[View Repo](https://github.com/Bin-Huang/chatbox) is a modern, Chatbox combines the best of modern web technologies with native desktop capabilities, showing how to build AI applications that users actually enjoy using. + +## Mental Model + ```mermaid flowchart TD A[User Interface] --> B[Chat Engine] @@ -43,7 +47,18 @@ flowchart TD class J,K,L extensions ``` -## Tutorial Chapters +## Why This Track Matters + +Chatbox is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Chatbox covering Building Modern AI Chat Interfaces, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with chatbox +- understanding ui architecture & components +- understanding ai provider integration +- understanding conversation management + +## Chapter Guide Welcome to your journey through modern AI chat interface development! This tutorial explores how to build polished, user-friendly conversational AI applications. @@ -62,7 +77,7 @@ Welcome to your journey through modern AI chat interface development! This tutor - stars: about **39k** - latest release: [`v1.19.0`](https://github.com/Bin-Huang/chatbox/releases/tag/v1.19.0) (published 2026-02-13) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/chroma-tutorial/README.md b/tutorials/chroma-tutorial/README.md index ff4d97a..d12119c 100644 --- a/tutorials/chroma-tutorial/README.md +++ b/tutorials/chroma-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "ChromaDB Tutorial" nav_order: 18 has_children: true +format_version: v2 --- # ChromaDB Tutorial: Building AI-Native Vector Databases @@ -18,6 +19,9 @@ Chroma[View Repo](https://github.com/chroma-core/chroma) is the AI-na Chroma enables developers to build sophisticated AI applications with persistent memory, fast retrieval, and powerful querying capabilities without the complexity of traditional databases. + +## Mental Model + ```mermaid flowchart TD A[Data Input] --> B[Embedding Generation] @@ -44,7 +48,18 @@ flowchart TD class J,K storage ``` -## Tutorial Chapters +## Why This Track Matters + +ChromaDB is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of ChromaDB covering Building AI-Native Vector Databases, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with chroma +- understanding collections & documents +- understanding embeddings & indexing +- understanding querying & retrieval + +## Chapter Guide Welcome to your journey through AI-native vector databases! This tutorial explores how to build powerful AI applications with Chroma's embedding database. @@ -63,7 +78,7 @@ Welcome to your journey through AI-native vector databases! This tutorial explor - stars: about **26.7k** - latest release: [`1.5.5`](https://github.com/chroma-core/chroma/releases/tag/1.5.5) (published 2026-03-10) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/claude-task-master-tutorial/README.md b/tutorials/claude-task-master-tutorial/README.md index 74f2d0b..d7a34ea 100644 --- a/tutorials/claude-task-master-tutorial/README.md +++ b/tutorials/claude-task-master-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Claude Task Master Tutorial" nav_order: 24 has_children: true +format_version: v2 --- # Claude Task Master Tutorial: AI-Powered Task Management for Developers @@ -18,6 +19,9 @@ Claude Task Master[View Repo](https://github.com/eyaltoledano/claude-task-m Task Master transforms how developers approach complex projects by using AI to analyze requirements, create detailed task plans, and maintain focus throughout the development process. + +## Mental Model + ```mermaid flowchart TD A[Project Requirements] --> B[AI Analysis] @@ -45,7 +49,18 @@ flowchart TD class F,I execution ``` -## Tutorial Chapters +## Why This Track Matters + +Claude Task Master is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Claude Task Master covering AI-Powered Task Management for Developers, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with claude task master +- understanding prd analysis & task generation +- understanding task management & execution +- understanding multi-model integration + +## Chapter Guide Welcome to your journey through AI-powered task management! This tutorial explores how to leverage Claude Task Master for intelligent project planning and execution. @@ -64,7 +79,7 @@ Welcome to your journey through AI-powered task management! This tutorial explor - stars: about **25.9k** - latest release: [`task-master-ai@0.43.0`](https://github.com/eyaltoledano/claude-task-master/releases/tag/task-master-ai@0.43.0) (published 2026-02-04) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/clickhouse-tutorial/README.md b/tutorials/clickhouse-tutorial/README.md index 354f039..d090358 100644 --- a/tutorials/clickhouse-tutorial/README.md +++ b/tutorials/clickhouse-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "ClickHouse Tutorial" nav_order: 27 has_children: true +format_version: v2 --- # ClickHouse Tutorial: High-Performance Analytical Database @@ -18,6 +19,9 @@ ClickHouse[View Repo](https://github.com/ClickHouse/ClickHouse) is an ClickHouse provides unparalleled performance for analytical queries while maintaining simplicity in deployment and management, making it a go-to solution for modern data analytics platforms. + +## Mental Model + ```mermaid flowchart TD A[Data Sources] --> B[ClickHouse Ingestion] @@ -49,7 +53,18 @@ flowchart TD class J,K,L analytics ``` -## Tutorial Chapters +## Why This Track Matters + +ClickHouse is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of ClickHouse covering High-Performance Analytical Database, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with clickhouse +- understanding data modeling & schemas +- understanding data ingestion & etl +- understanding query optimization + +## Chapter Guide Welcome to your journey through high-performance analytical databases! This tutorial explores how to master ClickHouse for building fast, scalable analytics systems. @@ -68,7 +83,7 @@ Welcome to your journey through high-performance analytical databases! This tuto - stars: about **46.4k** - latest release: [`v26.2.4.23-stable`](https://github.com/ClickHouse/ClickHouse/releases/tag/v26.2.4.23-stable) (published 2026-03-05) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/comfyui-tutorial/README.md b/tutorials/comfyui-tutorial/README.md index 46e0cb0..3b55db4 100644 --- a/tutorials/comfyui-tutorial/README.md +++ b/tutorials/comfyui-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "ComfyUI Tutorial" nav_order: 25 has_children: true +format_version: v2 --- # ComfyUI Tutorial: Mastering AI Image Generation Workflows @@ -18,6 +19,9 @@ ComfyUI[View Repo](https://github.com/comfyanonymous/ComfyUI) is a po ComfyUI represents a paradigm shift in AI image generation, offering unparalleled customization and control compared to traditional interfaces, making it the tool of choice for professional artists, researchers, and advanced users. + +## Mental Model + ```mermaid flowchart TD A[Text/Image Input] --> B[Text Encoder] @@ -50,7 +54,18 @@ flowchart TD class E,F output ``` -## Tutorial Chapters +## Why This Track Matters + +ComfyUI is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of ComfyUI covering Mastering AI Image Generation Workflows, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with comfyui +- understanding understanding nodes & workflows +- understanding text-to-image generation +- understanding image-to-image & inpainting + +## Chapter Guide Welcome to your journey through advanced AI image generation! This tutorial explores how to master ComfyUI's node-based interface for creating professional-grade image generation workflows. @@ -69,7 +84,7 @@ Welcome to your journey through advanced AI image generation! This tutorial expl - stars: about **106k** - latest release: [`v0.17.2`](https://github.com/comfyanonymous/ComfyUI/releases/tag/v0.17.2) (published 2026-03-15) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/copilotkit-tutorial/README.md b/tutorials/copilotkit-tutorial/README.md index f06a535..a90fee2 100644 --- a/tutorials/copilotkit-tutorial/README.md +++ b/tutorials/copilotkit-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "CopilotKit Tutorial" nav_order: 72 has_children: true +format_version: v2 --- # CopilotKit Tutorial: Building AI Copilots for React Applications @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +CopilotKit is increasingly relevant for developers working with modern AI/ML infrastructure. Create in-app AI assistants, chatbots, and agentic UIs with the open-source CopilotKit framework, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Create In-App AI Assistants** that understand your application context +- **Implement AI Actions** that can modify your app state +- **Build Generative UIs** with AI-created React components +- **Integrate LangGraph Agents** for complex agentic workflows + ## 🎯 What is CopilotKit? **CopilotKit**[View Repo](https://github.com/CopilotKit/CopilotKit) is an open-source framework for building AI copilots, chatbots, and in-app AI agents in React applications. It provides a complete toolkit for creating user-facing agentic applications with features like: @@ -29,6 +41,9 @@ has_children: true - **Human-in-the-Loop** - User approval for AI actions - **Shared State** - Real-time sync between UI and AI agents + +## Mental Model + ```mermaid flowchart TD A[React Application] --> B[CopilotKit Provider] @@ -73,7 +88,7 @@ flowchart TD > **LangGraph Execution**: Configurable LangGraph execution with user-defined configurations. -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and your first AI copilot 2. **[Chapter 2: Reading App Context](02-app-context.md)** - Making your app state visible to AI with useCopilotReadable @@ -84,7 +99,7 @@ flowchart TD 7. **[Chapter 7: Human-in-the-Loop](07-human-in-loop.md)** - User approval flows and interrupts 8. **[Chapter 8: Production Deployment](08-production.md)** - Scaling, security, and best practices -## What You'll Learn +## What You Will Learn - **Create In-App AI Assistants** that understand your application context - **Implement AI Actions** that can modify your app state diff --git a/tutorials/crewai-tutorial/README.md b/tutorials/crewai-tutorial/README.md index b452042..38f6e72 100644 --- a/tutorials/crewai-tutorial/README.md +++ b/tutorials/crewai-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "CrewAI Tutorial" nav_order: 23 has_children: true +format_version: v2 --- # CrewAI Tutorial: Building Collaborative AI Agent Teams @@ -11,6 +12,9 @@ CrewAI[View Repo](https://github.com/crewAIInc/crewAI) is a framework CrewAI focuses on creating purposeful AI teams where each agent has a specific role, expertise, and set of tools, working together toward shared objectives with clear communication and coordination. + +## Mental Model + ```mermaid flowchart TD A[Complex Task] --> B[Task Analysis] @@ -44,7 +48,18 @@ flowchart TD class G output ``` -## Tutorial Chapters +## Why This Track Matters + +CrewAI is increasingly relevant for developers working with modern AI/ML infrastructure. **Latest Release (v0.193.0+)**: CrewAI has evolved significantly with support for GPT-4.1, Gemini-2.0/2.5 Pro, enhanced knowledge management, agent evaluation functionality, and improved Mem0 memory integration, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with crewai +- understanding agent roles & specializations +- understanding task definition & planning +- understanding tool integration + +## Chapter Guide Welcome to your journey through collaborative AI agent teams! This tutorial explores how to build and orchestrate AI crews that work together to solve complex problems. @@ -63,7 +78,7 @@ Welcome to your journey through collaborative AI agent teams! This tutorial expl - stars: about **46.2k** - latest release: [`1.10.1`](https://github.com/crewAIInc/crewAI/releases/tag/1.10.1) (published 2026-03-04) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/deer-flow-tutorial/README.md b/tutorials/deer-flow-tutorial/README.md index a9bb683..87e0357 100644 --- a/tutorials/deer-flow-tutorial/README.md +++ b/tutorials/deer-flow-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Deer Flow Tutorial" nav_order: 36 has_children: true +format_version: v2 --- # Deer Flow Tutorial: Distributed Workflow Orchestration Platform @@ -20,6 +21,17 @@ has_children: true --- +## Why This Track Matters + +Deer Flow is increasingly relevant for developers working with modern AI/ML infrastructure. Orchestrate complex distributed workflows with Deer Flow's powerful task coordination and execution platform, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with deer flow +- understanding workflow basics +- understanding task management +- understanding dependencies + ## 🎯 What is Deer Flow? **Deer Flow** is a distributed workflow orchestration platform designed for coordinating complex tasks across multiple systems and services. It provides a robust framework for building, executing, and monitoring distributed workflows with support for parallelism, fault tolerance, and dynamic scaling. @@ -39,7 +51,7 @@ has_children: true - repository: [`bytedance/deer-flow`](https://github.com/bytedance/deer-flow) - stars: about **31k** -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -112,7 +124,7 @@ graph TB | **[07-monitoring](07-monitoring.md)** | Monitoring & Observability | 30 min | πŸ”΄ Expert | | **[08-advanced-patterns](08-advanced-patterns.md)** | Advanced Orchestration Patterns | 50 min | πŸ”΄ Expert | -## 🎯 Learning Outcomes +## What You Will Learn By the end of this tutorial, you'll be able to: @@ -272,7 +284,7 @@ Special thanks to the ByteDance team for creating this powerful distributed work *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with Deer Flow](01-getting-started.md) 2. [Chapter 2: Workflow Basics](02-workflow-basics.md) diff --git a/tutorials/dspy-tutorial/README.md b/tutorials/dspy-tutorial/README.md index eb90c59..dae609a 100644 --- a/tutorials/dspy-tutorial/README.md +++ b/tutorials/dspy-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "DSPy Tutorial" nav_order: 74 has_children: true +format_version: v2 --- # DSPy Tutorial: Programming Language Models @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +DSPy is increasingly relevant for developers working with modern AI/ML infrastructure. Learn to program language models declaratively with DSPy, the Stanford NLP framework for systematic prompt optimization and modular LLM pipelines, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Declarative Programming** - Specify what you want, let DSPy optimize how +- **Automatic Optimization** - Self-improving prompts and model configurations +- **Modular Design** - Build complex systems from reusable components +- **Systematic Evaluation** - Rigorous testing and validation frameworks + ## 🎯 What is DSPy? **DSPy**[View Repo](https://github.com/stanfordnlp/dspy) is a framework for algorithmically optimizing LM prompts and weights, developed by researchers at Stanford NLP. Unlike traditional prompt engineering, DSPy allows you to program LMs declaratively - you specify what you want to accomplish, and DSPy figures out how to optimize the prompts and model configurations. @@ -33,6 +45,9 @@ has_children: true | **Evaluation** | Manual testing | Systematic validation | | **Maintenance** | Brittle, manual updates | Self-improving systems | + +## Mental Model + ```mermaid flowchart TD A[Define Task] --> B[Write DSPy Program] @@ -117,7 +132,7 @@ mipro_optimizer = dspy.MIPROv2(metric=my_metric, num_candidates=10) optimized_program = mipro_optimizer.compile(program, trainset=trainset) ``` -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, basic concepts, and your first DSPy program 2. **[Chapter 2: Signatures](02-signatures.md)** - Defining input/output specifications for LM calls @@ -128,7 +143,7 @@ optimized_program = mipro_optimizer.compile(program, trainset=trainset) 7. **[Chapter 7: Evaluation & Metrics](07-evaluation.md)** - Systematic evaluation and custom metrics 8. **[Chapter 8: Production Deployment](08-production.md)** - Scaling, monitoring, and production best practices -## What You'll Learn +## What You Will Learn - **Declarative Programming** - Specify what you want, let DSPy optimize how - **Automatic Optimization** - Self-improving prompts and model configurations diff --git a/tutorials/elizaos-tutorial/README.md b/tutorials/elizaos-tutorial/README.md index 3d3edc9..5a2ee46 100644 --- a/tutorials/elizaos-tutorial/README.md +++ b/tutorials/elizaos-tutorial/README.md @@ -2,6 +2,7 @@ title: "ElizaOS Deep Dive" nav_order: 95 has_children: true +format_version: v2 --- # ElizaOS: Deep Dive Tutorial @@ -12,6 +13,17 @@ has_children: true [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/TypeScript-95%25-blue)](https://github.com/elizaOS/eliza) +## Why This Track Matters + +ElizaOS is increasingly relevant for developers working with modern AI/ML infrastructure. **Project**: [ElizaOS](https://github.com/elizaOS/eliza) β€” Autonomous agents for everyone, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with elizaos +- understanding agent runtime +- understanding character system +- understanding plugin architecture + ## What Is ElizaOS? ElizaOS is an open-source framework for building, deploying, and managing autonomous multi-agent AI systems. It provides a complete platform for creating AI agents β€” chatbots, business automation, game NPCs, and Web3-native agents that interact with blockchains and smart contracts. @@ -33,7 +45,7 @@ ElizaOS is an open-source framework for building, deploying, and managing autono - stars: about **17.8k** - latest release: [`v1.7.2`](https://github.com/elizaOS/eliza/releases/tag/v1.7.2) (published 2026-01-19) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -71,7 +83,7 @@ graph TB Connectors --> EVENT ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |---------|-------|-------------------| @@ -111,6 +123,12 @@ Ready to begin? Start with [Chapter 1: Getting Started](01-getting-started.md). *Built with insights from the [ElizaOS repository](https://github.com/elizaOS/eliza) and community documentation.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Getting Started with ElizaOS](01-getting-started.md) diff --git a/tutorials/fabric-tutorial/README.md b/tutorials/fabric-tutorial/README.md index 9c0c1d9..791a3f6 100644 --- a/tutorials/fabric-tutorial/README.md +++ b/tutorials/fabric-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Fabric Tutorial" nav_order: 35 has_children: true +format_version: v2 --- # Fabric Tutorial: Open-Source Framework for Augmenting Humans with AI @@ -20,6 +21,17 @@ has_children: true --- +## Why This Track Matters + +Fabric is increasingly relevant for developers working with modern AI/ML infrastructure. Enhance human capabilities with Fabric's modular framework for AI-powered cognitive assistance and task automation, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with fabric +- understanding pattern system +- understanding basic usage +- understanding advanced patterns + ## 🎯 What is Fabric? **Fabric** is an open-source framework designed to augment human capabilities using AI. It provides a modular system of "Patterns" (prompt engineering templates) and "Stitches" (composable AI workflows) that help users accomplish complex cognitive tasks more effectively. @@ -40,7 +52,7 @@ has_children: true - stars: about **39.9k** - latest release: [`v1.4.436`](https://github.com/danielmiessler/fabric/releases/tag/v1.4.436) (published 2026-03-15) -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -120,7 +132,7 @@ graph TB | **[07-integration-api](07-integration-api.md)** | API Integration & Automation | 30 min | πŸ”΄ Expert | | **[08-enterprise-deployment](08-enterprise-deployment.md)** | Enterprise Setup & Scaling | 45 min | πŸ”΄ Expert | -## 🎯 Learning Outcomes +## What You Will Learn By the end of this tutorial, you'll be able to: @@ -271,7 +283,7 @@ Special thanks to Daniel Miessler and the Fabric community for creating this pow *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with Fabric](01-getting-started.md) 2. [Chapter 2: Pattern System](02-pattern-system.md) diff --git a/tutorials/firecrawl-tutorial/README.md b/tutorials/firecrawl-tutorial/README.md index ea0a684..adc65d8 100644 --- a/tutorials/firecrawl-tutorial/README.md +++ b/tutorials/firecrawl-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Firecrawl Tutorial" nav_order: 16 has_children: true +format_version: v2 --- # Firecrawl Tutorial: Building LLM-Ready Web Scraping and Data Extraction Systems @@ -16,6 +17,9 @@ Firecrawl[View Repo](https://github.com/firecrawl/firecrawl) is a pow Firecrawl handles the complexity of web scraping - dealing with JavaScript rendering, anti-bot measures, and data cleaning - so you can focus on building amazing AI applications. + +## Mental Model + ```mermaid flowchart TD A[Web Content] --> B[Firecrawl Engine] @@ -41,7 +45,18 @@ flowchart TD class E,I,J,K,L output ``` -## Tutorial Chapters +## Why This Track Matters + +Firecrawl matters for developers building production systems. This track covers chapter 1: getting started with firecrawl, chapter 2: basic web scraping, chapter 3: advanced data extraction and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- understanding getting started with firecrawl +- understanding basic web scraping +- understanding advanced data extraction +- understanding javascript & dynamic content + +## Chapter Guide Welcome to your journey through web scraping and data extraction for AI applications! This tutorial explores how to build powerful systems that can extract, clean, and structure web content for LLM consumption. @@ -60,7 +75,7 @@ Welcome to your journey through web scraping and data extraction for AI applicat - stars: about **93.7k** - latest release: [`v2.8.0`](https://github.com/mendableai/firecrawl/releases/tag/v2.8.0) (published 2026-02-03) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/gpt-oss-tutorial/README.md b/tutorials/gpt-oss-tutorial/README.md index 1a7fc73..0d84d52 100644 --- a/tutorials/gpt-oss-tutorial/README.md +++ b/tutorials/gpt-oss-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "GPT Open Source - Deep Dive Tutorial" nav_order: 83 has_children: true +format_version: v2 --- # GPT Open Source: Deep Dive Tutorial @@ -21,7 +22,18 @@ has_children: true --- -## What This Tutorial Covers +## Why This Track Matters + +GPT Open Source is increasingly relevant for developers working with modern AI/ML infrastructure. A comprehensive guide to understanding, building, and deploying open-source GPT implementations -- from nanoGPT to GPT-NeoX and beyond, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started -- understan +- understanding transformer archite +- understanding tokenization & emb +- understanding training pipeline -- data + +## What You Will Learn This tutorial provides a deep dive into the open-source GPT ecosystem. You will learn how GPT models work at every level -- from raw transformer math to production-scale inference optimization. Whether you are training a small character-level model with nanoGPT or deploying a billion-parameter model with GPT-NeoX, this guide has you covered. @@ -37,6 +49,9 @@ This tutorial provides a deep dive into the open-source GPT ecosystem. You will | **Cerebras-GPT** | 111M-13B | Compute-optimal GPT models | Python/PyTorch | | **OpenLLaMA** | 3B-13B | Open reproduction of LLaMA | Python/PyTorch | + +## Mental Model + ```mermaid flowchart TD A[Open-Source GPT Ecosystem] --> B[Educational] @@ -69,7 +84,7 @@ flowchart TD - repository: [`karpathy/nanoGPT`](https://github.com/karpathy/nanoGPT) - stars: about **55k** -## Tutorial Structure +## Chapter Guide This tutorial is organized into 8 chapters that progressively build your understanding: diff --git a/tutorials/haystack-tutorial/README.md b/tutorials/haystack-tutorial/README.md index 4d1ebd4..a585c5b 100644 --- a/tutorials/haystack-tutorial/README.md +++ b/tutorials/haystack-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Haystack Tutorial" nav_order: 23 has_children: true +format_version: v2 --- # Haystack: Deep Dive Tutorial @@ -13,6 +14,17 @@ has_children: true [![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0) [![Python](https://img.shields.io/badge/Python-3.9+-blue)](https://github.com/deepset-ai/haystack) +## Why This Track Matters + +Haystack is increasingly relevant for developers working with modern AI/ML infrastructure. **Project**: [Haystack](https://github.com/deepset-ai/haystack) β€” An open-source framework for building production-ready LLM applications, RAG pipelines, and intelligent search systems, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with haystack +- understanding document stores +- understanding retrievers & search +- understanding generators & llms + ## What Is Haystack? Haystack is an open-source LLM framework by deepset for building composable AI pipelines. It provides a modular, component-based architecture that combines retrieval, generation, and evaluation into production-ready workflows. Haystack supports dozens of LLM providers, vector databases, and retrieval strategies out of the box. @@ -32,7 +44,7 @@ Haystack is an open-source LLM framework by deepset for building composable AI p - stars: about **24.5k** - latest release: [`v2.25.2`](https://github.com/deepset-ai/haystack/releases/tag/v2.25.2) (published 2026-03-05) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -71,7 +83,7 @@ graph TB JOINER --> RANKER --> PROMPT --> GEN ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |---------|-------|-------------------| @@ -105,6 +117,12 @@ Ready to begin? Start with [Chapter 1: Getting Started](01-getting-started.md). *Built with insights from the [Haystack repository](https://github.com/deepset-ai/haystack) and community documentation.