ReMe/plugins/beam/README_ZH.md
xyf2020 9975bb37b9
Some checks are pending
CI / Python tests / Unit Tests - py3.12 (push) Waiting to run
CI / Python tests / Unit Tests - py3.13 (push) Waiting to run
CI / Windows / CLI smoke - py3.11 (push) Waiting to run
Deploy / Documentation / Build documentation (push) Waiting to run
Deploy / Documentation / deploy (push) Blocked by required conditions
CI / Documentation / Test and build documentation (push) Waiting to run
CI / Python packages / Build and verify distributions (push) Waiting to run
CI / Python quality / Pre-commit (push) Waiting to run
CI / Python tests / Unit Tests - py3.11 (push) Waiting to run
Security / CodeQL / Analyze javascript-typescript (push) Waiting to run
Security / CodeQL / Analyze python (push) Waiting to run
Separate benchmark judge plugins (#535)
2026-09-10 20:16:46 +08:00

35 lines
2 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# BEAM 插件
[English](./README.md)
插件包含 BEAM 的记忆、回答 Step 及对应 Job 默认配置。可信评分 Step、提示词和
`answer_judge` Job 位于独立的 `plugins/beam-judge` 插件中。
ReMe 内置的 `benchmark.yaml` 负责公共评测 Job 和 Component数据集处理、runner 和结果仍留在
[`benchmark/beam`](../../benchmark/beam/README_ZH.md)。
在仓库根目录以 editable 模式安装 ReMe 和本插件,再运行评测:
```bash
python -m pip install -e ".[as]"
reme plugins install ./plugins/beam --editable
reme plugins install ./plugins/beam-judge --editable
reme plugins validate beam
reme plugins validate beam-judge
python benchmark/beam/run.py
```
editable 安装会注册 `beam` entry point并让源码修改立即生效。runner 选择内置 `benchmark`
配置,并为每个 Application 显式启用 `beam``beam-judge`。安装只让插件可被发现,不会在所有应用中全局启用。
`plugin.yaml` 注册 backend并通过 `application_defaults` 提供插件拥有的 `auto_memory`
`agentic_answer` Job。完整评测使用
`reme start config=benchmark plugins='["beam", "beam-judge"]'`。公共评测配置不继承 `default`,只运行声明的 Job
索引手动更新dream 定时任务和可选的 `auto_dream`
均保持关闭。原有 `auto_memory``agentic_answer``answer_judge``bench``judge` 名称及模型环境变量
保持不变,显式应用参数和 CLI 覆盖仍优先。安装或启用插件不会自动开始评测。
共享回答基类位于 `reme.steps.benchmark.base_agentic_answer`
`reme.steps.benchmark.beam` Python 导入路径已移除。自定义 Python 调用应从 `reme_beam`
导入记忆、搜索和回答 Step安装 `beam-judge` 后再从 `judge_beam` 导入评判 Step。
卸载插件后Application 和 CLI 服务必须移除插件选择,直到再次安装。
卸载不会删除数据集、工作区或结果。修改插件后需重启已有服务。