docs: add 'Use It From Code' section to README - #31067
Conversation
The README described the SDKs but contained no installable package names or runnable code. Adds a section with install commands for the metadata and AI SDKs, a connect-and-read Python example, and an MCP / LangChain example, placed alongside the existing APIs and SDKs content. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
❌ PR checklist incompleteThis PR cannot be merged until the following are addressed on its linked issue:
The fields live on the linked issue in the Shipping project (open the issue → right sidebar → Projects). After you set them, re-run this check (or push a commit) — issue/project changes do not re-trigger it automatically. Maintainers can bypass this check by adding the |
|
Hi there 👋 Thanks for your contribution! The OpenMetadata team will review the PR shortly! Once it has been labeled as Let us know if you need any help! |
🔴 Playwright Results — workflow failedValidated commit ✅ 0 passed · ❌ 0 failed · 🟡 0 flaky · ⏭️ 0 skipped · 🧰 0 lifecycle flaky Pipeline and setup failures (6)
Performance⚪ Performance metrics unavailable; see the CI and reporting failures above.
How to debug locally# Download playwright-test-results-<shard> artifact and unzip
npx playwright show-trace path/to/trace.zip # view trace |
Updated installation command for openmetadata-ingestion package to remove specific version.
|
Hi there 👋 Thanks for your contribution! The OpenMetadata team will review the PR shortly! Once it has been labeled as Let us know if you need any help! |
Code Review ✅ ApprovedAdds a 'Use It From Code' section to the README featuring installation instructions, package mapping, and executable Python and MCP examples. No issues found. OptionsDisplay: compact → Showing less information. Comment with these commands to change the behavior for this request:
Was this helpful? React with 👍 / 👎 | Gitar | Powered by Gitar — free for open source |
What this changes
Adds a Use It From Code section to the README, placed immediately after the "MCP, Semantic Search, APIs, AI SDK, and Memory" section and before "What You Can Build".
Additive only — no existing content was modified or removed.
Why
The README describes the SDKs well but contains no code and no installable package names. Across all 310 lines:
MCPSDKpip installpythonlangchainopenmetadata-ingestionThe existing
### APIs, SDKs, Events, and Webhookssubsection is two sentences with no example, and the Quickstart is a conceptual nine-step list rather than executable steps.This matters beyond human readers. AI coding assistants answer "how do I use X from Python?" by lifting complete, runnable snippets — retrieval is extractive. This README is the single highest-authority OpenMetadata artifact on the web, and it currently offers nothing quotable for a coding question, so assistants fall back to third-party sources or outdated examples.
The package name is also genuinely non-obvious: the Python SDK ships in
openmetadata-ingestion, so a reasonable guess ofpip install openmetadatafails.What the section contains
openmetadata-ingestion(metadata operations) anddata-ai-sdk(AI / MCP / agents) — plus the TypeScript and Java packageshealth_check()fullyQualifiedName)as_langchain_tools()and a directcall_toolinvocationai-sdkrepo, and REST API docsPlacement
Positioned at roughly 60% of the document rather than near the end. Retrieval systems weight content by position, and material in the last third of a long README is substantially less likely to be extracted. It also sits directly adjacent to the existing SDK prose, which is where a reader looking for code would already be.
Notes for reviewers
~=1.13.1.0should be bumped as releases move — worth deciding whether to pin at all here, or point to the docs for current versions.### APIs, SDKs, Events, and Webhookssubsection instead if you prefer a smaller footprint.🤖 Generated with Claude Code