docs: update nv-ingest component#8950
Conversation
|
Important Review skippedAuto incremental reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the WalkthroughThe documentation for the NVIDIA Retriever Extraction component was updated to describe new features, including image and infographic extraction, a high-resolution mode for PDFs, expanded parameter options, and revised output formats. Several input parameters were added, some defaults changed, and output descriptions were updated to reflect support for images and infographics. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant NVIDIA_Retriever_Extraction
User->>NVIDIA_Retriever_Extraction: Submit document with parameters (extract_images, extract_infographics, high_resolution, etc.)
NVIDIA_Retriever_Extraction->>NVIDIA_Retriever_Extraction: Process document
alt High Resolution PDF
NVIDIA_Retriever_Extraction->>NVIDIA_Retriever_Extraction: Use nemoretriever-parse for extraction
end
alt Extract Images/Infographics
NVIDIA_Retriever_Extraction->>NVIDIA_Retriever_Extraction: Extract images and infographics with filtering and captioning
end
NVIDIA_Retriever_Extraction-->>User: Return output (text, structured, image types with captions/infographics)
Possibly related PRs
Suggested labels
✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
Documentation and Community
|
dosubot
Bot
added
size:M
github-actions
Bot
added
documentation
|
Build successful! ✅ |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🔭 Outside diff range comments (1)
docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md (1)
1-4: Adddescriptionto the front-matter blockAll docs pages must include both
titleanddescriptionkeys in the front-matter per the docs guidelines. Missing the description breaks the docs site’s meta-data and search.--- title: Integrate NVIDIA Retriever Extraction with Langflow +description: Learn how to integrate the NVIDIA Retriever Extraction (NV-Ingest) component into your Langflow Flows. slug: /integrations-nvidia-ingest ---
🧹 Nitpick comments (4)
docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md (4)
12-12: Tighten grammar and hyphenate compound adjectivesDouble-spacing after pre- and the un-hyphenated “High Resolution” violate the style guide.
-The `nv-ingest` service supports multiple extraction methods for PDF, DOCX, and PPTX file types, and includes pre- and post-processing services like splitting, chunking, and embedding generation. The extractor service's High Resolution mode uses the `nemoretriever-parse` extraction method for better quality extraction from scanned PDF documents. This feature is only available for PDF files. +The `nv-ingest` service supports multiple extraction methods for PDF, DOCX, and PPTX files, and includes *pre-* and *post-processing* services such as splitting, chunking, and embedding generation. The extractor service’s *high-resolution* mode uses the `nemoretriever-parse` extraction method for improved extraction quality from scanned PDFs. This feature is available only for PDFs.
51-53: Hyphenate “high-resolution” and keep wording concise-The component supports text, charts, tables, images, and infographics. -Optionally, for PDF files, enable High Resolution mode for better quality extraction from scanned documents. +The component supports text, charts, tables, images, and infographics. +For PDFs, optionally enable *high-resolution* mode for higher-quality extraction from scanned documents.
79-92: Polish parameter descriptions for clarity & consistencyMinor wording/consistency issues:
-| extract_images | Extract Images | Extract images from document. Default: `True`. | -| extract_infographics | Extract Infographics | Extract infographics from document. Default: `False`. | +| extract_images | Extract Images | Extract images from documents. Default: `True`. | +| extract_infographics | Extract Infographics | Extract infographics from documents. Default: `False`. | ... -| min_image_size | Minimum Image Size Filter | Minimum image width/length in pixels. Default: `128`. | +| min_image_size | Minimum Image Size Filter | Minimum image **width or height** (in pixels). Default: `128`. | ... -| high_resolution | High Resolution (PDF only) | Process PDF in high-resolution mode for better quality extraction from scanned PDF. Default: `False`. | +| high_resolution | High-resolution (PDF only) | Process PDFs in high-resolution mode for improved extraction from scanned PDFs. Default: `False`. |
99-103: Resolve list-style lint errors & grammar in output descriptionmarkdownlint expects
*list markers, and the sentence reads awkwardly.-* `document_type`: The type of the document, which can be "text", "structured", or "image". +* `document_type`: The document type—`"text"`, `"structured"`, or `"image"`.(Consider converting the surrounding
-lists to*for consistency, or configure.markdownlintto accept-.)
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md(4 hunks)
🧰 Additional context used
📓 Path-based instructions (1)
`docs/docs/**/*.{md,mdx}`: All documentation content must be placed within the '...
docs/docs/**/*.{md,mdx}: All documentation content must be placed within the 'docs/' directory, organized into subdirectories such as 'getting-started', 'components', 'integrations', 'administration', 'contributing', and 'api-reference'.
