Sablier integrations using LLMs
You can use large language models (LLMs) to assist in building Sablier integrations. We provide resources to help LLMs consume our documentation effectively.
Plain text markdown files
You can access all documentation as plain text markdown files by adding .md
to the end of any URL. For example, you can
find the plain text version of this page at
https://docs.sablier.com/guides/building-with-llms.md.
This helps AI agents consume our content and allows you to copy and paste entire docs into an LLM. This format is preferable to scraping or copying from our documentation pages because:
- Plain text contains fewer formatting tokens.
- Content that isn't rendered in the default view (for example, hidden in a tab) is rendered in the plain text version.
- LLMs can parse and understand markdown hierarchy.
We also host an /llms.txt file which contains URLs to the plain text versions of
our pages. The /llms.txt
file is an emerging standard for making websites more accessible to LLMs.
Protocol-specific markdown files
We provide specialized markdown files for each protocol:
- llms-lockup.txt - Complete markdown file for Lockup documentation
- llms-flow.txt - Complete markdown file for Flow documentation
- llms-airdrops.txt - Complete markdown file for Merkle Airdrops documentation
- llms-training-data.txt - Full documentation content for training custom models