Skip to main content

Agent Eval 评估器

PyPI Python License: MIT

Agent 能力评估框架(agent-eval CLI)——基于 Agent-Driven 架构,支持课件生成、 代码生成、RAG、对话等多类 Agent 评估。

安装(发布后)

pip install ai-eval-scope                 # 基础:规则评估(无 LLM 依赖)
pip install "ai-eval-scope[llm]"          # + LLM Judge(OpenAI/Anthropic 兼容)
pip install "ai-eval-scope[agent]"        # + ExecutionAgent 执行引擎(DeepAgents 底座)
pip install "ai-eval-scope[vision]"       # + 视觉评估(playwright 截图渲染)
pip install "ai-eval-scope[datasets]"     # + 数据集下载(HuggingFace/ModelScope)

uv tool install "ai-eval-scope[agent]"    # uv:全局 CLI 工具安装
uvx --from "ai-eval-scope[agent]" agent-eval --help   # 一次性运行,不落盘

包名 ai-eval-scope,import 名 agent_eval,CLI 命令 agent-eval(命令名≠包名)。 Python ≥ 3.11。LLM 与凭证配置见 CLI 使用教程

开发

cd evaluator
uv sync --group dev                # 开发依赖组(PEP 735,含 llm/vision 测试依赖)
uv run playwright install chromium  # 下载 Chromium 浏览器二进制(~150MB,装到用户缓存)
uv run agent-eval --help

配置

交互式向导(推荐)

uv run agent-eval models login

向导流程:

  1. 选择提供商anthropic / openai / deepseek / custom(自定义 OpenAI 兼容端点)
  2. API Base URL:按提供商给默认值(anthropic 缺省 https://api.moonshot.cn/anthropic,即 Kimi 的 Anthropic 协议端点;openai 缺省 https://api.openai.com/v1;deepseek 缺省 https://api.deepseek.com/v1
  3. API Key:隐藏输入
  4. 逐角色确认模型
    • text — 文本 LLM Judge(默认必配)
    • vision — 视觉评估模型(用视觉规则集时需要)
    • agent — 执行侧模型(run/pipeline 驱动被测 Agent 用;未配置时自动回退 text

查看与验证

uv run agent-eval models list    # 查看(API Key 脱敏显示 前4…后4)
uv run agent-eval models test    # 对每个已配角色真实调用一次,打印时延
uv run agent-eval models logout  # 删除配置(含 key)

详见 CLI 使用教程CLAUDE.md

运行

uv run agent-eval eval \
  --package-dir workspace/packages/<包目录>/ \
  --package courseware

验证是否真正执行:产物中出现 *.png 截图、评估耗时显著增加(视觉渲染 + 视觉 LLM 调用), 且日志无「视觉跳过」「Chromium 启动失败」字样。缓存命中时会跳过视觉重算,调试时加 --no-cache 强制重评。

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_eval_scope-0.1.5.tar.gz (1.0 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ai_eval_scope-0.1.5-py3-none-any.whl (804.6 kB view details)

Uploaded Python 3

File details

Details for the file ai_eval_scope-0.1.5.tar.gz.

File metadata

  • Download URL: ai_eval_scope-0.1.5.tar.gz
  • Upload date:
  • Size: 1.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"12","id":"bookworm","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for ai_eval_scope-0.1.5.tar.gz
Algorithm Hash digest
SHA256 3439a067cbb5c5c27fc70c44410366cdee145367878340ae4d25cfdfe3db99f4
MD5 087c6d8a7dabcd91f6101e1c0867b5bd
BLAKE2b-256 4cb40a8224723cc990f4092901328ca7e248589cea33f41d057ce4228be6cde5

See more details on using hashes here.

File details

Details for the file ai_eval_scope-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: ai_eval_scope-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 804.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"12","id":"bookworm","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for ai_eval_scope-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 aeae039eecf8ace8e7ac1c3a118b067132da07ecab2575276c66a17fcce60139
MD5 cf28c7b37d149e2843a950e42944bb66
BLAKE2b-256 533d0d97d143adde272d077e1a2002ea59cefda0cd9ee0f0bf6c1ad358e8dc4e

See more details on using hashes here.

Release history Release notifications | RSS feed

0.2.1

2 files

0.2.0

2 files

This release

0.1.5 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page