ai-agent/config.yaml at ddc595a99df63d583e57cdfdd1e703984d03cad7 · Imaging-Plaza/ai-agent · 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
# AI Agent Model Configuration

# Default/fallback model (used for CLI and initial startup)
agent_model:
  # name: "gpt-5.1"
  # base_url: null                        # null for default OpenAI endpoint
  # api_key_env: "OPENAI_API_KEY"
  name: "openai/gpt-oss-120b"
  base_url: "https://inference-rcp.epfl.ch/v1"
  api_key_env: "EPFL_API_KEY"

# Available models for UI dropdown
available_models:
  - display_name: "gpt-4o-mini"
    name: "gpt-4o-mini"
    base_url: null
    provider: "OpenAI"
    api_key_env: "OPENAI_API_KEY"

  - display_name: "gpt-4o"
    name: "gpt-4o"
    base_url: null
    provider: "OpenAI"
    api_key_env: "OPENAI_API_KEY"

  - display_name: "gpt-5-mini"
    name: "gpt-5-mini"
    base_url: null
    provider: "OpenAI"
    api_key_env: "OPENAI_API_KEY"

  - display_name: "gpt-5.1"
    name: "gpt-5.1"
    base_url: null
    provider: "OpenAI"
    api_key_env: "OPENAI_API_KEY"

  - display_name: "openai/gpt-oss-120b [EPFL]"
    name: "openai/gpt-oss-120b"
    base_url: "https://inference-rcp.epfl.ch/v1"
    provider: "EPFL"
    api_key_env: "EPFL_API_KEY"

# Retrieval stack (embedder + reranker)
retrieval:
  embedder:
    backend: "remote"   # "remote" or "local"
    model_name: "Qwen/Qwen3-Embedding-8B"
    base_url: "https://inference-rcp.epfl.ch/v1"
    api_key_env: "EPFL_API_KEY_EMBEDDER"
    timeout_s: 20
    # local example:
    # backend: "local"
    # model_name: "BAAI/bge-m3"

  reranker:
    backend: "remote"   # "remote" or "local"
    model_name: "BAAI/bge-reranker-v2-m3"
    base_url: "https://inference-rcp.epfl.ch/v1"
    api_key_env: "EPFL_API_KEY_EMBEDDER"
    timeout_s: 20
    # local example:
    # backend: "local"
    # model_name: "BAAI/bge-reranker-v2-m3"