Add content related to summary index #665

RiskeyL · 2026-01-22T03:38:56Z

No description provided.

Copilot

Pull request overview

This pull request adds comprehensive documentation for the new Summary Auto-Gen feature, which automatically generates summaries for document chunks to enhance retrievability in knowledge bases.

Changes:

Added documentation for the Summary Auto-Gen feature across multiple knowledge management pages
Introduced new document and chunk management actions for generating and managing summaries
Added best practices section explaining when and how to use summaries effectively
Restructured and improved the chunking documentation for better clarity

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 9 comments.

File	Description
maintain-knowledge-documents.mdx	Added "Generate Summary" document action and "Add/Edit/Delete Summary" chunk operation; added new best practices section on using summaries to bridge query-content gaps
introduction.mdx	Added "Summary Auto-Gen" setting to knowledge base configuration table with usage instructions
knowledge-pipeline-orchestration.mdx	Added new "Summary Auto-Gen" section explaining the feature in the pipeline orchestration context
chunking-and-cleaning-text.mdx	Restructured chunking documentation with improved explanations and added "Enable Summary Auto-Gen" section; includes better explanation of delimiters and chunk modes

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

en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents.mdx

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx

en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents.mdx

en/use-dify/knowledge/manage-knowledge/introduction.mdx

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx

Auto-generated translations for documentation changes in PR #665. Last-Processed-Commit: fe61cff Original-PR: #665 Languages: Chinese (zh), Japanese (ja) 🤖 Generated with GitHub Actions

github-actions · 2026-01-22T03:53:50Z

🌐 Multi-language Sync

✅ Created sync PR #666

Synced 8 files to cn + jp

Both PRs can merge independently. Future commits here will auto-update the sync PR.

Auto-generated translations for changes in commit fe61cff. Last-Processed-Commit: fe61cff Original-PR: #665 Languages: Chinese (zh), Japanese (ja) 🤖 Generated with GitHub Actions

github-actions · 2026-01-22T03:54:22Z

🌐 Multi-language Sync

✅ Updated sync PR #666

Future commits will auto-update the sync PR.

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated no new comments.

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

Auto-generated translations for changes in commit d37bc6b. Last-Processed-Commit: d37bc6b Original-PR: #665 Languages: Chinese (zh), Japanese (ja) 🤖 Generated with GitHub Actions

github-actions · 2026-01-22T04:11:57Z

🌐 Multi-language Sync

✅ Updated sync PR #666

Synced 6 files to cn + jp

Future commits will auto-update the sync PR.

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 5 comments.

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

Copilot · 2026-01-22T05:58:39Z

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx

+Click **Preview** to see how your content will be chunked. A limited number of chunks will be displayed for a quick review.

-Once configured, click **“Preview Chunk”** to see the chunking results. You can see the total character count of the parent chunk. Characters highlighted in blue represent child chunks, and the character count for the current child chunk is also displayed for reference.
+If the results don't perfectly match your expectations, choose the closest configuration—you can manually fine-tune chunks later. See [Manage Documents and Chunks](/en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents) for details.


The link text "Manage Documents and Chunks" doesn't match the actual page title "Manage Knowledge Content". While the link target is correct, consider using either the exact page title or adjusting the text to something like "manage documents and chunks" (lowercase, as part of a sentence) to make it clear it's a descriptive reference rather than a title reference.

en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents.mdx

Copilot · 2026-01-22T05:58:40Z

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx


-    Instead of splitting the text into paragraphs, the entire document is used as the parent chunk and retrieved directly. For performance reasons, only the first 10,000 tokens of the text are retained. This setting is ideal for smaller documents where paragraphs are interrelated, requiring full doc retrieval.
+- **Remove all URLs and email addresses**\
+  Eliminates URLs and email addresses that rarely contribute to meaningful retrieval.


The phrase "URLs and email addresses that rarely contribute to meaningful retrieval" could be more precise. Consider "URLs and email addresses, which rarely contribute to meaningful retrieval" or "URLs and email addresses that typically don't contribute to meaningful retrieval" to make the statement clearer and less absolute.

Suggested change

Eliminates URLs and email addresses that rarely contribute to meaningful retrieval.

Eliminates URLs and email addresses, which rarely contribute to meaningful retrieval.

Copilot · 2026-01-22T05:58:40Z

en/use-dify/knowledge/knowledge-pipeline/knowledge-pipeline-orchestration.mdx

+
+Summaries are embedded and indexed for retrieval as well. When a summary matches a query, its corresponding chunk is also returned.
+
+You can manually edit auto-generated summaries or regenerate them for specific documents later. See [Manage Documents and Chunks](/en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents) for details.


The link text "Manage Documents and Chunks" doesn't match the actual page title "Manage Knowledge Content". While the link target is correct, consider using either the exact page title or adjusting the text to something like "manage documents and chunks" (lowercase, as part of a sentence) to make it clear it's a descriptive reference rather than a title reference.

