Loading...
Loading...
3,528 documents available
id: embedding-first-chunking-second-smarter-rag-retrieval-with-max-min-semantic-chunking.md
!!! danger "Experimental"
This document explains how to use LangChain's text splitters to divide documents into smaller chunks for better processing by Large Language Models (LLMs).
keywords: [recursivecharactertextsplitter]
Author: [nawazdhandala](https://github.com/nawazdhandala)
**Join us at Interrupt: The Agent AI Conference by LangChain on May 13 & 14 in San Francisco!**

This guide provides a comprehensive overview of how to leverage the ElevenLabs API to generate long-form, multi-host audio content. It is specifically tailored for integration into the existing `rhythm-lab-app`, building upon its current implementation of single-voice podcast generation. By the end of this guide, you will be able to create dynamic, conversational audio with multiple speakers, enhancing the immersive experience of your application.
title: Task Chunking for ADHD Brains
[kerchunk][kerchunk] supports cloud-friendly access of data
`snix-castore`'s BlobStore is a content-addressed storage system, using [blake3]
I asked ChatGPT how we can chunk a YouTube transcript
title: How to implement HLS chunking in Vercel
CodeRAG uses Abstract Syntax Tree (AST) parsing to split code into semantic chunks rather than arbitrary character or line-based splits. This produces more meaningful search units.
**Datum:** 2026-03-10
This specification describes the binary data chunking algorithm used by
This document describes the design for extending `calculate-optimal-chunks.ts` to support **per-example granularity** in test distribution, complementing the existing per-file approach.
<!-- markdownlint-disable-file MD029 MD036 MD026 -->
**Supersedes:** Previous `extractChunks()` + `splitLargeChunk()` approach
The original system was creating too many tiny chunks (14 chunks for 1793 characters), fragmenting context and reducing answer quality. The new **adaptive chunking system** intelligently handles all document types with optimal chunk sizes.
The architecture you described is the standard setup for embedding-based retrieval in RAG systems:
<!-- AGENT_TASK_START: task-8-system-prompt-chunking.md -->
Examples of using different chunking strategies.
**Status:** In Progress