genie-api-cache-queue/app.yaml at main · databricks-solutions/genie-api-cache-queue · 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
# Databricks Apps Configuration
# Reference: https://docs.databricks.com/aws/en/dev-tools/databricks-apps/

name: genie-cache-queue
display_name: "Genie API with Cache & Queue"
description: "Intelligent query caching and rate limiting for Databricks Genie API"

# Run command (requirements.txt auto-installed by runtime, frontend pre-built in frontend/dist/)
command:
  - "python"
  - "-m"
  - "uvicorn"
  - "entrypoint:app"
  - "--host"
  - "0.0.0.0"
  - "--port"
  - "8000"

# Compute configuration
compute:
  size: small  # small (2 cores, 8GB), medium (4 cores, 16GB), large (8 cores, 32GB)

# Environment variables
# DATABRICKS_HOST and DATABRICKS_TOKEN are automatically provided by Databricks Apps
env:
  - name: STORAGE_BACKEND
    value: pgvector
  - name: LAKEBASE_INSTANCE
    value: <your-lakebase-instance>
  - name: LAKEBASE_CATALOG
    value: default
  - name: LAKEBASE_SCHEMA
    value: public

# Static files served by FastAPI (not needed here)

# Resource limits
resources:
  cpu: 2
  memory: 8Gi