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Getting Started with Haystack](01-getting-started.md) diff --git a/tutorials/huggingface-tutorial/README.md b/tutorials/huggingface-tutorial/README.md index b838eb9..9edeca6 100644 --- a/tutorials/huggingface-tutorial/README.md +++ b/tutorials/huggingface-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "HuggingFace Transformers Tutorial" nav_order: 20 has_children: true +format_version: v2 --- # HuggingFace Transformers Tutorial: Building State-of-the-Art AI Models @@ -18,6 +19,9 @@ HuggingFace Transformers[View Repo](https://github.com/huggingface/transfor Transformers has become the foundation of modern AI development, with over 100,000 models and 10,000+ datasets available through the HuggingFace Hub. + +## Mental Model + ```mermaid flowchart TD A[Data Input] --> B[HuggingFace Hub] @@ -45,7 +49,18 @@ flowchart TD class F output ``` -## Tutorial Chapters +## Why This Track Matters + +HuggingFace Transformers is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of HuggingFace Transformers covering Building State-of-the-Art AI Models, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with huggingface transf +- understanding text classification & analysis +- understanding text generation +- understanding question answering + +## Chapter Guide Welcome to your journey through the HuggingFace Transformers ecosystem! This tutorial explores how to leverage state-of-the-art AI models for your applications. @@ -64,7 +79,7 @@ Welcome to your journey through the HuggingFace Transformers ecosystem! This tut - stars: about **158k** - latest release: [`v5.3.0`](https://github.com/huggingface/transformers/releases/tag/v5.3.0) (published 2026-03-04) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/instructor-tutorial/README.md b/tutorials/instructor-tutorial/README.md index 39873c5..b075f49 100644 --- a/tutorials/instructor-tutorial/README.md +++ b/tutorials/instructor-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Instructor Tutorial" nav_order: 84 has_children: true +format_version: v2 --- # Instructor Tutorial: Structured LLM Outputs @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +Instructor is increasingly relevant for developers working with modern AI/ML infrastructure. Get reliable, typed responses from LLMs with Pydantic validation, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Extract Structured Data** reliably from any LLM +- **Define Schemas** with Pydantic for type safety +- **Handle Validation Errors** with automatic retries +- **Work with Complex Data** including nested objects + ## 🎯 What is Instructor? **Instructor**[View Repo](https://github.com/instructor-ai/instructor) is a library that makes it easy to get structured, validated outputs from LLMs. Instead of parsing free-form text, define a Pydantic model and Instructor ensures the LLM returns data that matches your schema. @@ -34,6 +46,9 @@ has_children: true | **Simple API** | Just patch your existing client | | **Extensible** | Custom validators and complex nested structures | + +## Mental Model + ```mermaid flowchart LR A[Prompt + Schema] --> B[Instructor] @@ -60,7 +75,7 @@ flowchart LR - stars: about **12.5k** - latest release: [`v1.14.5`](https://github.com/instructor-ai/instructor/releases/tag/v1.14.5) (published 2026-01-29) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and first structured extraction 2. **[Chapter 2: Pydantic Models](02-pydantic-models.md)** - Designing effective schemas @@ -71,7 +86,7 @@ flowchart LR 7. **[Chapter 7: Advanced Patterns](07-advanced.md)** - Validators, hooks, and optimization 8. **[Chapter 8: Production Use](08-production.md)** - Best practices and scaling -## What You'll Learn +## What You Will Learn - **Extract Structured Data** reliably from any LLM - **Define Schemas** with Pydantic for type safety diff --git a/tutorials/khoj-tutorial/README.md b/tutorials/khoj-tutorial/README.md index 9b058d8..234ab48 100644 --- a/tutorials/khoj-tutorial/README.md +++ b/tutorials/khoj-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Khoj AI - Personal Assistant Deep Dive" nav_order: 84 has_children: true +format_version: v2 --- # Khoj AI: Deep Dive Tutorial @@ -13,6 +14,17 @@ has_children: true [![License: AGPL v3](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0) [![Python](https://img.shields.io/badge/Python-Django-green)](https://github.com/khoj-ai/khoj) +## Why This Track Matters + +Khoj AI is increasingly relevant for developers working with modern AI/ML infrastructure. **Project**: [Khoj](https://github.com/khoj-ai/khoj) β€” An open-source, self-hostable AI personal assistant that connects to your notes, documents, and online data, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started +- understanding architecture overview +- understanding data connectors +- understanding search & retrieval + ## What Is Khoj? Khoj is an open-source AI personal assistant that transforms your scattered notes, documents, and online data into a searchable, conversational knowledge base. It combines semantic search with LLM-backed chat to help you retrieve, synthesize, and act on your personal information. Khoj can be self-hosted for full data privacy or used via the hosted service. @@ -32,7 +44,7 @@ Khoj is an open-source AI personal assistant that transforms your scattered note - stars: about **33.4k** - latest release: [`2.0.0-beta.25`](https://github.com/khoj-ai/khoj/releases/tag/2.0.0-beta.25) (published 2026-02-22) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -82,7 +94,7 @@ graph TB SERVER --> Storage ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |---------|-------|-------------------| @@ -116,6 +128,12 @@ Ready to begin? Start with [Chapter 1: Getting Started](01-getting-started.md). *Built with insights from the [Khoj repository](https://github.com/khoj-ai/khoj) and community documentation.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Getting Started](01-getting-started.md) diff --git a/tutorials/kubernetes-operator-patterns/README.md b/tutorials/kubernetes-operator-patterns/README.md index ad4287f..8ec505d 100644 --- a/tutorials/kubernetes-operator-patterns/README.md +++ b/tutorials/kubernetes-operator-patterns/README.md @@ -3,6 +3,7 @@ layout: default title: "Kubernetes Operator Patterns" nav_order: 76 has_children: true +format_version: v2 --- # Kubernetes Operator Patterns: Building Production-Grade Controllers @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +Kubernetes Operator Patterns is increasingly relevant for developers working with modern AI/ML infrastructure. Master Kubernetes Operators with hands-on Go implementation using the Operator SDK and controller-runtime library for enterprise application management, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Operator Development**: Build controllers that extend Kubernetes functionality +- **Go Programming**: Advanced Go patterns for concurrent, distributed systems +- **Kubernetes Deep Dive**: Internal workings of controllers, admission webhooks, and API extensions +- **Production Patterns**: Enterprise-grade operator development with testing and observability + ## 🎯 What are Kubernetes Operators? **Kubernetes Operators** extend the Kubernetes API to create, configure, and manage instances of complex applications. They encode operational knowledgeβ€”the kind typically held by human operatorsβ€”into software that can automate Day 1 (installation, configuration) and Day 2 (upgrades, backups, failover) operations. @@ -33,6 +45,9 @@ has_children: true | **Scalability Issues** | Native K8s scaling | | **Documentation Heavy** | Self-documenting APIs | + +## Mental Model + ```mermaid flowchart TD A[User] -->|kubectl apply| B[Kubernetes API Server] @@ -130,7 +145,7 @@ func (r *MyAppReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl - **Backup & Recovery**: Automated backup and disaster recovery - **Monitoring & Observability**: Integrated monitoring and alerting -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Operator SDK setup, project scaffolding, and core concepts 2. **[Chapter 2: Custom Resource Definitions](02-custom-resources.md)** - Designing and implementing CRDs with OpenAPI validation @@ -141,7 +156,7 @@ func (r *MyAppReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl 7. **[Chapter 7: Observability & Debugging](07-observability.md)** - Metrics, logging, tracing, and troubleshooting 8. **[Chapter 8: Production Deployment](08-production-deployment.md)** - OLM, Helm charts, security, and scaling patterns -## What You'll Learn +## What You Will Learn - **Operator Development**: Build controllers that extend Kubernetes functionality - **Go Programming**: Advanced Go patterns for concurrent, distributed systems diff --git a/tutorials/lancedb-tutorial/README.md b/tutorials/lancedb-tutorial/README.md index 57a81a2..ff80061 100644 --- a/tutorials/lancedb-tutorial/README.md +++ b/tutorials/lancedb-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "LanceDB Tutorial" nav_order: 45 has_children: true +format_version: v2 --- # LanceDB Tutorial: Serverless Vector Database for AI @@ -22,6 +23,17 @@ has_children: true --- +## Why This Track Matters + +LanceDB is increasingly relevant for developers working with modern AI/ML infrastructure. Master LanceDB, the open-source serverless vector database designed for AI applications, RAG systems, and semantic search, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Store Vectors** efficiently with the Lance format +- **Search Semantically** using approximate nearest neighbors +- **Filter Results** with SQL-like predicates +- **Build RAG Systems** with vector + full-text search + ## What is LanceDB? **LanceDB** is an open-source, serverless vector database built on the Lance data format. It's designed from the ground up for AI applications, offering fast vector similarity search, filtering, and full-text search without the operational overhead of traditional databases. @@ -38,6 +50,9 @@ has_children: true | **Python/JS Native** | First-class Python and JavaScript SDKs | | **Zero-Copy** | Memory-mapped access for efficiency | + +## Mental Model + ```mermaid flowchart TD A[Your Application] --> B[LanceDB] @@ -77,7 +92,7 @@ flowchart TD - stars: about **9.5k** - latest release: [`v0.27.0-beta.5`](https://github.com/lancedb/lancedb/releases/tag/v0.27.0-beta.5) (published 2026-03-09) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and first database 2. **[Chapter 2: Data Modeling](02-data-modeling.md)** - Schemas, tables, and data types @@ -88,7 +103,7 @@ flowchart TD 7. **[Chapter 7: Production Deployment](07-production.md)** - Cloud storage, scaling, and monitoring 8. **[Chapter 8: Advanced Patterns](08-advanced-patterns.md)** - Multi-tenancy, versioning, and RAG systems -## What You'll Learn +## What You Will Learn - **Store Vectors** efficiently with the Lance format - **Search Semantically** using approximate nearest neighbors diff --git a/tutorials/langchain-architecture-guide/README.md b/tutorials/langchain-architecture-guide/README.md index c77e551..cd41f3e 100644 --- a/tutorials/langchain-architecture-guide/README.md +++ b/tutorials/langchain-architecture-guide/README.md @@ -3,6 +3,7 @@ layout: default title: "LangChain Architecture - Internal Design Deep Dive" nav_order: 86 has_children: true +format_version: v2 --- # LangChain Architecture: Internal Design Deep Dive @@ -16,6 +17,9 @@ This guide explores LangChain[View Repo](https://github.com/langchain-ai/la Think of this as the difference between learning to drive a car and studying how the engine works. Both forms of knowledge are valuable, but understanding the internals gives you the power to extend, debug, and optimize the framework at a level that surface-level usage never can. + +## Mental Model + ```mermaid flowchart TB subgraph Core["langchain-core"] @@ -63,6 +67,17 @@ flowchart TB class LS,LG,LE eco ``` +## Why This Track Matters + +LangChain Architecture matters for developers building production systems. This track covers chapter 1: gett, chap, chapter 3: and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- understanding gett +- understanding chap +- understanding +- understanding chain + ## Who This Guide Is For This guide is designed for developers who already have working experience with LangChain and want to go deeper. You should be comfortable with: @@ -78,7 +93,7 @@ This guide is designed for developers who already have working experience with L - stars: about **130k** - latest release: [`langchain-core==1.2.19`](https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.19) (published 2026-03-13) -## Tutorial Chapters +## Chapter Guide Each chapter dissects a major subsystem of the LangChain codebase: @@ -119,6 +134,12 @@ Let's begin with [Chapter 1: Getting Started -- Ecosystem Overview](01-getting-s --- *Built with insights from the [LangChain](https://github.com/langchain-ai/langchain) project.