Suggested change

You can manually edit auto-generated summaries or regenerate them for specific documents later. See [Manage Documents and Chunks](/en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents) for details.

You can manually edit auto-generated summaries or regenerate them for specific documents later. See [Manage Knowledge Content](/en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents) for details.

Copilot · 2026-01-22T05:58:40Z

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx


-* **Chunk Delimiter**: The system automatically chunks the text whenever the specified delimiter appears. The default value is `\n`, which chunks text by sentences.
-* **Maximum chunk length:** Specifies the maximum number of text characters allowed per chunk. If this limit is exceeded, the system will automatically enforce chunking.
+You can manually edit auto-generated summaries or regenerate them for specific documents later. See [Manage Documents and Chunks](/en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents) for details.


The link text "Manage Documents and Chunks" doesn't match the actual page title "Manage Knowledge Content". While the link target is correct, consider using either the exact page title or adjusting the text to something like "manage documents and chunks" (lowercase, as part of a sentence) to make it clear it's a descriptive reference rather than a title reference.

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

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

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx

Copilot

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated no new comments.

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

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Riskey added 3 commits January 9, 2026 11:58

draft: add content related to summary index

7f3b4c3

refine the chunking configurations page

27c1dfd

Revise based on hands-on testing

fe61cff

Copilot AI review requested due to automatic review settings January 22, 2026 03:38

dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Jan 22, 2026

Copilot started reviewing on behalf of RiskeyL January 22, 2026 03:39 View session

dosubot bot added the documentation Improvements or additions to documentation label Jan 22, 2026

mintlify bot deployed to staging January 22, 2026 03:41 View deployment

Copilot AI reviewed Jan 22, 2026

View reviewed changes

github-actions bot mentioned this pull request Jan 22, 2026

🌐 Sync PR #665 translations: Add content related to summary index #666

Open

Copilot AI review requested due to automatic review settings January 22, 2026 04:06

Copilot started reviewing on behalf of RiskeyL January 22, 2026 04:06 View session

mintlify bot deployed to staging January 22, 2026 04:07 View deployment

Copilot AI reviewed Jan 22, 2026

View reviewed changes

RiskeyL force-pushed the add/summary-index branch from d37bc6b to 2fa579c Compare January 22, 2026 04:27

mintlify bot deployed to staging January 22, 2026 04:28 View deployment

Copilot AI review requested due to automatic review settings January 22, 2026 05:53

RiskeyL force-pushed the add/summary-index branch from 2fa579c to f804cf3 Compare January 22, 2026 05:53

Copilot started reviewing on behalf of RiskeyL January 22, 2026 05:53 View session

mintlify bot deployed to staging January 22, 2026 05:54 View deployment

Copilot AI reviewed Jan 22, 2026

View reviewed changes

RiskeyL force-pushed the add/summary-index branch from f804cf3 to b874d19 Compare January 22, 2026 07:23

mintlify bot deployed to staging January 22, 2026 07:24 View deployment

Copilot AI review requested due to automatic review settings January 22, 2026 07:25

RiskeyL force-pushed the add/summary-index branch from b874d19 to 7cd52d4 Compare January 22, 2026 07:25

Copilot started reviewing on behalf of RiskeyL January 22, 2026 07:25 View session

mintlify bot deployed to staging January 22, 2026 07:26 View deployment

Copilot AI reviewed Jan 22, 2026

View reviewed changes

en/use-dify/knowledge/create-knowledge/chunking-and-cleaning-text.mdx Show resolved Hide resolved

Copilot AI review requested due to automatic review settings January 22, 2026 07:35

Copilot started reviewing on behalf of RiskeyL January 22, 2026 07:36 View session

mintlify bot deployed to staging January 22, 2026 07:36 View deployment

Copilot AI reviewed Jan 22, 2026

View reviewed changes

Apply suggestions from code review

718702b

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

RiskeyL force-pushed the add/summary-index branch from e0dd9e3 to 718702b Compare January 22, 2026 07:41

mintlify bot deployed to staging January 22, 2026 07:42 View deployment

	Eliminates URLs and email addresses that rarely contribute to meaningful retrieval.
	Eliminates URLs and email addresses, which rarely contribute to meaningful retrieval.


		Summaries are embedded and indexed for retrieval as well. When a summary matches a query, its corresponding chunk is also returned.

		You can manually edit auto-generated summaries or regenerate them for specific documents later. See [Manage Documents and Chunks](/en/use-dify/knowledge/manage-knowledge/maintain-knowledge-documents) for details.

Add content related to summary index #665

Are you sure you want to change the base?

Add content related to summary index #665

Conversation

RiskeyL commented Jan 22, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

github-actions bot commented Jan 22, 2026

🌐 Multi-language Sync

Uh oh!

github-actions bot commented Jan 22, 2026

🌐 Multi-language Sync

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

github-actions bot commented Jan 22, 2026

🌐 Multi-language Sync

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Jan 22, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Copilot AI Jan 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 22, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants