AIQB
TutorialsOrdinary

Code Search RAG: Chunk by Function With tree-sitter, Not by 512 Tokens

Source: DEV Community·

Summary

Fixed token windows cut functions in half. A runnable tree-sitter chunker that splits Python by function and class, scored against plain token windows.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-b9829fc02c9d2e5b205e628b
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Your Browser Can Do WHAT?! 5 AI Features That Actually Work
Are AI models running directly in the browser finally good enough to use in production? Let's find...
Source: DEV Community
TutorialsOrdinary
Top 5 Enterprise AI Gateways
Most companies did not plan their AI infrastructure. It grew as usage across teams increased. Someone...
Source: DEV Community
TutorialsOrdinary
Your App Has Login. That Doesn’t Mean Your Users’ Data Is Safe.
Your app has login. Passwords are hashed. Tokens are validated. Private pages redirect...
Source: DEV Community
TutorialsOrdinary
Gemini Gems become skills in November and custom GPTs retire on December 11. What to copy out first.
If you built a Gem in Gemini or a custom GPT in ChatGPT, it is about to be converted into something...
Source: DEV Community · ChatGPT / GPT / Gemini
TutorialsOrdinary
GGUF vs safetensors — the runtime decides, not the format
The same model in three containers: 397 MB of Q4_K_M GGUF, 1.20 GB of BF16 GGUF, 1.50 GB of BF16 safetensors. The bytes are the record's honest numbers — the runtime decides.
Source: DEV Community
TutorialsOrdinary
Your computer-use agent clicks 20 pixels off: screenshots vs the accessibility tree
Every computer-use agent has to answer one question before it can click anything: what is on the...
Source: DEV Community
TutorialsOrdinary
A 1B model isn't smart enough to read a contract. So I never asked it to.
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle TL;DR —...
Source: DEV Community
TutorialsOrdinary
Where Claude Code, Codex, Copilot CLI and OpenCode Keep Config, Memory and Logs
One cheat sheet per CLI: config, CLAUDE.md/AGENTS.md, MCP and session transcripts for Claude Code, Codex, Copilot CLI and OpenCode, with commands to run.
Source: DEV Community · Claude
TutorialsOrdinary
Writing Pages That Survive RAG Chunking
When Perplexity, ChatGPT search or Google's AI features answer a question, they don't read your page...
Source: DEV Community · ChatGPT
TutorialsOrdinary
Pure vs Effectful: Why My n8n Retry Policy Tags Nodes, Not Failures
Last week I posted my retry budget rule: retry once with feedback, then route to a human. A reader...
Source: DEV Community