Add and organize materials

The knowledge base supports files, Cherry Studio notes, local directories, and single web addresses. After import, you should also check the processing status, body text, and chunks, and reindex when the source is updated.

The completion standard is not “the file has appeared in the list,” but that the source can be read, the chunks are complete, and real questions can retrieve the correct source.

Choose the correct entry point

Choose the entry point according to the source: use [File] for a small number of files, [Directory] for a collection of similar files, [Note] for Cherry Studio content, and [Link] for public web pages.

Entry	What kind of materials it suits	Relationship after import	Main considerations
Files	PDF, Office, Markdown, text, etc.	Save a hosted copy	Up to 20 items can be selected at a time
Notes	Content already organized in Cherry Studio	A snapshot of the content at the time of import	Later changes to the original note will not sync automatically
Directory	A batch of local files under the same topic	Create source entries based on the directory contents	Do not import an unrelated directory as a whole
Link	A single publicly accessible web page	Save a snapshot of the web page at crawl time	Login pages, script-rendered pages, or restricted pages may be incomplete

Supported files include PDF, DOCX, DOC, PPTX, XLSX, XLS, MD, TXT, CSV, HTML, and EPUB. Scanned PDFs or image-based content also require OCR checking.

Add and verify sources

1

1. Select the source

Open the knowledge base, click the Add Source button, and choose [File], [Note], [Directory], or [Link].

2

2. Confirm the selected content

Files and notes can be selected in batches; up to 20 items can be added interactively at a time. When there are more sources, add them in batches or use the directory entry point.

3

3. Handle naming conflicts

When a new source has the same name as an existing entry, choose [Keep All] or [Replace]. [Replace] is usually chosen when updating policies, manuals, and note snapshots.

Choosing [Keep All] allows both new and old content to participate in retrieval. Do this only when you truly need to query different versions in parallel, and indicate the date or version in the name.

4

4. Wait for processing to complete

The source will go through stages such as copying, reading, chunking, and indexing. Vector indexes will not be created if no embedding model is configured, but keyword indexes will still be created.

After the source becomes available, spot-check the body text and chunks.

5

5. Spot-check the body text and chunks

Open the source to view the body text, or view the chunks from the source row menu. Focus on whether the title order, tables, OCR text, and key sentences have been split incorrectly.

6

6. Complete the retrieval test

Use a question with a clear answer to check the correct source and excerpt. After the source is updated, retest using the same set of questions.

Final acceptance should be based on the source, excerpt completeness, and ranking, not just on whether results are returned.

Source status and handling methods

Symptom	Possible cause	Handling method
Processing for a long time	The file is large, or the parser or model is unavailable	Check the original file, document processing, and embedding model
Error displayed	Copying, reading, chunking, or indexing failed	Open the error message and handle it according to the failed stage
Missing body text or garbled text	The file processor is not compatible, or scanned content was not OCRed	Change the document processing method or configure OCR
Chunks are missing key sentences	Chunk boundaries are not appropriate	Adjust the chunks and then run [Reindex]
Old and new versions are both matched	[Keep All] was chosen for sources with the same name	Delete the old entry, or re-import and choose [Replace]

Reindex and delete

After the chunking, parser, or embedding settings change, old entries will not automatically apply the new settings. Use [Reindex] for a single source, or select multiple sources and reindex them.

Deleting an entry will remove the hosted copy and index from the current knowledge base. It will not delete the original file or original note, but before deleting, you should still confirm whether the knowledge base contains the only copy.

Configuration notes

Configuration item	Product default	Suggested starting point	Effect	Applicable scenario	Notes
Number added at once	Up to 20 items	First add a small number of representative sources	Control the size of each import	First time building the knowledge base or troubleshooting	Verify parsing and retrieval before large-scale import
Handling same-name items	Choose when conflicts occur	Use [Replace] when updating sources	Decide whether new and old entries coexist	Policy, manual, and note updates	[Keep All] may allow old content to participate in retrieval
Reindex	Run manually	Run after settings changes	Make old sources use the new parsing, chunking, or model settings	Fine-tune or fix sources	A retrieval test must be performed again after completion

User case

Xiaolin updates the business travel policy every month. He imports the new file with the same name and chooses [Replace]. After the source finishes processing, he spot-checks the body text and chunks, then uses fixed questions to test the lodging, transportation, and approval rules.

The completion standard is: old rules no longer appear in the retrieval results, and the conditions and amounts in the new rules can be matched consistently.

Common questions

Will the knowledge base update automatically after I modify the original note?

No. Notes are imported as a snapshot of the content at that time. After modifying it, you need to add it again and choose [Replace], or run [Reindex] on the corresponding source.

Why does the web page only capture part of the content?

Pages that require login, depend on script rendering, or have access restrictions may not be fully captured. You can save the body text using files or notes first, then import it.

Will deleting a knowledge base entry delete the original file?

It will not delete the original file or original note, but it will remove the hosted copy and index from the knowledge base.

Continue reading

Document parsing and OCR

Handle missing text, garbled characters, and scanned content.

Check materials and recall

Verify retrieval quality with fixed questions.

Data, privacy, and maintenance

Understand backup, deletion, and service boundaries.