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Getting Started -- Ecosystem Overview](01-getting-started.md) diff --git a/tutorials/langchain-tutorial/README.md b/tutorials/langchain-tutorial/README.md index 667dc0b..d87b0e7 100644 --- a/tutorials/langchain-tutorial/README.md +++ b/tutorials/langchain-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "LangChain Tutorial" nav_order: 10 has_children: true +format_version: v2 --- # LangChain Tutorial: Building AI Applications with Large Language Models @@ -11,6 +12,9 @@ LangChain[View Repo](https://github.com/langchain-ai/langchain) is a Imagine you're building a smart assistant that can not only answer questions but also remember previous conversations, search through documents, and even take actions on your behalf. LangChain makes this possible by providing a standardized way to connect language models with other sources of data and functionality. + +## Mental Model + ```mermaid flowchart TD A[User Input] --> B[Prompt Template] @@ -39,7 +43,18 @@ flowchart TD class G,H external ``` -## Tutorial Chapters +## Why This Track Matters + +LangChain is increasingly relevant for developers working with modern AI/ML infrastructure. **Pydantic 2 Required**: LangChain v0.3 fully migrated to Pydantic 2. Code using `langchain_core.pydantic_v1` should be updated to native Pydantic 2 syntax, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with langchain +- understanding prompt templates & chains +- understanding memory systems +- understanding document loading & processing + +## Chapter Guide Welcome to your journey through LangChain! This tutorial is structured to take you from basic concepts to advanced implementations: @@ -58,7 +73,7 @@ Welcome to your journey through LangChain! This tutorial is structured to take y - stars: about **130k** - latest release: [`langchain-core==1.2.19`](https://github.com/langchain-ai/langchain/releases/tag/langchain-core==1.2.19) (published 2026-03-13) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/langgraph-tutorial/README.md b/tutorials/langgraph-tutorial/README.md index 300c060..0b1cb62 100644 --- a/tutorials/langgraph-tutorial/README.md +++ b/tutorials/langgraph-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "LangGraph Tutorial" nav_order: 19 has_children: true +format_version: v2 --- # LangGraph Tutorial: Building Stateful Multi-Actor Applications @@ -18,6 +19,9 @@ LangGraph[View Repo](https://github.com/langchain-ai/langgraph) is a LangGraph enables developers to create sophisticated applications with multiple interacting components, persistent state management, and complex control flows that go beyond simple sequential chains. + +## Mental Model + ```mermaid flowchart TD A[User Input] --> B[State Manager] @@ -45,7 +49,18 @@ flowchart TD class H,J decision ``` -## Tutorial Chapters +## Why This Track Matters + +LangGraph is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of LangGraph covering Building Stateful Multi-Actor Applications, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with langgraph +- understanding state management +- understanding nodes and edges +- understanding conditional logic + +## Chapter Guide Welcome to your journey through stateful multi-actor applications! This tutorial explores how to build complex AI systems with LangGraph. @@ -64,7 +79,7 @@ Welcome to your journey through stateful multi-actor applications! This tutorial - stars: about **26.5k** - latest release: [`cli==0.4.18`](https://github.com/langchain-ai/langgraph/releases/tag/cli==0.4.18) (published 2026-03-15) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/letta-tutorial/README.md b/tutorials/letta-tutorial/README.md index aceb17a..8eda0e9 100644 --- a/tutorials/letta-tutorial/README.md +++ b/tutorials/letta-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Letta Tutorial" nav_order: 87 has_children: true +format_version: v2 --- # Letta Tutorial: Stateful LLM Agents @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +Letta is increasingly relevant for developers working with modern AI/ML infrastructure. Build AI agents with persistent memory using the framework formerly known as MemGPT, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Build Stateful Agents** that remember everything +- **Manage Memory Hierarchies** for infinite context +- **Create Custom Tools** for agent capabilities +- **Deploy Agent APIs** for production use + ## 🎯 What is Letta? **Letta**[View Repo](https://github.com/letta-ai/letta) (formerly MemGPT) is a framework for building stateful LLM agents with persistent memory. Unlike traditional chatbots that forget context, Letta agents maintain long-term memory across conversations. @@ -34,6 +46,9 @@ has_children: true | **Multi-Agent** | Coordinate multiple agents | | **REST API** | Deploy agents as services | + +## Mental Model + ```mermaid flowchart TD A[User Message] --> B[Letta Agent] @@ -72,7 +87,7 @@ flowchart TD - stars: about **21.6k** - latest release: [`0.16.6`](https://github.com/letta-ai/letta/releases/tag/0.16.6) (published 2026-03-04) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and first agent 2. **[Chapter 2: Memory Architecture](02-memory.md)** - Core, archival, and recall memory @@ -83,7 +98,7 @@ flowchart TD 7. **[Chapter 7: REST API](07-api.md)** - Deploying agents as services 8. **[Chapter 8: Production Deployment](08-production.md)** - Scaling and best practices -## What You'll Learn +## What You Will Learn - **Build Stateful Agents** that remember everything - **Manage Memory Hierarchies** for infinite context diff --git a/tutorials/liveblocks-tutorial/README.md b/tutorials/liveblocks-tutorial/README.md index 47733b4..09c0dd3 100644 --- a/tutorials/liveblocks-tutorial/README.md +++ b/tutorials/liveblocks-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Liveblocks - Real-Time Collaboration Deep Dive" nav_order: 85 has_children: true +format_version: v2 --- # Liveblocks - Real-Time Collaboration Deep Dive @@ -14,6 +15,17 @@ has_children: true A comprehensive guide to building collaborative applications with Liveblocks, the real-time collaboration infrastructure used by companies building the next generation of multiplayer experiences. +## Why This Track Matters + +Liveblocks - Real-Time Collaboration Deep Dive matters for developers building production systems. This track covers chapter 1: getting started, chapter 2: presence & awarene, chapter 3: storage & and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- understanding getting started +- understanding presence & awarene +- understanding storage & +- understanding comments & threads + ## What is Liveblocks? Liveblocks is a platform for adding real-time collaboration features to any application. It provides the infrastructure and APIs needed to build experiences like those found in Figma, Notion, Google Docs, and other collaborative tools. Rather than building complex real-time systems from scratch, Liveblocks gives you production-ready primitives for presence, storage, comments, and notifications. @@ -65,7 +77,7 @@ graph TB | **Text Editor** | Collaborative text editing (Yjs/Tiptap) | Rich text documents, notes | | **AI** | AI-powered collaboration features | Copilots within collaborative contexts | -## Tutorial Structure +## Chapter Guide This tutorial is organized into eight chapters that progressively build your understanding of Liveblocks: @@ -107,7 +119,7 @@ Before starting, you should be comfortable with: - **Next.js** basics (recommended but not required) - **REST APIs** and WebSocket concepts -## Architecture Overview +## Mental Model ```mermaid graph LR @@ -188,6 +200,12 @@ Ready to get started? Head to **[Chapter 1: Getting Started](./01-getting-starte --- *Built with insights from the [Liveblocks](https://liveblocks.io) platform.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Getting Started](01-getting-started.md) diff --git a/tutorials/llama-cpp-tutorial/README.md b/tutorials/llama-cpp-tutorial/README.md index 3369225..834efdb 100644 --- a/tutorials/llama-cpp-tutorial/README.md +++ b/tutorials/llama-cpp-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "llama.cpp Tutorial" nav_order: 86 has_children: true +format_version: v2 --- # llama.cpp Tutorial: Local LLM Inference @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +llama.cpp is increasingly relevant for developers working with modern AI/ML infrastructure. Run large language models efficiently on your local machine with pure C/C++, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Build llama.cpp** for your platform +- **Run Models Locally** without cloud dependencies +- **Quantize Models** for memory efficiency +- **Use GPU Acceleration** for faster inference + ## 🎯 What is llama.cpp? **llama.cpp**[View Repo](https://github.com/ggerganov/llama.cpp) is a pure C/C++ implementation for running LLMs locally. It supports a wide range of models and hardware, from MacBooks to servers, with impressive performance through quantization and optimization. @@ -34,6 +46,9 @@ has_children: true | **CPU Optimized** | AVX, AVX2, AVX-512 acceleration | | **Model Support** | LLaMA, Mistral, Phi, Qwen, and more | + +## Mental Model + ```mermaid flowchart TD A[GGUF Model File] --> B[llama.cpp] @@ -68,7 +83,7 @@ flowchart TD - stars: about **98.1k** - latest release: [`b8370`](https://github.com/ggerganov/llama.cpp/releases/tag/b8370) (published 2026-03-16) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Building llama.cpp and running your first model 2. **[Chapter 2: Model Formats](02-model-formats.md)** - Understanding GGUF and quantization @@ -79,7 +94,7 @@ flowchart TD 7. **[Chapter 7: Advanced Features](07-advanced.md)** - Grammar, embedding, and multimodal 8. **[Chapter 8: Integration](08-integration.md)** - Python bindings and production use -## What You'll Learn +## What You Will Learn - **Build llama.cpp** for your platform - **Run Models Locally** without cloud dependencies diff --git a/tutorials/llama-factory-tutorial/README.md b/tutorials/llama-factory-tutorial/README.md index 9d11ccb..72937ec 100644 --- a/tutorials/llama-factory-tutorial/README.md +++ b/tutorials/llama-factory-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "LLaMA-Factory Tutorial" nav_order: 28 has_children: true +format_version: v2 --- # LLaMA-Factory Tutorial: Unified Framework for LLM Training and Fine-tuning @@ -18,6 +19,9 @@ LLaMA-Factory[View Repo](https://github.com/hiyouga/LLaMA-Factory) is LLaMA-Factory democratizes access to advanced LLM capabilities by providing a unified, user-friendly interface that works across different model architectures and training scenarios. + +## Mental Model + ```mermaid flowchart TD A[Raw Data] --> B[LLaMA-Factory Pipeline] @@ -49,7 +53,18 @@ flowchart TD class G,N,O deployment ``` -## Tutorial Chapters +## Why This Track Matters + +LLaMA-Factory is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of LLaMA-Factory covering Unified Framework for LLM Training and Fine-tuning, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with llama-factory +- understanding data preparation +- understanding model configuration +- understanding training pipeline + +## Chapter Guide Welcome to your journey through unified LLM training! This tutorial explores how to master LLaMA-Factory for building and fine-tuning large language models. @@ -68,7 +83,7 @@ Welcome to your journey through unified LLM training! This tutorial explores how - stars: about **68.5k** - latest release: [`v0.9.4`](https://github.com/hiyouga/LLaMA-Factory/releases/tag/v0.9.4) (published 2025-12-31) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/llamaindex-tutorial/README.md b/tutorials/llamaindex-tutorial/README.md index 836d4b6..a2a5095 100644 --- a/tutorials/llamaindex-tutorial/README.md +++ b/tutorials/llamaindex-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "LlamaIndex Tutorial" nav_order: 17 has_children: true +format_version: v2 --- # LlamaIndex Tutorial: Building Advanced RAG Systems and Data Frameworks @@ -18,6 +19,9 @@ LlamaIndex[View Repo](https://github.com/run-llama/llama_index) (form LlamaIndex enables you to build sophisticated AI applications that can reason over private data, maintain context across conversations, and provide accurate, up-to-date responses based on your specific knowledge base. + +## Mental Model + ```mermaid flowchart TD A[Data Sources] --> B[LlamaIndex Ingestion] @@ -49,7 +53,18 @@ flowchart TD class E,N,O output ``` -## Tutorial Chapters +## Why This Track Matters + +LlamaIndex is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of LlamaIndex covering Building Advanced RAG Systems and Data Frameworks, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with llamaindex +- understanding data ingestion & loading +- understanding indexing & storage +- understanding query engines & retrieval + +## Chapter Guide Welcome to your journey through advanced RAG systems and data frameworks! This tutorial explores how to build powerful AI applications with LlamaIndex's comprehensive toolkit. @@ -68,7 +83,7 @@ Welcome to your journey through advanced RAG systems and data frameworks! This t - stars: about **47.7k** - latest release: [`v0.14.16`](https://github.com/run-llama/llama_index/releases/tag/v0.14.16) (published 2026-03-10) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/lobechat-ai-platform/README.md b/tutorials/lobechat-ai-platform/README.md index 9e3dcbb..e8248cc 100644 --- a/tutorials/lobechat-ai-platform/README.md +++ b/tutorials/lobechat-ai-platform/README.md @@ -2,6 +2,7 @@ title: "LobeChat AI Platform" nav_order: 96 has_children: true +format_version: v2 --- # LobeChat AI Platform: Deep Dive Tutorial @@ -12,6 +13,17 @@ has_children: true [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/TypeScript-Next.js-blue)](https://github.com/lobehub/lobe-chat) +## Why This Track Matters + +LobeChat AI Platform is increasingly relevant for developers working with modern AI/ML infrastructure. **Project**: [LobeChat](https://github.com/lobehub/lobe-chat) β€” An open-source, modern-design AI chat framework for building private LLM applications, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding lobechat system overview +- understanding chat interface implementation +- understanding streaming architecture +- understanding ai integration patterns + ## What Is LobeChat? LobeChat is an open-source AI chat framework that enables you to build and deploy private LLM applications with multi-agent collaboration, plugin extensibility, and a modern UI. It supports dozens of model providers and offers one-click deployment via Vercel or Docker. @@ -31,7 +43,7 @@ LobeChat is an open-source AI chat framework that enables you to build and deplo - stars: about **73.7k** - latest release: [`v2.1.42`](https://github.com/lobehub/lobe-chat/releases/tag/v2.1.42) (published 2026-03-14) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -66,7 +78,7 @@ graph TB Backend --> Extensions ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |---------|-------|-------------------| @@ -99,6 +111,12 @@ Ready to begin? Start with [Chapter 1: System Overview](01-system-overview.md). *Built with insights from the [LobeChat repository](https://github.com/lobehub/lobe-chat) and community documentation.