ontobricks/.env.example at master · databrickslabs/ontobricks · 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
# OntoBricks Environment Configuration
# Copy this file to .env and fill in your values
#
# NOTE: For Databricks Apps deployment, most of these are set automatically
# by the platform. This file is primarily for LOCAL development.
#
# ── Quick start ──────────────────────────────────────────────────────────────
# 1. Copy:  cp .env.example .env
# 2. Fill in DATABRICKS_HOST, one auth method (PAT recommended), and the
#    Lakebase / UC Volume coordinates below.
# 3. Run:   ./scripts/start.sh
# -----------------------------------------------------------------------------

# ============================================================================
# Databricks Connection (Required)
# ============================================================================
# Your Databricks workspace URL
DATABRICKS_HOST=https://your-workspace.cloud.databricks.com

# ── Authentication — choose ONE ──────────────────────────────────────────────
#
# Option A (recommended for local dev): Personal Access Token
#   Generate at: Workspace → User Settings → Developer → Access Tokens
#   Leave blank if using Option B.
DATABRICKS_TOKEN=

# Option B: Databricks CLI OAuth profile
#   If DATABRICKS_TOKEN is blank, OntoBricks resolves credentials from
#   ~/.databrickscfg at runtime (via the Databricks SDK). scripts/start.sh
#   can also call `databricks auth token --profile <DATABRICKS_CONFIG_PROFILE>`
#   to inject a short-lived token into the process environment.
#
#   Prerequisites:
#     1. Install the Databricks CLI  (brew install databricks)
#     2. Authenticate once:  databricks auth login --profile <profile-name>
#     3. Set the profile name below (must match ~/.databrickscfg exactly).
#
#   If your ~/.databrickscfg has two profiles pointing at the same host
#   you MUST set this to pick one — otherwise the SDK raises an ambiguity error.
#
DATABRICKS_CONFIG_PROFILE=DEFAULT

# SQL Warehouse ID for query execution
# Find at: Workspace → SQL → SQL Warehouses → (select) → Connection details
DATABRICKS_SQL_WAREHOUSE_ID=

# ============================================================================
# Registry Backend — Lakebase (Postgres)
# ============================================================================
REGISTRY_BACKEND=lakebase

# Four coordinates that identify the target Lakebase resource:
#
#   LAKEBASE_PROJECT   — Lakebase Autoscaling project name (e.g. ontobricks-app)
#   LAKEBASE_BRANCH    — branch within that project (default: main)
#   LAKEBASE_DATABASE  — Postgres database name    (e.g. ontobricks_registry)
#   LAKEBASE_SCHEMA    — Postgres schema           (e.g. ontobricks_registry)
#   PGUSER             — your Databricks account email (local dev only;
#                        injected automatically by the Apps runtime)
#
# LakebaseAuth resolves the Postgres host automatically via the Databricks
# API — you do NOT need to set PGHOST for local dev.
#
# In Databricks Apps the platform auto-injects PGHOST/PGPORT/PGDATABASE/PGUSER
# from the bound ``database`` resource; those override the vars below.
#
LAKEBASE_PROJECT=ontobricks-app
LAKEBASE_BRANCH=main
LAKEBASE_DATABASE=ontobricks_registry
LAKEBASE_SCHEMA=ontobricks_registry
PGUSER=you@databricks.com

# Advanced: set PGHOST directly to bypass the project/branch API lookup
# (useful if OAuth is unavailable or if you know the raw Lakebase endpoint).
# Find it at: Compute → Lakebase → <project> → <branch> → Connection details
# PGHOST=

# ============================================================================
# Unity Catalog Volume — binary artefacts (domain document uploads)
# ============================================================================
# The domain registry lives in Lakebase (above). The Volume is only used for
# binary attachments (documents imported by the ontology designer).
# Full path: /Volumes/<REGISTRY_CATALOG>/<REGISTRY_SCHEMA>/<REGISTRY_VOLUME>
# In Databricks Apps the volume resource is auto-bound.
REGISTRY_CATALOG=
REGISTRY_SCHEMA=
REGISTRY_VOLUME=

# ============================================================================
# MLflow Tracing (Optional — for AI agent features)
# ============================================================================
# Send agent traces to your Databricks workspace instead of local mlflow.db.
# Requires DATABRICKS_HOST and a valid auth method above.
# MLFLOW_TRACKING_URI=databricks
# ONTOBRICKS_MLFLOW_EXPERIMENT=ontobricks-agents

# ============================================================================
# Application Settings (Optional)
# ============================================================================
# Secret key for session encryption (use a strong random string in production)
SECRET_KEY=your-secret-key-change-in-production

# Application port — set automatically in Databricks Apps via DATABRICKS_APP_PORT
# DATABRICKS_APP_PORT=8000