Skip to content

README.md

Latest commit

 

History

History
47 lines (34 loc) · 2.1 KB

README.md

File metadata and controls

47 lines (34 loc) · 2.1 KB
Raw

Inspire AI — Workspace Installer

This repository is structured for customer deployment: only the installer notebook lives at the root; the full Databricks App lives in app/.

Agent v1.1.3 (current)
Ship Agent notebook + App aligned to v1.1.3
Path /Shared/inspire-ai/dbx_inspire_ai_agent
Artifacts 09_generation_options → PDF Catalog / Presentation only
Genie Scope via 13_generate_genie_code_for (not generation options)
Quality Canonical: Coverage Mode (All) / Balanced / Strict Quality
Jobs Always pass non-empty 14_session_id (skips nested launcher gate)
Runtime Auto-detects LLM serving endpoints; adaptive timeouts
Validate cd app && npm test

Customer deployment (no npm)

  1. Import into your Databricks workspace:
    • installer_workspace.py (this file — Python notebook)
    • The app/ folder next to it (same parent folder), or upload app/dist/InspireAI-workspace.zip to
      /Workspace/Users/<your-email>/InspireAI-workspace.zip
  2. Open installer_workspace.py, attach Serverless (or a cluster with UC + Apps access).
  3. Pick SQL warehouse and Unity Catalog in the notebook parameters.
  4. Run All (last cell runs main()).

The installer will:

  • Deploy the inspire-ai Databricks App from the app/ bundle
  • Publish agent notebooks under /Shared/inspire-ai/
  • Grant the App service principal UC and warehouse permissions

Then open Compute → Apps → inspire-ai.

Layout

Path Purpose
installer_workspace.py One-time workspace installer (customer entry point)
app/ Full-stack app — backend, frontend, notebooks, internal deploy scripts

Developers: see app/README.md and app/deployment.md.

Legal Information

This software is provided as-is and is not officially supported by Databricks through customer technical support channels. Support, questions, and feature requests can be communicated through the Issues page of this repo.