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: LobeChat System Overview](01-system-overview.md) diff --git a/tutorials/localai-tutorial/README.md b/tutorials/localai-tutorial/README.md index 5939918..0d6339c 100644 --- a/tutorials/localai-tutorial/README.md +++ b/tutorials/localai-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "LocalAI Tutorial" nav_order: 92 has_children: true +format_version: v2 --- # LocalAI Tutorial: Self-Hosted OpenAI Alternative @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +LocalAI is increasingly relevant for developers working with modern AI/ML infrastructure. Run LLMs, image generation, and audio models locally with an OpenAI-compatible API, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Deploy LocalAI** with Docker or from source +- **Install Models** from the gallery +- **Use OpenAI SDK** with local models +- **Generate Images** with Stable Diffusion + ## 🎯 What is LocalAI? **LocalAI**[View Repo](https://github.com/mudler/LocalAI) is a free, open-source alternative to OpenAI that runs locally. It provides an OpenAI-compatible API for LLMs, image generation, audio transcription, and text-to-speechβ€”all running on consumer hardware. @@ -34,6 +46,9 @@ has_children: true | **Docker Ready** | Simple deployment | | **Privacy** | 100% local, no data leaves | + +## Mental Model + ```mermaid flowchart TD A[OpenAI SDK/API Calls] --> B[LocalAI Server] @@ -71,7 +86,7 @@ flowchart TD - stars: about **43.7k** - latest release: [`v4.0.0`](https://github.com/mudler/LocalAI/releases/tag/v4.0.0) (published 2026-03-14) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation and first model 2. **[Chapter 2: Model Gallery](02-models.md)** - Installing and managing models @@ -82,7 +97,7 @@ flowchart TD 7. **[Chapter 7: Configuration](07-configuration.md)** - Advanced settings and tuning 8. **[Chapter 8: Integrations](08-integration.md)** - Production integrations and optimization -## What You'll Learn +## What You Will Learn - **Deploy LocalAI** with Docker or from source - **Install Models** from the gallery diff --git a/tutorials/mcp-python-sdk-tutorial/README.md b/tutorials/mcp-python-sdk-tutorial/README.md index 808697c..dac29f8 100644 --- a/tutorials/mcp-python-sdk-tutorial/README.md +++ b/tutorials/mcp-python-sdk-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "MCP Python SDK Tutorial" nav_order: 89 has_children: true +format_version: v2 --- # MCP Python SDK Tutorial: Building AI Tool Servers @@ -13,6 +14,17 @@ has_children: true [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![Python](https://img.shields.io/badge/Python-3.10+-blue)](https://github.com/modelcontextprotocol/python-sdk) +## Why This Track Matters + +MCP Python SDK is increasingly relevant for developers working with modern AI/ML infrastructure. Master the Model Context Protocol Python SDK to build custom tool servers that extend Claude and other LLMs with powerful capabilities, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with mcp python sdk +- understanding core concepts - resources, tools, and prompts +- understanding server architecture +- understanding advanced patterns + ## 🎯 What is MCP Python SDK? The **Model Context Protocol (MCP) Python SDK** is the official Python implementation for building MCP servers - standardized tool providers that AI assistants like Claude can securely interact with. MCP enables LLMs to access external data sources, call APIs, execute code, and interact with systems through a unified protocol. @@ -35,7 +47,7 @@ The **Model Context Protocol (MCP) Python SDK** is the official Python implement - stars: about **22.2k** - latest release: [`v1.26.0`](https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.26.0) (published 2026-01-24) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -82,7 +94,7 @@ graph TB class FS,DB,API,CODE backend ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |:--------|:------|:------------------| @@ -107,7 +119,7 @@ graph TB | **Testing** | pytest, pytest-asyncio | | **Common Integrations** | FastAPI, SQLAlchemy, httpx, aiofiles | -## What You'll Build +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/meilisearch-tutorial/README.md b/tutorials/meilisearch-tutorial/README.md index bc83575..3a08a07 100644 --- a/tutorials/meilisearch-tutorial/README.md +++ b/tutorials/meilisearch-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "MeiliSearch Tutorial" nav_order: 23 has_children: true +format_version: v2 --- # MeiliSearch Tutorial: Lightning Fast Search Engine @@ -26,7 +27,18 @@ MeiliSearch[View Repo](https://github.com/meilisearch/meilisearch) is --- -## 🎯 What You'll Learn +## Why This Track Matters + +MeiliSearch is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of MeiliSearch covering Lightning Fast Search Engine, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with meilisearch +- understanding document management +- understanding search fundamentals +- understanding typo tolerance & relevance + +## What You Will Learn This comprehensive tutorial will guide you through Meilisearch, a powerful search engine written in Rust that provides: @@ -73,7 +85,7 @@ curl -X POST 'http://localhost:7700/indexes/movies/documents' \ curl 'http://localhost:7700/indexes/movies/search?q=avengers' ``` -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB diff --git a/tutorials/mem0-tutorial/README.md b/tutorials/mem0-tutorial/README.md index 3c68f33..29f3614 100644 --- a/tutorials/mem0-tutorial/README.md +++ b/tutorials/mem0-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Mem0 Tutorial" nav_order: 15 has_children: true +format_version: v2 --- # Mem0 Tutorial: Building Production-Ready AI Agents with Scalable Long-Term Memory @@ -18,6 +19,9 @@ Mem0[View Repo](https://github.com/mem0ai/mem0) is a universal memory Mem0 enhances AI assistants and agents with a production-ready memory system that delivers +26% accuracy improvements, 91% faster responses, and 90% lower token usage compared to traditional memory approaches. + +## Mental Model + ```mermaid flowchart TD A[User Input] --> B[Memory Layer] @@ -47,7 +51,18 @@ flowchart TD class E,F output ``` -## Tutorial Chapters +## Why This Track Matters + +Mem0 is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Mem0 covering Building Production-Ready AI Agents with Scalable Long-Term Memory, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with mem0 +- understanding memory architecture & types +- understanding core memory operations +- understanding advanced memory features + +## Chapter Guide Welcome to your journey through scalable AI memory systems! This tutorial explores how to build production-ready AI agents with intelligent long-term memory. @@ -66,7 +81,7 @@ Welcome to your journey through scalable AI memory systems! This tutorial explor - stars: about **50k** - latest release: [`v1.0.5`](https://github.com/mem0ai/mem0/releases/tag/v1.0.5) (published 2026-03-03) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/n8n-ai-tutorial/README.md b/tutorials/n8n-ai-tutorial/README.md index 4b80385..8f7fa0f 100644 --- a/tutorials/n8n-ai-tutorial/README.md +++ b/tutorials/n8n-ai-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "n8n AI Tutorial" nav_order: 93 has_children: true +format_version: v2 --- # n8n AI Tutorial: Workflow Automation with AI @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +n8n AI is increasingly relevant for developers working with modern AI/ML infrastructure. Build powerful AI-powered automations with n8n's visual workflow builder, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Build AI Workflows** visually with n8n +- **Connect LLM Providers** (OpenAI, Anthropic, Ollama) +- **Process Documents** with AI extraction +- **Create AI Agents** with tool access + ## 🎯 What is n8n? **n8n**[View Repo](https://github.com/n8n-io/n8n) is a fair-code workflow automation platform that lets you connect anything to everything. With its AI capabilities, you can build intelligent automations that leverage LLMs, process documents, and make smart decisions. @@ -34,6 +46,9 @@ has_children: true | **Code When Needed** | JavaScript/Python in workflows | | **Agents** | Build AI agents with tools | + +## Mental Model + ```mermaid flowchart LR A[Trigger] --> B[n8n Workflow] @@ -67,7 +82,7 @@ flowchart LR - stars: about **179k** - latest release: [`n8n@2.11.4`](https://github.com/n8n-io/n8n/releases/tag/n8n@2.11.4) (published 2026-03-13) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation and first workflow 2. **[Chapter 2: AI Nodes](02-ai-nodes.md)** - Using OpenAI, Anthropic, and local models @@ -78,7 +93,7 @@ flowchart LR 7. **[Chapter 7: Custom AI Tools](07-custom-tools.md)** - Extending agent capabilities 8. **[Chapter 8: Production Deployment](08-production.md)** - Scaling and monitoring -## What You'll Learn +## What You Will Learn - **Build AI Workflows** visually with n8n - **Connect LLM Providers** (OpenAI, Anthropic, Ollama) diff --git a/tutorials/n8n-mcp-tutorial/README.md b/tutorials/n8n-mcp-tutorial/README.md index f1d795c..3b2225d 100644 --- a/tutorials/n8n-mcp-tutorial/README.md +++ b/tutorials/n8n-mcp-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "n8n MCP Tutorial" nav_order: 88 has_children: true +format_version: v2 --- # n8n Model Context Protocol: Deep Dive Tutorial @@ -13,6 +14,17 @@ has_children: true [![License: Sustainable Use](https://img.shields.io/badge/License-Sustainable_Use-blue.svg)](https://github.com/n8n-io/n8n/blob/master/LICENSE.md) [![TypeScript](https://img.shields.io/badge/TypeScript-Node.js-blue)](https://github.com/n8n-io/n8n) +## Why This Track Matters + +n8n Model Context Protocol is increasingly relevant for developers working with modern AI/ML infrastructure. **Project**: [n8n](https://github.com/n8n-io/n8n) β€” Visual workflow automation with Model Context Protocol (MCP) integration for AI-powered tool use, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding understanding mcp protocol and n8n integration +- understanding the n8nmcpengine - core integration interface +- understanding session management and http server +- understanding n8napiclient - communicating with n8n + ## What Is This Tutorial? This tutorial covers n8n's integration with the Model Context Protocol (MCP) β€” the open standard for connecting AI models to external tools and data sources. Learn how n8n implements MCP servers, manages sessions, and exposes workflow automation as AI-callable tools. @@ -31,7 +43,7 @@ This tutorial covers n8n's integration with the Model Context Protocol (MCP) β€” - stars: about **179k** - latest release: [`n8n@2.11.4`](https://github.com/n8n-io/n8n/releases/tag/n8n@2.11.4) (published 2026-03-13) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -61,7 +73,7 @@ graph TB DISC --> TOOLS ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |---------|-------|-------------------| @@ -92,6 +104,12 @@ Ready to begin? Start with [Chapter 1: MCP Protocol](01_mcp_protocol.md). *Built with insights from the [n8n repository](https://github.com/n8n-io/n8n) and MCP specification.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Understanding MCP Protocol and n8n Integration](01_mcp_protocol.md) diff --git a/tutorials/openbb-tutorial/README.md b/tutorials/openbb-tutorial/README.md index 6e27b44..b93efbf 100644 --- a/tutorials/openbb-tutorial/README.md +++ b/tutorials/openbb-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "OpenBB Tutorial" nav_order: 33 has_children: true +format_version: v2 --- # OpenBB Tutorial: Complete Guide to Investment Research Platform @@ -20,6 +21,17 @@ has_children: true --- +## Why This Track Matters + +OpenBB is increasingly relevant for developers working with modern AI/ML infrastructure. Democratize investment research with OpenBB's comprehensive financial data and analysis platform, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with openbb +- understanding financial data access +- understanding technical analysis +- understanding fundamental analysis + ## 🎯 What is OpenBB? **OpenBB** is an open-source investment research platform that provides access to financial data, analytics, and research tools. Originally forked from Gamma Technologies' Gamestonk Terminal, OpenBB has evolved into a comprehensive platform for investment research, data analysis, and portfolio management. @@ -39,7 +51,7 @@ has_children: true - stars: about **63.2k** - latest release: [`ODP`](https://github.com/OpenBB-finance/OpenBB/releases/tag/ODP) (published 2026-02-09) -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -97,7 +109,7 @@ graph TB | **[07-custom-extensions](07-custom-extensions.md)** | Building Custom Extensions | 45 min | πŸ”΄ Expert | | **[08-enterprise-deployment](08-enterprise-deployment.md)** | Enterprise Setup & Scaling | 50 min | πŸ”΄ Expert | -## 🎯 Learning Outcomes +## What You Will Learn By the end of this tutorial, you'll be able to: @@ -238,7 +250,7 @@ Special thanks to the OpenBB development team and the open-source community for *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with OpenBB](01-getting-started.md) 2. [Chapter 2: Financial Data Access](02-data-access.md) diff --git a/tutorials/openclaw-tutorial/README.md b/tutorials/openclaw-tutorial/README.md index 274f7a2..2ecfb8f 100644 --- a/tutorials/openclaw-tutorial/README.md +++ b/tutorials/openclaw-tutorial/README.md @@ -2,6 +2,7 @@ title: "OpenClaw Deep Dive" nav_order: 94 has_children: true +format_version: v2 --- # OpenClaw: Deep Dive Tutorial @@ -12,6 +13,17 @@ has_children: true [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/TypeScript-82%25-blue)](https://github.com/openclaw/openclaw) +## Why This Track Matters + +OpenClaw is increasingly relevant for developers working with modern AI/ML infrastructure. **Project**: [OpenClaw](https://github.com/openclaw/openclaw) β€” Your own personal AI assistant. Any OS. Any Platform, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with openclaw +- understanding gateway architecture +- understanding channel drivers +- understanding agent runtime + ## What Is OpenClaw? OpenClaw is an open-source, self-hosted personal AI assistant that connects to the messaging channels you already use β€” WhatsApp, Telegram, Slack, Discord, iMessage, Signal, and more. Everything runs locally, meaning your data stays on your hardware. @@ -33,7 +45,7 @@ OpenClaw is an open-source, self-hosted personal AI assistant that connects to t - stars: about **316k** - latest release: [`v2026.3.13-1`](https://github.com/openclaw/openclaw/releases/tag/v2026.3.13-1) (published 2026-03-14) -## Architecture Overview +## Mental Model ```mermaid graph TB @@ -73,7 +85,7 @@ graph TB Runtime --> Execution ``` -## Tutorial Structure +## Chapter Guide | Chapter | Topic | What You'll Learn | |---------|-------|-------------------| @@ -118,6 +130,12 @@ Ready to begin? Start with [Chapter 1: Getting Started](01-getting-started.md). *Built with insights from the [OpenClaw repository](https://github.com/openclaw/openclaw) and community documentation.