Skip to content

Sync docs for schema and metadata fields#2435

Open
natoverse wants to merge 13 commits into
mainfrom
docs/schema-metadata-sync
Open

Sync docs for schema and metadata fields#2435
natoverse wants to merge 13 commits into
mainfrom
docs/schema-metadata-sync

Conversation

@natoverse

Copy link
Copy Markdown
Collaborator

Summary

  • Align input docs with current supported formats (JSONL, Parquet, MarkItDown)
  • Update schema documentation for documents and text_units fields
  • Clarify chunking field prepending behavior via raw_data
  • Fix stale architecture/dataflow references to current data model paths
  • Correct output storage field descriptions in config docs

Validation

  • uv run mkdocs build -q

@natoverse natoverse requested a review from a team as a code owner July 10, 2026 22:59
@natoverse

Copy link
Copy Markdown
Collaborator Author

Resolves #2416 and #2301

Comment thread docs/examples_notebooks/drift_search.ipynb Outdated
Comment thread docs/examples_notebooks/drift_search.ipynb Outdated
Comment thread docs/examples_notebooks/drift_search.ipynb Outdated

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates GraphRAG documentation and example notebooks to match the current schema, config surface area, and supported input formats (including raw_data metadata prepending and additional readers), and refreshes notebook examples to the newer graphrag_llm APIs.

Changes:

  • Align input/output schema docs with raw_data, creation_date, relationship_ids, and findings list typing.
  • Expand docs to reflect additional input formats (JSONL, Parquet, MarkItDown) and update stale architecture/dataflow paths.
  • Update example notebooks to use graphrag_llm model factory APIs.

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated 10 comments.

Show a summary per file
File Description
docs/index/outputs.md Updates documented output table schemas (e.g., findings, raw_data, relationship_ids).
docs/index/inputs.md Updates supported input format docs and explains raw_data + chunking.prepend_metadata behavior.
docs/index/default_dataflow.md Fixes stale references to the data model folder path.
docs/index/architecture.md Updates the “input reader” section to list current built-in readers.
docs/examples_notebooks/local_search.ipynb Migrates LLM setup to graphrag_llm factories.
docs/examples_notebooks/global_search.ipynb Migrates LLM setup to graphrag_llm factories; currently includes executed outputs/cell counts.
docs/examples_notebooks/global_search_with_dynamic_community_selection.ipynb Migrates LLM setup to graphrag_llm factories.
docs/examples_notebooks/drift_search.ipynb Migrates LLM/vector setup; currently includes warnings + saved error tracebacks.
docs/config/yaml.md Updates YAML config docs for new input types and chunk-prepending behavior.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread docs/examples_notebooks/drift_search.ipynb Outdated
Comment thread docs/examples_notebooks/drift_search.ipynb Outdated
Comment thread docs/examples_notebooks/drift_search.ipynb Outdated
Comment thread docs/examples_notebooks/drift_search.ipynb Outdated
Comment thread docs/examples_notebooks/global_search.ipynb Outdated
Comment thread docs/examples_notebooks/global_search.ipynb Outdated
Comment thread docs/examples_notebooks/global_search.ipynb
Comment thread docs/examples_notebooks/global_search.ipynb
Comment thread docs/examples_notebooks/global_search.ipynb
Comment thread docs/examples_notebooks/global_search.ipynb
natoverse and others added 4 commits July 13, 2026 16:01
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
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.

4 participants