Metadata-Version: 2.3
Name: pjlab_lwh_t_convert
Version: 0.1.0
Summary: Handy benchmarking converter for any agentic harness.
Author: opposj
Author-email: opposj <18965385801@163.com>
Requires-Dist: fastapi>=0.115.0
Requires-Dist: uvicorn>=0.30.0
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# Test Converter

OpenAI-compatible chat completion shim for routing `/chat/completions` requests to a local processor.

## Add Plugin

Run `t_convert_0425` in your repo to create `t_convert_processor.py`, then fill its `processor` function by importing and adapting your existing inference code. (Recommended LLM generation)

## Launch Server

Run `T_CONVERT_PROCESSOR=t_convert_processor:processor uvicorn pjlab_lwh_t_convert.server:app --host 0.0.0.0 --port 8000`, then point OpenAI SDK clients at this server as `base_url`.

## Compatibility

**OpenAI Python SDK Version**: "2.31.0"
