Skip to content

Add 2026-06-llmops-quickstart blog code#91

Open
CEDipEngineering wants to merge 2 commits into
databricks-solutions:mainfrom
CEDipEngineering:add-2026-06-llmops-quickstart
Open

Add 2026-06-llmops-quickstart blog code#91
CEDipEngineering wants to merge 2 commits into
databricks-solutions:mainfrom
CEDipEngineering:add-2026-06-llmops-quickstart

Conversation

@CEDipEngineering

Copy link
Copy Markdown

What this is

End-to-end LLMOps quickstart on Databricks — a customer support ticket classifier
that carries an LLM agent through the full lifecycle: data ingestion → agent build →
evaluation (Champion gate) → deployment → batch + real-time inference.

Accompanies an upcoming Databricks Community blog post (JIRA TLC-1077).

Contents

  • New folder 2026-06-llmops-quickstart/ (follows the YYYY-MM-[name] convention)
  • MLflow ChatAgent on a Foundation Model API endpoint, evaluation gate promoting a
    Champion alias in Unity Catalog, and a Databricks Asset Bundle deploying schema,
    experiment, and jobs (dev/prod targets)
  • Extensive README.md (setup, structure, data note, licenses, blog-link placeholder)
  • LICENSE.md — unmodified copy of the repo's Databricks license
  • CODEOWNERS entry added for the new folder

Guidelines checklist

  • I have read the contribution guidelines
  • No sensitive information / no secrets (CI pipelines referencing SP secrets were excluded)
  • No PII; no external dataset (only 30 small, hand-written synthetic tickets)
  • Licenses listed in the README; Databricks license unchanged
  • Folder renamed to YYYY-MM-[folder_name]
  • Added myself to CODEOWNERS
  • Domain SME has reviewed the code and approved in a PR comment (pending)

Blog post link will be added to the README once published.

End-to-end LLMOps quickstart on Databricks (customer support ticket
classifier): MLflow ChatAgent on a Foundation Model API endpoint, an
evaluation gate that promotes a Champion in Unity Catalog, and a
Databricks Asset Bundle that deploys schema, experiment, and jobs with
batch + real-time inference.

- Folder follows the YYYY-MM-[name] convention
- README documents setup, structure, data (30 synthetic tickets, no PII), and licenses
- LICENSE.md is an unmodified copy of the repo Databricks license
- CODEOWNERS entry added for the new folder

I have read the contribution guidelines. No sensitive info, no PII, no
external dataset. Pending: SME code review approval and internal approval.

Co-authored-by: Isaac
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant