Como Desenvolvi uma Memória que Evolui Sozinha no Claude Code + Obsidian (Método do Karpathy)

Share

Summary

This video explains how to build a personal knowledge base using LLMs, Claude Code, and Obsidian, following the method proposed by Andrej Karpathy. The author demonstrates how to ingest data from various sources, process it, and create a connected knowledge graph for optimized learning.

Highlights

Introduction to the LLM Knowledge Base Concept
00:00:00

The video introduces Andrej Karpathy's method of using Large Language Models (LLMs) to create a personal knowledge base. The speaker, Audermus, with 6 years of experience in AI, explains how this system optimizes learning and research, similar to a personal wiki.

Understanding Karpathy's Tweet and Key Components
00:00:59

Audermus details Karpathy's tweet, highlighting the use of LLMs for personal knowledge base construction across various research topics. The process involves data ingestion from sources like YouTube, articles, and blogs, using tools like the Obsidian Web Clipper Extension. The system categorizes information into 'raw' files and processed 'wiki' concepts.

Architecture and Workflow of the Knowledge Base System
00:08:24

The video outlines the system's architecture: data from various sources (articles, GitHub repos, etc.) enters a 'raw' folder. An LLM then compiles these into a 'wiki' of digestible knowledge, explaining concepts and entities. Backlinks create a knowledge graph, and the system supports Q&A, generating responses in formats like Markdown, slides, or graphs. Obsidian acts as the IDE.

Setting Up Claude Code and Obsidian for Your Knowledge Base
00:11:49

Audermus guides viewers through setting up their personal knowledge base. He provides a detailed prompt for Claude Code that, after answering specific questions about the project's purpose and data sources, generates a configuration for Obsidian. This includes a folder structure and initial settings.

Configuring Obsidian and Ingesting Web Content
00:16:17

The speaker demonstrates how to open the created folder in Obsidian and configure the Obsidian Web Clipper extension. This extension allows users to import web pages into their Obsidian vault, which automatically stores the content as raw data in a designated 'clippings' folder.

Processing and Linking Ingested Articles with Claude Code
00:20:58

Audermus shows how to use Claude Code to process the raw web content. By typing 'injest' and referencing the article, the LLM analyzes the text, identifies key concepts and entities, and creates detailed wiki pages, linking them in the knowledge graph. This process enriches the personal knowledge base with structured information.

Ingesting YouTube Videos and the Role of the MCP Server
00:26:40

As a bonus, the video explains how to ingest YouTube videos by configuring a custom connector in Claude Code, referencing an MCP server (Media Cloud Platform). This enables the LLM to retrieve and process video transcripts, adding them to the knowledge base and linking relevant concepts.

Understanding the Difference Between LLM Wiki and RAG
00:32:56

Audermus clarifies the distinction between the LLM wiki method and Retrieval Augmented Generation (RAG). While both use external knowledge, RAG relies on semantic search and vectorial databases for efficient information retrieval, especially at scale. The LLM wiki, conversely, directly processes an index and is better suited for smaller, personal knowledge bases, though less efficient with larger datasets due to context window limitations.

Recently Summarized Articles

Loading...