jchristn /

TextChunker

TextChunker turns text, streams, files, lists, and tables into clean, token sized chunks for retrieval augmented generation and embedding pipelines

A new way for AI to search for data
View on GitHub
1GitHub stars
18commits on main
0forks

C# 99.6%, Batchfile 0.4% · created 2026-09-22 · last push 2026-10-03

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit db8bfbac0b. It is the newest commit on main.

Selected work

Joel Christner
@jchristn

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-10-28. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

chunkchunkerchunkingchunksparseparserparser-libraryrag

Example questions

The prompt

Paste it into your AI agent. It clones jchristn/TextChunker at the pinned commit and indexes it on your machine.

Search the GitHub repository jchristn/TextChunker with XERJ (https://hub.xerj.org/corpus/jchristn--textchunker).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/jchristn/TextChunker TextChunker && git -C TextChunker checkout db8bfbac0b0a3e764d086ad3036eb8f389064e1b
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./TextChunker --url http://127.0.0.1:9200 --prefix textchunker --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

Related

Joel ChristnerAI, prompts and agents corporahttparseoxclightningcsstevfik/gleannhazemkhaled-94/faq_generatoradlerqa/wardeniq

Stats: GitHub API, fetched 2026-10-29. Selected work and consent: the XERJ registry.