* +## What You Will Learn + +- Core architecture and key abstractions +- Practical patterns for production use +- Integration and extensibility approaches + ## Navigation & Backlinks - [Start Here: Chapter 1: Getting Started with OpenClaw](01-getting-started.md) diff --git a/tutorials/outlines-tutorial/README.md b/tutorials/outlines-tutorial/README.md index 0cdc6ca..676bbfc 100644 --- a/tutorials/outlines-tutorial/README.md +++ b/tutorials/outlines-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Outlines Tutorial" nav_order: 15 has_children: true +format_version: v2 --- # Outlines Tutorial: Structured Text Generation with LLMs @@ -16,7 +17,18 @@ has_children: true Outlines[View Repo](https://github.com/outlines-dev/outlines) is a Python library that allows you to control Large Language Model outputs with structural constraints. Use JSON Schema, regular expressions, context-free grammars, and more to guide model generation. -## Tutorial Chapters +## Why This Track Matters + +Outlines is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Outlines covering Structured Text Generation with LLMs, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Constrained Generation**: Force LLMs to follow specific patterns and structures +- **JSON Schema Validation**: Generate perfectly structured JSON data +- **Type Safety**: Use Pydantic models for runtime type checking +- **Grammar Control**: Implement context-free grammars for complex structures + +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation and basic constrained generation 2. **[Chapter 2: Text Patterns](02-text-patterns.md)** - Regular expressions and string constraints @@ -33,7 +45,7 @@ Outlines[View Repo](https://github.com/outlines-dev/outlines) is a Py - stars: about **13.6k** - latest release: [`1.2.12`](https://github.com/dottxt-ai/outlines/releases/tag/1.2.12) (published 2026-03-03) -## What You'll Learn +## What You Will Learn - **Constrained Generation**: Force LLMs to follow specific patterns and structures - **JSON Schema Validation**: Generate perfectly structured JSON data @@ -68,7 +80,7 @@ By the end of this tutorial, you'll be able to: - πŸ“Š **FastAPI Ready**: Type-safe API responses - πŸ—οΈ **Framework Agnostic**: Works with any Python application -## Architecture Overview +## Mental Model ```mermaid graph TD diff --git a/tutorials/perplexica-tutorial/README.md b/tutorials/perplexica-tutorial/README.md index 39b4b2b..579cfa3 100644 --- a/tutorials/perplexica-tutorial/README.md +++ b/tutorials/perplexica-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Perplexica Tutorial" nav_order: 23 has_children: true +format_version: v2 --- # Perplexica Tutorial: AI-Powered Search Engine @@ -18,6 +19,9 @@ Perplexica[View Repo](https://github.com/ItzCrazyKns/Perplexica) is a Perplexica combines the power of large language models with web search capabilities to provide comprehensive, contextual answers to complex queries, making it an excellent tool for research and information discovery. + +## Mental Model + ```mermaid flowchart TD A[User Query] --> B[Query Processing] @@ -46,7 +50,18 @@ flowchart TD class F,G,H,I,J synthesis ``` -## Tutorial Chapters +## Why This Track Matters + +Perplexica is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Perplexica covering AI-Powered Search Engine, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with perplexica +- understanding search engine architecture +- understanding ai integration +- understanding web scraping and data collection + +## Chapter Guide Welcome to your journey through AI-powered search technology! This tutorial explores building intelligent search engines with Perplexica. @@ -65,7 +80,7 @@ Welcome to your journey through AI-powered search technology! This tutorial expl - stars: about **33k** - latest release: [`v1.12.1`](https://github.com/ItzCrazyKns/Perplexica/releases/tag/v1.12.1) (published 2025-12-31) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/phidata-tutorial/README.md b/tutorials/phidata-tutorial/README.md index e23a2a6..688409d 100644 --- a/tutorials/phidata-tutorial/README.md +++ b/tutorials/phidata-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Phidata Tutorial" nav_order: 16 has_children: true +format_version: v2 --- # Phidata Tutorial: Building Autonomous AI Agents @@ -16,7 +17,18 @@ has_children: true Phidata[View Repo](https://github.com/phidatahq/phidata) is a framework for building autonomous AI agents with memory, reasoning, and tool integration capabilities. Create intelligent agents that can perform complex tasks, maintain conversation context, and use various tools to accomplish goals. -## Tutorial Chapters +## Why This Track Matters + +Phidata is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Phidata covering Building Autonomous AI Agents, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Agent Creation**: Build autonomous AI agents with specialized capabilities +- **Tool Integration**: Connect agents to external tools, APIs, and services +- **Memory Management**: Implement persistent memory and context retention +- **Multi-Agent Coordination**: Create collaborative agent teams + +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation and your first AI agent 2. **[Chapter 2: Agent Architecture](02-agent-architecture.md)** - Understanding Phidata's agent components @@ -33,7 +45,7 @@ Phidata[View Repo](https://github.com/phidatahq/phidata) is a framewo - stars: about **38.7k** - latest release: [`v2.5.9`](https://github.com/phidatahq/phidata/releases/tag/v2.5.9) (published 2026-03-10) -## What You'll Learn +## What You Will Learn - **Agent Creation**: Build autonomous AI agents with specialized capabilities - **Tool Integration**: Connect agents to external tools, APIs, and services @@ -69,7 +81,7 @@ By the end of this tutorial, you'll be able to: - πŸ“Š **Analytics**: Detailed metrics and performance tracking - πŸš€ **Production Ready**: Enterprise-grade reliability and monitoring -## Architecture Overview +## Mental Model ```mermaid graph TD diff --git a/tutorials/photoprism-tutorial/README.md b/tutorials/photoprism-tutorial/README.md index 149cf8b..26d0a04 100644 --- a/tutorials/photoprism-tutorial/README.md +++ b/tutorials/photoprism-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "PhotoPrism Tutorial" nav_order: 25 has_children: true +format_version: v2 --- # PhotoPrism Tutorial: AI-Powered Photos App @@ -17,7 +18,18 @@ has_children: true --- -## 🎯 What You'll Learn +## Why This Track Matters + +PhotoPrism is increasingly relevant for developers working with modern AI/ML infrastructure. **AI Photo Management Revolution**: Enhanced facial recognition, LLM integrations, and advanced organization features mark PhotoPrism's evolution, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with photoprism +- understanding ai features & configuration +- understanding photo management +- understanding search & discovery + +## What You Will Learn This comprehensive tutorial will guide you through PhotoPrism, a powerful AI-powered photo management application that brings professional photo organization to your personal server: @@ -60,7 +72,7 @@ docker run -d \ # Access at http://localhost:2342 ``` -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -168,7 +180,7 @@ By the end of this tutorial, you'll be able to: *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with PhotoPrism](01-getting-started.md) 2. [Chapter 2: AI Features & Configuration](02-ai-features-configuration.md) diff --git a/tutorials/postgresql-query-planner/README.md b/tutorials/postgresql-query-planner/README.md index ab7bed9..7370389 100644 --- a/tutorials/postgresql-query-planner/README.md +++ b/tutorials/postgresql-query-planner/README.md @@ -3,6 +3,7 @@ layout: default title: "PostgreSQL Query Planner" nav_order: 1 has_children: true +format_version: v2 --- # PostgreSQL Query Planner Deep Dive @@ -14,7 +15,18 @@ has_children: true [![C](https://img.shields.io/badge/C-blue)](https://github.com/postgres/postgres) -## What You'll Learn +## Why This Track Matters + +PostgreSQL Query Planner Deep Dive is increasingly relevant for developers working with modern AI/ML infrastructure. Master PostgreSQL's query execution engine, understand EXPLAIN output, and optimize complex queries for maximum performance, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding query planning fundamentals +- understanding statistics and cost estimation +- understanding scan operations +- understanding join strategies + +## What You Will Learn This tutorial provides an in-depth exploration of PostgreSQL's query planner and executor, teaching you how to analyze, understand, and optimize query performance at the database level. @@ -45,6 +57,9 @@ This tutorial provides an in-depth exploration of PostgreSQL's query planner and β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ ``` + +## Mental Model + ```mermaid graph LR SQL[SQL Query] --> PARSER[Parser] @@ -69,7 +84,7 @@ graph LR - PostgreSQL installed (14+ recommended) - Familiarity with database concepts (tables, indexes, joins) -## Tutorial Chapters +## Chapter Guide ### [Chapter 1: Query Planning Fundamentals](01-fundamentals.md) Understanding how PostgreSQL transforms SQL into execution plans, the role of the planner, and reading basic EXPLAIN output. diff --git a/tutorials/posthog-tutorial/README.md b/tutorials/posthog-tutorial/README.md index a299442..0789490 100644 --- a/tutorials/posthog-tutorial/README.md +++ b/tutorials/posthog-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "PostHog Tutorial" nav_order: 29 has_children: true +format_version: v2 --- # PostHog Tutorial: Open Source Product Analytics Platform @@ -16,6 +17,9 @@ PostHog[View Repo](https://github.com/PostHog/posthog) is a comprehen PostHog empowers product teams to build better products by providing deep insights into user behavior without compromising on privacy or data ownership. + +## Mental Model + ```mermaid flowchart TD A[User Interactions] --> B[PostHog SDK] @@ -45,7 +49,18 @@ flowchart TD class output ``` -## Tutorial Chapters +## Why This Track Matters + +PostHog matters for developers building production systems. This track covers chapter 1: getting started with posthog, chapter 2: event tracking & properties, chapter 3: user analytics & funnels and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- understanding getting started with posthog +- understanding event tracking & properties +- understanding user analytics & funnels +- understanding session recordings + +## Chapter Guide Welcome to your journey through modern product analytics! This tutorial explores how to master PostHog for building data-driven products. @@ -64,7 +79,7 @@ Welcome to your journey through modern product analytics! This tutorial explores - stars: about **32k** - latest release: [`posthog-cli-v0.7.1`](https://github.com/PostHog/posthog/releases/tag/posthog-cli-v0.7.1) (published 2026-03-05) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/pydantic-ai-tutorial/README.md b/tutorials/pydantic-ai-tutorial/README.md index 19c3656..9e88aa7 100644 --- a/tutorials/pydantic-ai-tutorial/README.md +++ b/tutorials/pydantic-ai-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Pydantic AI Tutorial" nav_order: 17 has_children: true +format_version: v2 --- # Pydantic AI Tutorial: Type-Safe AI Agent Development @@ -16,7 +17,18 @@ has_children: true Pydantic AI[View Repo](https://github.com/pydantic/pydantic-ai) is a Python library for building type-safe AI agents using Pydantic