0 Fork 0

mirror of https://github.com/Haidra-Org/AI-Horde.git synced 2026-11-06 05:17:31 +00:00

Files

T

History

tazlin b3eb8a8877 docs: adjust copy for legibility, tone and readability

- Reworded the chat worker how-to, tutorial, wire examples and the explanation page so each sentence states one thing in plain terms
- The same pass over the docstrings, comments and log messages of the minimal chat worker tool and the chat test helpers
- Renamed the wire-example tests' answered_by field to response_example

2026-11-02 13:31:00 -05:00

check_token_counter.py

docs: adjust copy for legibility, tone and readability

2026-11-02 13:31:00 -05:00

minimal_chat_worker.py

docs: adjust copy for legibility, tone and readability

2026-11-02 13:31:00 -05:00

README.md

feat(tools): add a minimal chat worker for OpenAI-compatible backends

2026-11-02 13:30:59 -05:00

README.md

Minimal chat worker

minimal_chat_worker.py serves AI Horde chat jobs from any backend with an OpenAI-compatible POST /v1/chat/completions. tests/integration/test_minimal_chat_worker_example.py runs it against the in-process horde. Write a minimal chat worker shows how to run it.

--template-overhead sets the tokens the fit check adds to every prompt count, for every --token-counter. It replaces the startup measurement: the probe's prompt count for bytes, and 0 for an exact counter.