{"id":47686292,"url":"https://github.com/databricks-solutions/prompt-playground","last_synced_at":"2026-04-02T14:51:33.360Z","repository":{"id":344267213,"uuid":"1171846900","full_name":"databricks-solutions/prompt-playground","owner":"databricks-solutions","description":null,"archived":false,"fork":false,"pushed_at":"2026-03-13T22:22:11.000Z","size":1047,"stargazers_count":0,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-14T09:45:18.612Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/databricks-solutions.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE.md","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-03T17:11:32.000Z","updated_at":"2026-03-13T22:21:48.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/databricks-solutions/prompt-playground","commit_stats":null,"previous_names":["databricks-solutions/prompt-playground"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/databricks-solutions/prompt-playground","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fprompt-playground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fprompt-playground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fprompt-playground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fprompt-playground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/databricks-solutions","download_url":"https://codeload.github.com/databricks-solutions/prompt-playground/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fprompt-playground/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31308446,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-02T12:59:32.332Z","status":"ssl_error","status_checked_at":"2026-04-02T12:54:48.875Z","response_time":89,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-04-02T14:51:32.519Z","updated_at":"2026-04-02T14:51:33.354Z","avatar_url":"https://github.com/databricks-solutions.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Prompt Playground\n\nPrompt Playground is an interactive, no-code Databricks App for designing, testing, and evaluating prompts stored in the [Prompt Registry](https://docs.databricks.com/aws/en/mlflow3/genai/prompt-version-mgmt/prompt-registry/). It enables product owners, prompt engineers, and both technical and non-technical users to iterate on prompt templates, run them against live model serving endpoints, and evaluate quality at scale — without writing code.\n\n- **Manage prompts** — browse, create, and version prompt templates directly from the UI\n- **Iterate interactively** — fill in `{{template_variables}}`, run against any model serving endpoint, and preview the fully rendered prompt before executing\n- **Evaluate at scale** — run a prompt version against any Unity Catalog Delta table, score with built-in LLM-as-judge presets or custom judges, and triage low-scoring results in-app\n- **Tightly integrated with Databricks** — every run and evaluation is logged as an MLflow trace with direct links to the Experiments UI; all data stays in your Unity Catalog environment\n\n## Installation\n\n### Prerequisites\n\n- [Databricks CLI](https://docs.databricks.com/dev-tools/cli/install.html) `\u003e= 0.220.0`, authenticated via `databricks auth login`\n- A **SQL Warehouse** running in your workspace\n- A **model serving endpoint** — [Foundation Model API](https://docs.databricks.com/machine-learning/foundation-models/index.html) endpoints work out of the box\n- The app's **service principal** must have `MANAGE` on the Unity Catalog schema where your prompts are stored, and `MANAGE` on the schema where eval results will be written\n\n### Setup\n\n**1. Clone the repository**\n\n```bash\ngit clone https://github.com/databricks-solutions/prompt-playground.git\ncd prompt-playground\n```\n\n**2. Deploy**\n\n```bash\ndatabricks bundle validate\ndatabricks bundle deploy\ndatabricks bundle run prompt_playground\n```\n\nThe app URL will be printed in the output. You can also find it under **Compute \u003e Apps** in your workspace.\n\n## Usage\n\n\u003e **First time? Start here:** Open the app and check out the **How to Use** tab for a full walkthrough. Click the **Settings** icon in the upper right to configure your SQL Warehouse, prompt catalog/schema, and evaluation dataset catalog/schema.\n\n**Register your first prompt from within the app:**\n\n1. Open the Prompt Playground app\n2. Click the **+** icon next to the Prompt selector\n3. Fill in a name, optional description, and template (use `{{variable}}` placeholders)\n4. Click **Create Prompt** — the new prompt is registered and immediately selected\n\n## Troubleshooting\n\n**App fails to start / \"MANAGE privilege\" error**\n→ The service principal is missing `MANAGE` on the prompts schema.\n\n**\"No prompts found\"**\n→ Open Settings (upper right) and verify your prompt catalog and schema are correct. Confirm the app's service principal has access to that schema.\n\n**Eval datasets not loading**\n→ Open Settings and verify your evaluation dataset catalog and schema. Confirm the service principal has `MANAGE` on that schema.\n\n**Model endpoint not listed**\n→ The endpoint may not be in `READY` state. Check **Serving \u003e Endpoints** in your workspace.\n\n## How to get help\n\nFor questions or bugs, please contact agents-outreach@databricks.com and the team will reach out shortly.\n\n## License\n\nThis project is licensed under the [Databricks DB License](LICENSE.md).\n\n| library | description | license | source |\n|---------|-------------|---------|--------|\n| React | Frontend framework | MIT | https://github.com/facebook/react |\n| FastAPI | Backend web framework | MIT | https://github.com/tiangolo/fastapi |\n| Tailwind CSS | Utility-first CSS | MIT | https://github.com/tailwindlabs/tailwindcss |\n| Vite | Frontend build tool | MIT | https://github.com/vitejs/vite |\n| MLflow | ML lifecycle management | Apache 2.0 | https://github.com/mlflow/mlflow |\n| Lucide React | Icon library | ISC | https://github.com/lucide-icons/lucide |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatabricks-solutions%2Fprompt-playground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatabricks-solutions%2Fprompt-playground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatabricks-solutions%2Fprompt-playground/lists"}