models. It provides structured outputs, runtime validation, and seamless integration with popular AI providers. -## Tutorial Chapters +## Why This Track Matters + +Pydantic AI is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Pydantic AI covering Type-Safe AI Agent Development, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Type Safety**: Build AI agents with guaranteed type-safe inputs and outputs +- **Structured Data**: Generate perfectly structured responses using Pydantic models +- **Provider Integration**: Connect with OpenAI, Anthropic, Google, and other providers +- **Tool Integration**: Extend agent capabilities with custom tools and functions + +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation and basic agent creation with type safety 2. **[Chapter 2: Model Configuration](02-model-configuration.md)** - Setting up different AI providers and models @@ -33,7 +45,7 @@ Pydantic AI[View Repo](https://github.com/pydantic/pydantic-ai) is a - stars: about **15.5k** - latest release: [`v1.68.0`](https://github.com/pydantic/pydantic-ai/releases/tag/v1.68.0) (published 2026-03-13) -## What You'll Learn +## What You Will Learn - **Type Safety**: Build AI agents with guaranteed type-safe inputs and outputs - **Structured Data**: Generate perfectly structured responses using Pydantic models @@ -67,7 +79,7 @@ By the end of this tutorial, you'll be able to: - πŸ”„ **Async Operations**: Non-blocking operations for high performance - πŸ“ˆ **Scalability**: Built for production workloads and monitoring -## Architecture Overview +## Mental Model ```mermaid graph TD diff --git a/tutorials/quivr-tutorial/README.md b/tutorials/quivr-tutorial/README.md index f1ab55b..6275055 100644 --- a/tutorials/quivr-tutorial/README.md +++ b/tutorials/quivr-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Quivr Tutorial" nav_order: 31 has_children: true +format_version: v2 --- # Quivr Tutorial: Open-Source RAG Framework for Document Ingestion @@ -16,6 +17,9 @@ Quivr[View Repo](https://github.com/QuivrHQ/quivr) is an open-source Quivr combines the power of vector databases, large language models, and modern web technologies to create a comprehensive platform for document-based AI interactions. + +## Mental Model + ```mermaid flowchart TD A[Document Upload] --> B[Text Extraction] @@ -46,7 +50,18 @@ flowchart TD class G,H,I,J output ``` -## Tutorial Chapters +## Why This Track Matters + +Quivr matters for developers building production systems. This track covers chapter 1: getting started with quivr, chapter 2: document processing, chapter 3: vector embeddings and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- understanding getting started with quivr +- understanding document processing +- understanding vector embeddings +- understanding query processing + +## Chapter Guide Welcome to your journey through document-based AI interactions! This tutorial explores how to build intelligent RAG applications with Quivr. @@ -65,7 +80,7 @@ Welcome to your journey through document-based AI interactions! This tutorial ex - stars: about **39k** - latest release: [`core-0.0.33`](https://github.com/QuivrHQ/quivr/releases/tag/core-0.0.33) (published 2025-02-04) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/ragflow-tutorial/README.md b/tutorials/ragflow-tutorial/README.md index e70cf62..1824c67 100644 --- a/tutorials/ragflow-tutorial/README.md +++ b/tutorials/ragflow-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "RAGFlow Tutorial" nav_order: 32 has_children: true +format_version: v2 --- # RAGFlow Tutorial: Complete Guide to Open-Source RAG Engine @@ -20,6 +21,17 @@ has_children: true --- +## Why This Track Matters + +RAGFlow is increasingly relevant for developers working with modern AI/ML infrastructure. Transform documents into intelligent Q&A systems with RAGFlow's comprehensive RAG (Retrieval-Augmented Generation) platform, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with ragflow +- understanding document processing +- understanding knowledge base setup +- understanding retrieval system + ## 🎯 What is RAGFlow? **RAGFlow** is an open-source RAG (Retrieval-Augmented Generation) engine designed for document-based question answering systems. It combines advanced document parsing, vector search, and large language models to create intelligent conversational interfaces that can answer questions based on your documents. @@ -39,7 +51,7 @@ has_children: true - stars: about **75.1k** - latest release: [`v0.24.0`](https://github.com/infiniflow/ragflow/releases/tag/v0.24.0) (published 2026-02-10) -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -67,7 +79,7 @@ graph TB | **[07-advanced-features](07-advanced-features.md)** | Advanced Features & Customization | 45 min | πŸ”΄ Expert | | **[08-production-deployment](08-production-deployment.md)** | Production Deployment & Scaling | 50 min | πŸ”΄ Expert | -## 🎯 Learning Outcomes +## What You Will Learn By the end of this tutorial, you'll be able to: @@ -205,7 +217,7 @@ Special thanks to the RAGFlow development team for creating this amazing open-so *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with RAGFlow](01-getting-started.md) 2. [Chapter 2: Document Processing](02-document-processing.md) diff --git a/tutorials/react-fiber-internals/README.md b/tutorials/react-fiber-internals/README.md index 5c0d9d1..2325826 100644 --- a/tutorials/react-fiber-internals/README.md +++ b/tutorials/react-fiber-internals/README.md @@ -3,6 +3,7 @@ layout: default title: "React Fiber Internals" nav_order: 1 has_children: true +format_version: v2 --- # React Fiber Internals @@ -14,7 +15,18 @@ has_children: true [![JavaScript](https://img.shields.io/badge/JavaScript-blue)](https://github.com/facebook/react) -## What You'll Learn +## Why This Track Matters + +React Fiber Internals is increasingly relevant for developers working with modern AI/ML infrastructure. Deep dive into React's reconciliation algorithm, the Fiber architecture that powers modern React applications, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding introduction to fiber +- understanding fiber data structure +- understanding render phase +- understanding commit phase + +## What You Will Learn This tutorial provides a comprehensive exploration of React Fiber, the reimplementation of React's core algorithm introduced in React 16. Understanding Fiber helps you write more performant React applications and debug complex rendering issues. @@ -59,6 +71,9 @@ This tutorial provides a comprehensive exploration of React Fiber, the reimpleme β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ ``` + +## Mental Model + ```mermaid graph TB JSX[JSX / createElement] --> ELEMENTS[React Elements] @@ -86,7 +101,7 @@ graph TB - Familiarity with JavaScript and the DOM - Basic understanding of data structures (trees, linked lists) -## Tutorial Chapters +## Chapter Guide ### [Chapter 1: Introduction to Fiber](01-introduction.md) Why React needed Fiber, the problems it solves, and how it differs from the Stack reconciler. diff --git a/tutorials/semantic-kernel-tutorial/README.md b/tutorials/semantic-kernel-tutorial/README.md index 71a26f4..bb330e5 100644 --- a/tutorials/semantic-kernel-tutorial/README.md +++ b/tutorials/semantic-kernel-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Semantic Kernel Tutorial" nav_order: 89 has_children: true +format_version: v2 --- # Semantic Kernel Tutorial: Microsoft's AI Orchestration @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +Semantic Kernel is increasingly relevant for developers working with modern AI/ML infrastructure. Build enterprise AI applications with Microsoft's SDK for integrating LLMs, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Build AI Applications** with Microsoft's enterprise SDK +- **Create Plugins** with native and semantic functions +- **Engineer Prompts** with templates and variables +- **Connect AI Services** from multiple providers + ## 🎯 What is Semantic Kernel? **Semantic Kernel**[View Repo](https://github.com/microsoft/semantic-kernel) is Microsoft's open-source SDK for integrating LLMs into applications. It provides a unified way to orchestrate AI services, plugins, and memory, making it easy to build sophisticated AI applications. @@ -34,6 +46,9 @@ has_children: true | **Connectors** | OpenAI, Azure, Hugging Face | | **Enterprise Ready** | Built for production at scale | + +## Mental Model + ```mermaid flowchart TD A[Application] --> B[Semantic Kernel] @@ -73,7 +88,7 @@ flowchart TD - stars: about **27.5k** - latest release: [`python-1.41.0`](https://github.com/microsoft/semantic-kernel/releases/tag/python-1.41.0) (published 2026-03-13) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and first kernel 2. **[Chapter 2: Plugins & Functions](02-plugins.md)** - Native and semantic functions @@ -84,7 +99,7 @@ flowchart TD 7. **[Chapter 7: Agents](07-agents.md)** - Building autonomous AI agents 8. **[Chapter 8: Production Deployment](08-production.md)** - Enterprise patterns and scaling -## What You'll Learn +## What You Will Learn - **Build AI Applications** with Microsoft's enterprise SDK - **Create Plugins** with native and semantic functions diff --git a/tutorials/sillytavern-tutorial/README.md b/tutorials/sillytavern-tutorial/README.md index 4950c49..2724302 100644 --- a/tutorials/sillytavern-tutorial/README.md +++ b/tutorials/sillytavern-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "SillyTavern Tutorial" nav_order: 34 has_children: true +format_version: v2 --- # SillyTavern Tutorial: Advanced LLM Frontend for Power Users @@ -20,6 +21,17 @@ has_children: true --- +## Why This Track Matters + +SillyTavern is increasingly relevant for developers working with modern AI/ML infrastructure. Unlock the full potential of large language models with SillyTavern's comprehensive interface for role-playing, creative writing, and AI experimentation, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with sillytavern +- understanding character creation +- understanding chat management +- understanding prompt engineering + ## 🎯 What is SillyTavern? **SillyTavern** is a user-friendly interface for chatting with AI Large Language Models (LLMs), with advanced features for power users. It supports extensive customization, multiple model backends, and a rich ecosystem of extensions for enhanced functionality. @@ -40,7 +52,7 @@ has_children: true - stars: about **24.4k** - latest release: [`1.16.0`](https://github.com/SillyTavern/SillyTavern/releases/tag/1.16.0) (published 2026-02-14) -## πŸ—οΈ Architecture Overview +## Mental Model ```mermaid graph TB @@ -112,7 +124,7 @@ graph TB | **[07-advanced-features](07-advanced-features.md)** | Power User Features | 45 min | πŸ”΄ Expert | | **[08-custom-development](08-custom-development.md)** | Extension Development | 50 min | πŸ”΄ Expert | -## 🎯 Learning Outcomes +## What You Will Learn By the end of this tutorial, you'll be able to: @@ -263,7 +275,7 @@ Special thanks to the SillyTavern development team and the vibrant community for *Generated by [AI Codebase Knowledge Builder](https://github.com/johnxie/awesome-code-docs)* -## Full Chapter Map +## Chapter Guide 1. [Chapter 1: Getting Started with SillyTavern](01-getting-started.md) 2. [Chapter 2: Character Creation](02-character-creation.md) diff --git a/tutorials/siyuan-tutorial/README.md b/tutorials/siyuan-tutorial/README.md index fe1c0d1..b3bf640 100644 --- a/tutorials/siyuan-tutorial/README.md +++ b/tutorials/siyuan-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "SiYuan Tutorial" nav_order: 12 has_children: true +format_version: v2 --- # SiYuan Tutorial: Privacy-First Knowledge Management @@ -18,6 +19,9 @@ SiYuan[View Repo](https://github.com/siyuan-note/siyuan) is a privacy SiYuan combines the best of note-taking apps with advanced features like block-based editing, bi-directional linking, and powerful query capabilities. It's designed for serious knowledge workers who value privacy and data ownership. + +## Mental Model + ```mermaid flowchart TD A[User Interface] --> B[Block System] @@ -42,7 +46,18 @@ flowchart TD class H,I,J extensions ``` -## Tutorial Chapters +## Why This Track Matters + +SiYuan is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of SiYuan covering Privacy-First Knowledge Management, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with siyuan +- understanding block-based architecture +- understanding data storage & persistence +- understanding query system & search + +## Chapter Guide Welcome to your journey through SiYuan's architecture! This tutorial explores how to build privacy-first knowledge management systems with local data control. @@ -61,7 +76,7 @@ Welcome to your journey through SiYuan's architecture! This tutorial explores ho - stars: about **41.9k** - latest release: [`v3.6.0`](https://github.com/siyuan-note/siyuan/releases/tag/v3.6.0) (published 2026-03-13) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/smolagents-tutorial/README.md b/tutorials/smolagents-tutorial/README.md index acf6ec9..521d12b 100644 --- a/tutorials/smolagents-tutorial/README.md +++ b/tutorials/smolagents-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Smolagents Tutorial" nav_order: 76 has_children: true +format_version: v2 --- # Smolagents Tutorial: Hugging Face's Lightweight Agent Framework @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +Smolagents is increasingly relevant for developers