react/react14.yaml at main · skipprd/react · 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
version: 1

server:
  port: 8787

storage:
  bucket: asgsdag-datalake

scope:
  tenant: picnic
  workspace: dev
  project_id: example14
  # project_id: test

llm:
  # Keep secrets in env: OPENAI_API_KEY (or LLM_API_KEY).
  provider: OPENAI_COMPAT
  base_url: https://api.openai.com
  reason_model: gpt-5.6-luna
  task_model: gpt-5.6-luna
  embed_model: text-embedding-3-small
  context_length: 8192
  http_timeout_secs: 120
  max_tokens: 8192
  temperature: 0.2
  top_p: 1.0

providers:
  # Exactly one warehouse provider (bronze/raw + silver/gold + dbt target).
  warehouse:
    kind: athena
    workgroup: picnic
    region: eu-west-1
    # Athena catalog (Glue Data Catalog).
    catalog: AwsDataCatalog
    # Bronze/raw schema (Glue database).
    schema: test_raw
    result_s3: s3://asgsdag-datalake/
    discovery_cache_ttl_secs: 120
    max_concurrency: 15

  catalog:
    enabled: true
    refresh_secs: 10800 # 3 hours
    max_concurrency: 8

  dbt:
    enabled: true
    # Run dbt on the host (e.g. local venv), not via Docker.
    runner: host
    target: athena

    # Naming strategy (portable across warehouses):
    # dbt will materialize into: <target_schema>_<tier_suffix>
    # This avoids accidental doubled schemas like `test_warehouse_test_warehouse`.
    naming:
      # Base schema name (dbt target.schema). Example: `test`
      # target_schema: example
      # target_schema: test
      # Tier suffixes. Example schemas: `silver`, `warehouse|gold`
      silver_suffix: silver
      gold_suffix: gold

    # ---- Future warehouse examples (commented) ----
    # To switch providers, change providers.warehouse.kind
    # and ensure providers.dbt.target matches providers.warehouse.kind.
    #
    # providers:
    #   warehouse:
    #     kind: snowflake
    #     database: ANALYTICS
    #     schema: RAW
    #     warehouse: COMPUTE_WH
    #     role: ANALYST
    #   dbt:
    #     target: snowflake

  vector:
    enabled: true