MASEval/mkdocs.yml at main · parameterlab/MASEval · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
site_name: Multi-Agent System Evaluation
site_description: "System-level multi-agent benchmarks"
docs_dir: docs
site_dir: site
site_author: ParameterLab
site_url: https://maseval.readthedocs.io/en/stable/
repo_name: parameterlab/maseval
repo_url: https://github.com/parameterlab/maseval
edit_uri: edit/main/docs/

theme:
  name: material
  logo: assets/logo-short.svg
  favicon: assets/favicon.svg
  palette:
    # Light mode
    - media: "(prefers-color-scheme: light)"
      scheme: default
      primary: teal
      accent: teal
      toggle:
        icon: material/brightness-7
        name: Switch to dark mode

    # Dark mode
    - media: "(prefers-color-scheme: dark)"
      scheme: slate
      primary: teal
      accent: teal
      toggle:
        icon: material/brightness-4
        name: Switch to light mode

  features:
    - navigation.sections
    - content.code.copy
    - navigation.indexes

extra_css:
  - css/mkdocstrings.css

markdown_extensions:
  - admonition
  - pymdownx.details
  - pymdownx.superfences:
      custom_fences:
        - name: mermaid
          class: mermaid
          format: !!python/name:pymdownx.superfences.fence_code_format
  - attr_list
  - pymdownx.emoji:
      emoji_index: !!python/name:material.extensions.emoji.twemoji
      emoji_generator: !!python/name:material.extensions.emoji.to_svg

plugins:
  - search
  - git-revision-date-localized:
      enable_creation_date: true
      type: date
  - mkdocs-jupyter:
      include_source: True
      execute: False
  - mkdocstrings:
      handlers:
        python:
          options:
            # Render Google-style docstrings and show sections as lists instead of tables
            # docstring_style: google
            docstring_section_style: spacy
            # Show type annotations in signatures inline with the heading
            show_signature: true
            show_signature_annotations: true
            signature_crossrefs: true
            separate_signature: true
            # Keep type paths brief in signatures
            annotations_path: brief
            show_root_full_path: false
            show_root_heading: true
            type_parameter_headings: true
            show_source: false
            inherited_members: true # Include inherited members in the documentation

            # Hide private members (methods/attributes starting with _)
            extra:
              show_private: false

nav:
  - Home: index.md
  - Getting Started:
      - Quickstart: getting-started/quickstart.md
      - FAQ: getting-started/faq.md
  - Guides:
      - guides/index.md
      - Message Tracing: guides/message-tracing.md
      - Configuration Gathering: guides/config-gathering.md
      - Exception Handling: guides/exception-handling.md
      - Seeding: guides/seeding.md
      - Usage & Cost Tracking: guides/usage-tracking.md
  - Examples:
      - examples/index.md
      - Tiny Tutorial: examples/tutorial.ipynb
      - 5-A-Day Benchmark: examples/five_a_day_benchmark.ipynb
  - Reference:
      - reference/index.md
      - Core:
          - Agent: reference/agent.md
          - Benchmark: reference/benchmark.md
          - Callback: reference/callback.md
          - Environment: reference/environment.md
          - Evaluator: reference/evaluator.md
          - Exceptions: reference/exceptions.md
          - History: reference/history.md
          - Model: reference/model.md
          - Scorer: reference/scorer.md
          - Seeding: reference/seeding.md
          - Simulator: reference/simulator.md
          - Tasks: reference/task.md
          - Usage & Cost: reference/usage.md
          - User: reference/user.md
          - Utilities: reference/utilities.md
      - Interface:
          - Agents:
              - CAMEL-AI: interface/agents/camel.md
              - LangGraph: interface/agents/langgraph.md
              - LlamaIndex: interface/agents/llamaindex.md
              - SmolAgents: interface/agents/smolagents.md
          - Models:
              - Anthropic: interface/inference/anthropic.md
              - Google GenAI: interface/inference/google_genai.md
              - HuggingFace: interface/inference/huggingface.md
              - LiteLLM: interface/inference/litellm.md
              - OpenAI: interface/inference/openai.md
          - Environments:
              - ARE: interface/environments/are.md
      - Benchmarks:
          - ConVerse: benchmark/converse.md
          - GAIA2: benchmark/gaia2.md
          - MACS: benchmark/macs.md
          - MMLU: benchmark/mmlu.md
          - MultiAgentBench: benchmark/multiagentbench.md
          - Tau2: benchmark/tau2.md