working with modern AI/ML infrastructure. Build efficient AI agents with minimal code using Hugging Face's smolagents library, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **Create Minimal Agents** that accomplish complex tasks +- **Use Built-in Tools** for web search, image generation, and more +- **Build Custom Tools** tailored to your domain +- **Execute Code Safely** with sandboxed Python execution + ## 🎯 What is Smolagents? **Smolagents**[View Repo](https://github.com/huggingface/smolagents) is Hugging Face's lightweight library for building AI agents. It provides a minimal yet powerful abstraction for creating agents that can use tools, execute code, and solve complex tasks. @@ -33,6 +45,9 @@ has_children: true | **Model Agnostic** | Works with any LLM through a unified interface | | **Transparency** | Clear visibility into agent reasoning and actions | + +## Mental Model + ```mermaid flowchart TD A[User Task] --> B[Smolagent] @@ -67,7 +82,7 @@ flowchart TD - stars: about **26.1k** - latest release: [`v1.24.0`](https://github.com/huggingface/smolagents/releases/tag/v1.24.0) (published 2026-01-16) -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and your first smolagent 2. **[Chapter 2: Understanding Agents](02-understanding-agents.md)** - Agent types and execution modes @@ -78,7 +93,7 @@ flowchart TD 7. **[Chapter 7: Advanced Patterns](07-advanced.md)** - Multi-agent systems and orchestration 8. **[Chapter 8: Production Deployment](08-production.md)** - Scaling, safety, and best practices -## What You'll Learn +## What You Will Learn - **Create Minimal Agents** that accomplish complex tasks - **Use Built-in Tools** for web search, image generation, and more diff --git a/tutorials/supabase-tutorial/README.md b/tutorials/supabase-tutorial/README.md index fd387d6..84443d0 100644 --- a/tutorials/supabase-tutorial/README.md +++ b/tutorials/supabase-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Supabase Tutorial" nav_order: 26 has_children: true +format_version: v2 --- # Supabase Tutorial: Building Modern Backend Applications @@ -16,6 +17,9 @@ Supabase[View Repo](https://github.com/supabase/supabase) is an open- Supabase transforms how developers build applications by providing a complete backend infrastructure that scales automatically while maintaining full control and customization capabilities. + +## Mental Model + ```mermaid flowchart TD A[Client Application] --> B[Supabase Client] @@ -54,7 +58,18 @@ flowchart TD class I,J,K,L,M,N,O,P,Q,R,S,T advanced ``` -## Tutorial Chapters +## Why This Track Matters + +Supabase matters for developers building production systems. This track covers chapter 1: getting started with supabase, chapter 2: database design & management, chapter 3: authentication & authorization and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- understanding getting started with supabase +- understanding database design & management +- understanding authentication & authorization +- understanding real-time features + +## Chapter Guide Welcome to your journey through modern backend development! This tutorial explores how to build scalable, secure applications with Supabase's comprehensive platform. @@ -73,7 +88,7 @@ Welcome to your journey through modern backend development! This tutorial explor - stars: about **99.1k** - latest release: [`v1.26.03`](https://github.com/supabase/supabase/releases/tag/v1.26.03) (published 2026-03-05) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/superagi-tutorial/README.md b/tutorials/superagi-tutorial/README.md index e5de0b1..b01c6cf 100644 --- a/tutorials/superagi-tutorial/README.md +++ b/tutorials/superagi-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "SuperAGI Tutorial" nav_order: 25 has_children: true +format_version: v2 --- # SuperAGI Tutorial: Production-Ready Autonomous AI Agents @@ -18,6 +19,9 @@ SuperAGI[View Repo](https://github.com/TransformerOptimus/SuperAGI) i SuperAGI combines the power of large language models with practical agent architectures, enabling agents to plan, execute, and learn from their experiences in real-world applications. + +## Mental Model + ```mermaid flowchart TD A[User Goal] --> B[Agent Reasoning] @@ -47,7 +51,18 @@ flowchart TD class F,G learning ``` -## Tutorial Chapters +## Why This Track Matters + +SuperAGI is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of SuperAGI covering Production-Ready Autonomous AI Agents, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with superagi +- understanding agent architecture +- understanding tool integration +- understanding memory & learning + +## Chapter Guide Welcome to your journey through autonomous AI agent development! This tutorial explores how to build production-ready autonomous agents with SuperAGI. @@ -66,7 +81,7 @@ Welcome to your journey through autonomous AI agent development! This tutorial e - stars: about **17.3k** - latest release: [`v0.0.14`](https://github.com/TransformerOptimus/SuperAGI/releases/tag/v0.0.14) (published 2024-01-16) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/swarm-tutorial/README.md b/tutorials/swarm-tutorial/README.md index 050b640..7ef2d4a 100644 --- a/tutorials/swarm-tutorial/README.md +++ b/tutorials/swarm-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "OpenAI Swarm Tutorial" nav_order: 71 has_children: true +format_version: v2 --- # OpenAI Swarm Tutorial: Lightweight Multi-Agent Orchestration @@ -20,6 +21,17 @@ has_children: true --- +## Why This Track Matters + +OpenAI Swarm matters for developers building production systems. This track covers chapter 1: getting started with openai swarm, chapter 2: agent design, chapter 3: function calling & tools and helps you understand how the components fit together for real-world use. + +This track focuses on: + +- **Design Specialized Agents** with distinct roles and capabilities +- **Implement Smooth Handoffs** between agents based on context +- **Build Complex Workflows** with multi-agent collaboration +- **Manage Shared State** using context variables + ## 🎯 What is Swarm? **Swarm**[View Repo](https://github.com/openai/swarm) is an educational framework from OpenAI designed for lightweight multi-agent orchestration. It provides a simple, ergonomic way to coordinate multiple AI agents, enabling seamless handoffs and collaborative problem-solving. @@ -34,6 +46,9 @@ has_children: true | **Context Variables** | Shared state passed between agents during handoffs | | **Function Calling** | Tool integration for agent capabilities | + +## Mental Model + ```mermaid flowchart LR A[User Request] --> B[Triage Agent] @@ -66,7 +81,7 @@ flowchart LR - repository: [`openai/swarm`](https://github.com/openai/swarm) - stars: about **21.2k** -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, setup, and your first Swarm agent 2. **[Chapter 2: Agent Design](02-agent-design.md)** - Creating agents with instructions and personalities @@ -77,7 +92,7 @@ flowchart LR 7. **[Chapter 7: Multi-Agent Patterns](07-multi-agent-patterns.md)** - Complex orchestration strategies 8. **[Chapter 8: Production Considerations](08-production.md)** - Scaling, monitoring, and best practices -## What You'll Learn +## What You Will Learn - **Design Specialized Agents** with distinct roles and capabilities - **Implement Smooth Handoffs** between agents based on context diff --git a/tutorials/turborepo-tutorial/README.md b/tutorials/turborepo-tutorial/README.md index 9d7ae19..a43629f 100644 --- a/tutorials/turborepo-tutorial/README.md +++ b/tutorials/turborepo-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Turborepo Tutorial" nav_order: 21 has_children: true +format_version: v2 --- # Turborepo Tutorial: High-Performance Monorepo Build System @@ -18,6 +19,9 @@ Turborepo[View Repo](https://github.com/vercel/turborepo) is a high-p Turborepo enables developers to build scalable monorepos with efficient caching, parallel execution, and smart dependency management, making large codebases feel as fast as small ones. + +## Mental Model + ```mermaid flowchart TD A[Monorepo] --> B[Turborepo] @@ -52,7 +56,18 @@ flowchart TD class J,K,L,M,N,O,P,Q optimization ``` -## Tutorial Chapters +## Why This Track Matters + +Turborepo is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Turborepo covering High-Performance Monorepo Build System, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with turborepo +- understanding workspace configuration +- understanding task pipelines +- understanding caching strategies + +## Chapter Guide Welcome to your journey through high-performance monorepo development! This tutorial explores building and optimizing large-scale JavaScript/TypeScript codebases with Turborepo. @@ -71,7 +86,7 @@ Welcome to your journey through high-performance monorepo development! This tuto - stars: about **30k** - latest release: [`v2.8.17`](https://github.com/vercel/turborepo/releases/tag/v2.8.17) (published 2026-03-13) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: diff --git a/tutorials/vllm-tutorial/README.md b/tutorials/vllm-tutorial/README.md index 927ce4e..6b4d9b2 100644 --- a/tutorials/vllm-tutorial/README.md +++ b/tutorials/vllm-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "vLLM Tutorial" nav_order: 75 has_children: true +format_version: v2 --- # vLLM Tutorial: High-Performance LLM Inference @@ -19,6 +20,17 @@ has_children: true --- +## Why This Track Matters + +vLLM is increasingly relevant for developers working with modern AI/ML infrastructure. Master vLLM for blazing-fast, cost-effective large language model inference with advanced optimization techniques, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- **High-Performance Inference** - Achieve maximum throughput with minimal latency +- **Memory Optimization** - Efficiently serve large models with limited resources +- **Production Deployment** - Scale vLLM for enterprise applications +- **Advanced Features** - Streaming, tool calling, and multi-modal capabilities + ## 🎯 What is vLLM? **vLLM**[View Repo](https://github.com/vllm-project/vllm) is a high-performance, memory-efficient inference engine for large language models. It achieves state-of-the-art serving throughput while maintaining low latency, making it ideal for production LLM deployments. @@ -33,6 +45,9 @@ has_children: true | **Scalability** | Excellent | Limited | | **Cost Efficiency** | Superior | Higher operational costs | + +## Mental Model + ```mermaid flowchart TD A[Input Request] --> B[Continuous Batching] @@ -72,7 +87,7 @@ Custom GPU kernels for attention, normalization, and matrix operations that outp ### Advanced Scheduling Intelligent request scheduling that minimizes latency while maximizing throughput. -## Tutorial Chapters +## Chapter Guide 1. **[Chapter 1: Getting Started](01-getting-started.md)** - Installation, basic setup, and your first vLLM inference 2. **[Chapter 2: Model Loading](02-model-loading.md)** - Loading different model formats (HuggingFace, quantized, etc.) @@ -83,7 +98,7 @@ Intelligent request scheduling that minimizes latency while maximizing throughpu 7. **[Chapter 7: Production Deployment](07-production-deployment.md)** - Serving with FastAPI, Docker, and Kubernetes 8. **[Chapter 8: Monitoring & Scaling](08-monitoring-scaling.md)** - Performance monitoring and auto-scaling -## What You'll Learn +## What You Will Learn - **High-Performance Inference** - Achieve maximum throughput with minimal latency - **Memory Optimization** - Efficiently serve large models with limited resources diff --git a/tutorials/whisper-cpp-tutorial/README.md b/tutorials/whisper-cpp-tutorial/README.md index 9d32ba2..f603725 100644 --- a/tutorials/whisper-cpp-tutorial/README.md +++ b/tutorials/whisper-cpp-tutorial/README.md @@ -3,6 +3,7 @@ layout: default title: "Whisper.cpp Tutorial" nav_order: 11 has_children: true +format_version: v2 --- # Whisper.cpp Tutorial: High-Performance Speech Recognition in C/C++ @@ -18,6 +19,9 @@ Whisper.cpp[View Repo](https://github.com/ggml-org/whisper.cpp) is a Imagine building a voice assistant that can run on a Raspberry Pi, or adding speech recognition to an embedded system. Whisper.cpp makes this possible by running the Whisper model entirely on CPU with minimal memory requirements. + +## Mental Model + ```mermaid flowchart TD A[Audio Input] --> B[Feature Extraction] @@ -40,7 +44,18 @@ flowchart TD class H,I,J performance ``` -## Tutorial Chapters +## Why This Track Matters + +Whisper.cpp is increasingly relevant for developers working with modern AI/ML infrastructure. A deep technical walkthrough of Whisper.cpp covering High-Performance Speech Recognition in C/C++, and this track helps you understand the architecture, key patterns, and production considerations. + +This track focuses on: + +- understanding getting started with whisper.cpp +- understanding audio processing fundamentals +- understanding model architecture & ggml +- understanding core api & usage patterns + +## Chapter Guide Welcome to your journey through Whisper.cpp! This tutorial takes you from basic audio processing to building complete speech recognition applications. @@ -59,7 +74,7 @@ Welcome to your journey through Whisper.cpp! This tutorial takes you from basic - stars: about **47.6k** - latest release: [`v1.8.3`](https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.3) (published 2026-01-15) -## What You'll Learn +## What You Will Learn By the end of this tutorial, you'll be able to: