docs(26.05): extraction reconcile updates scoped to 26.5.0 behavior#2313
Merged
kheiss-uwzoo merged 6 commits intoJul 8, 2026
Merged
Conversation
Port Kurt-owned extraction workflow, API reference, support matrix, and nav/IA reconcile changes from PR 2311 onto 26.05. Includes the Greptile fixes for ASRParams and mkdocstrings module paths.
Contributor
Greptile SummaryThis PR updates the 26.05 extraction documentation. The main changes are:
|
| Filename | Overview |
|---|---|
| docs/docs/extraction/faq.md | Clarifies FAQ guidance for Nemotron Parse and chart-filtered retrieval. |
| docs/docs/extraction/multimodal-extraction.md | Adds chart modality and captioning scope details for the multimodal extraction page. |
| docs/docs/extraction/prerequisites-support-matrix.md | Updates GPU support rows and notes for audio/video extraction and Nemotron Parse. |
| docs/docs/extraction/troubleshoot.md | Updates OOM troubleshooting with batching, sink routing, and service response options. |
Reviews (6): Last reviewed commit: "docs(26.05): scope extraction docs to 26..." | Re-trigger Greptile
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Address PR 2313 review: remove the inaccurate MCP section from workflow-agentic-retrieval (no /mcp, mcp-stdio, or ingest_documents on the 26.05 retriever service) and document the supported Python API + VDB retrieval orchestration path instead. Correct support matrix OCR references to match the chart default (nemotron-ocr-v1:1.3.0), not v2.
Match main with no exceptions per review directive. Reverts the 26.05-only deltas so the PR-touched docs are identical to main: restore MCP agentic section, OCR v2 references in the support matrix, and the main module paths in audio-video and the API reference (mkdocstrings + ASRParams import).
26.05 retriever service does not expose /mcp, mcp-stdio, or ingest_documents. Document the supported Python API, VDB retrieval, and starter-kit orchestration path instead.
Align nimOperator.ocr with the 26.05 chart default (nemotron-ocr-v1:1.3.0). Keep local Hugging Face OCR v2 paragraph unchanged.
kheiss-uwzoo
changed the title
Revert main-only information-architecture and code-path churn that did not apply to the 26.05 release (restored custom-metadata, integrations, and nimclient pages; dropped main-only customize-extend and starter-kits pages; reverted nemo_retriever.common.params / graph.retriever module paths and blob/main link retargeting back to the 26.05 surface). Re-apply only genuine June-July documentation fixes valid for 26.5.0: - faq.md, multimodal-extraction.md: chart modality requires the default pdfium layout path; nemotron_parse does not emit chart/infographic rows - prerequisites-support-matrix.md: H200 NVL unsupported for self-hosted Parakeet ASR; nemotron-parse supported on RTX PRO 4500 - troubleshoot.md: replace stale save_to_disk OOM guidance with supported batching / output-sink / return_results guidance Docs-only; no runtime, test, or chart changes.
sosahi
approved these changes
Jul 8, 2026
This was referenced Jul 8, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Cherry-picks June–July documentation bug fixes from
mainonto26.05, scoped to 26.5.0 behavior only. Does not port main-only information architecture (new pages, nav renumbering, page consolidation, module-path reorg, orblob/mainlink retargeting).Prior commits that attempted to align extraction docs byte-for-byte with
mainwere reverted incb23e1d9. The PR now restores the 26.05 release doc surface (custom-metadata.md,integrations-langchain-llamaindex-haystack.md,nimclient.md, 26.05 module paths,blob/26.05chart links) and applies only vetted doc corrections.Net scope vs
upstream/26.05: 4 files,+33 / -17lines. Docs-only — no.py, test, or chart changes.File changes (vs
upstream/26.05)faq.mdmultimodal-extraction.md; Nemotron Parse FAQ notes chart modality requires pdfium layout pathextract_method=nemotron_parsedoes not emit chart/infographic modality rowsmultimodal-extraction.mdprerequisites-support-matrix.mdtroubleshoot.mdsave_to_diskguidance with supported batching, output sinks, andreturn_results=FalseIntentionally not in this PR (main-only or already on 26.05)
custom-metadata.md, addcustomize-extend.md/starter-kits.mdnemo_retriever.common.params/graph.retrievermodule pathsparamsandretriever/mcp,mcp-stdio,ingest_documents)blob/mainchart linkshelm/openshift.md)26.05branchmkdocstringspath fix (#2234)upstream/26.0526.05 release alignment
nemotron-ocr-v1:1.3.0undernimOperator.ocr(unchanged on 26.05)nemotron_parseSelf-review
docs/docs/extraction/**only — nomkdocs.yml, no.py)upstream/26.05is 4 Markdown files onlycustom-metadata.md, integrations,nimclient.md)blob/mainlink retargetingTest plan
cb23e1d9git diff upstream/26.05...HEAD --name-only— 4 doc files, no.pycustom-metadata.mdrestored; test expects this page on 26.05)llvmlite/Python 3.12), unrelated to docs