All documentation markdown files must start with a frontmatter block containing at least 'title' and 'description' fields.
Use admonitions (:::tip, :::warning, :::danger) in markdown files to highlight important information, warnings, or critical issues.
Reference images in documentation using the '/img/' path and provide descriptive alt text in markdown.
Use code blocks with language identifiers and optional titles for code examples in markdown documentation.
Documentation content must follow the style guide: professional but approachable tone, second person voice, present tense, short paragraphs, sentence case headers, inline code with backticks, bold for UI elements, italic for emphasis, and parallel structure in lists.
Use consistent terminology: always capitalize 'Langflow', 'Component', and 'Flow' when referring to Langflow concepts; always uppercase 'API' and 'JSON'.
📄 Source: CodeRabbit Inference Engine (.cursor/rules/docs_development.mdc)
List of files the instruction was applied to:
docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md
🧠 Learnings (1)
📓 Common learnings
Learnt from: CR
PR: langflow-ai/langflow#0
File: .cursor/rules/docs_development.mdc:0-0
Timestamp: 2025-06-30T14:40:02.682Z
Learning: Applies to docs/docs/**/*.{md,mdx} : Use consistent terminology: always capitalize 'Langflow', 'Component', and 'Flow' when referring to Langflow concepts; always uppercase 'API' and 'JSON'.
🪛 LanguageTool
docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md
[grammar] ~12-~12: Use commas correctly
Context: ...on methods for PDF, DOCX, and PPTX file types, and includes pre- and post-processing s...
(QB_NEW_EN_OTHER_ERROR_IDS_33)
[grammar] ~12-~12: Use correct spacing
Context: ...DOCX, and PPTX file types, and includes pre- and post-processing services like splitting...
(QB_NEW_EN_OTHER_ERROR_IDS_5)
[uncategorized] ~12-~12: If this is a compound adjective that modifies the following noun, use a hyphen.
Context: ...ing generation. The extractor service's High Resolution mode uses the nemoretriever-parse ext...
(EN_COMPOUND_ADJECTIVE_INTERNAL)
[grammar] ~12-~12: Use correct spacing
Context: ... This feature is only available for PDF files. The NVIDIA Retriever Extraction com...
(QB_NEW_EN_OTHER_ERROR_IDS_5)
[uncategorized] ~52-~52: If this is a compound adjective that modifies the following noun, use a hyphen.
Context: ...hics. Optionally, for PDF files, enable High Resolution mode for better quality extraction from...
(EN_COMPOUND_ADJECTIVE_INTERNAL)
[grammar] ~57-~57: Use correct spacing
Context: ...raDB Vector** component with a Data output. 
9. Run the flow. Inspect your Astra DB vec...
(QB_NEW_EN_OTHER_ERROR_IDS_5)
[grammar] ~91-~91: There might be a problem here.
Context: ...ion from scanned PDF. Default: False. | ### Outputs The NVIDIA Retriever Extraction com...
(QB_NEW_EN_MERGED_MATCH)
[grammar] ~102-~102: There might be a mistake here.
Context: ...type of the document, which can be "text", "structured", or "image". - `descriptio...
(QB_NEW_EN_OTHER)
[grammar] ~102-~102: There might be a mistake here.
Context: ...cument, which can be "text", "structured", or "image". - description: Additional...
(QB_NEW_EN_OTHER)
[grammar] ~102-~102: There might be a mistake here.
Context: ...h can be "text", "structured", or "image". - description: Additional description...
(QB_NEW_EN_OTHER)
[grammar] ~115-~115: Use correct spacing
Context: ...eing processed from the table_content metadata. - Documents with document_type: "image"...
(QB_NEW_EN_OTHER_ERROR_IDS_5)
[grammar] ~119-~119: Use modal and auxiliary verbs correctly
Context: ...t extracted from documents. - Caption text stored in the text field when `captio...
(QB_NEW_EN_OTHER_ERROR_IDS_24)
🪛 markdownlint-cli2 (0.17.2)
docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md
96-96: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
97-97: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
98-98: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
99-99: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
100-100: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
101-101: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
102-102: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
113-113: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
114-114: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
115-115: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
117-117: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
118-118: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
119-119: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
120-120: Unordered list style
Expected: asterisk; Actual: dash
(MD004, ul-style)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: build-and-deploy
aimurphy
left a comment
aimurphy
left a comment
There was a problem hiding this comment.
just one question, otherwise lgtm
github-actions
Bot
added
documentation
|
Build successful! ✅ |
* add-high-res-and-defaults * Update docs/docs/Integrations/Nvidia/integrations-nvidia-ingest.md
4 participants
Update docs to reflect some changes made to the component here.
Summary by CodeRabbit