centersl/dify-docs
1
0
Fork 0
mirror of https://github.com/langgenius/dify-docs.git synced 2026-03-27 13:28:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

Refine docs based on readability, usability, and enterprise PM feedback (#619)

Browse Source 
* Refine docs based on internal feedback

* update the zh and ja docs

---------

Co-authored-by: Riskey <riskey47@dify.ai>
This commit is contained in:
Riskey
2025-12-16 19:37:13 +08:00
committed by GitHub
parent 821b83c0b5
commit 5d7556d5f2
15 changed files with 101 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
en/use-dify/knowledge/create-knowledge/import-text-data/readme.mdx
View File

@@ -12,30 +12,34 @@ When quick-creating a knowledge base, you can upload local files as its data sou
2. Select **Import from file** as the data source, then upload your files.
- Maximum file size: 15 MB
- Maximum number of files per upload: 5
<Info>
On Dify Cloud, **batch uploading** is only available on [the **Professional** and **Team** plans](https://dify.ai/pricing).
</Info>
<Info>
On Dify Cloud, **batch uploading** (up to 50 files per upload) is only available on [paid plans](https://dify.ai/pricing).
</Info>
- Maximum file size: 15 MB
<Tip>
For self-hosted deployments, you can adjust these two limits via the environment variables `UPLOAD_FILE_SIZE_LIMIT` and `UPLOAD_FILE_BATCH_LIMIT`.
</Tip>
---
**For Images in Uploaded Files**
JPG, JPEG, PNG, and GIF images under 2 MB are automatically extracted as attachments to their corresponding chunks. These images can be managed independently and are returned alongside their chunks during retrieval.
JPG, JPEG, PNG, and GIF images under 2 MB are automatically extracted as attachments to their corresponding chunks. These images can be managed independently and are returned alongside their chunks during retrieval.
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
<Tip>
For self-hosted deployments, you can adjust the size limit via the environment variable `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`.
For self-hosted deployments, you can adjust the following limits via environment variables:
- Maximum image size: `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`
- Maximum number of attachments per chunk: `SINGLE_CHUNK_ATTACHMENT_LIMIT`
</Tip>
<Note>
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
For self-hosted deployments, you can adjust this limit via the environment variable `SINGLE_CHUNK_ATTACHMENT_LIMIT`.
</Note>
The above extraction rule applies to:
- Images embedded in DOCX files

12
en/use-dify/knowledge/create-knowledge/setting-indexing-methods.mdx
View File

@@ -10,10 +10,6 @@ Similar to the search engines use efficient indexing algorithms to match search
The knowledge base offers two index methods: **High-Quality** and **Economical**, each with different retrieval setting options.
<Note>
The original **Q\&A mode (available only for the Community Edition)** is now an optional feature under the High Quality index method.
</Note>
<Tabs>
<Tab title="High Quality">
@@ -35,8 +31,12 @@ The knowledge base offers two index methods: **High-Quality** and **Economical**
The High-Quality index method supports three retrieval strategies: vector search, full-text search, or hybrid search. Learn more in [Configure the Retrieval Settings](#configure-the-retrieval-settings).
### Enable Q&A Mode (Optional, Community Edition Only)
### Q&A Mode
<Info>
Q&A mode is available for self-hosted deployments only.
</Info>
When this mode is enabled, the system segments the uploaded text and automatically generates Q\&A pairs for each segment after summarizing its content.
Compared with the common **Q to P** strategy (user questions matched with text paragraphs), the Q\&A mode uses a **Q to Q** strategy (questions matched with questions).

18
en/use-dify/knowledge/knowledge-pipeline/knowledge-pipeline-orchestration.mdx
View File

@@ -196,7 +196,9 @@ You can choose Dify's Doc Extractor to process files, or select tools based on y
<Accordion title="For images in documents">
Images in documents can be extracted using appropriate doc processors. Extracted images are attached to their corresponding chunks, can be managed independently, and are returned alongside those chunks during retrieval.
Images in documents can be extracted using appropriate doc processors. Extracted images are attached to their corresponding chunks, can be managed independently, and are returned alongside those chunks during retrieval.
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
If no images are extracted by the selected processor, Dify will automatically extract JPG, JPEG, PNG, and GIF images under 2 MB that are referenced via accessible URLs using the following Markdown syntax:
@@ -204,15 +206,13 @@ If no images are extracted by the selected processor, Dify will automatically ex
- `![alt text](image_url "optional title")`
<Tip>
For self-hosted deployments, you can adjust the size limit via the environment variable `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`.
For self-hosted deployments, you can adjust these limits via environment variables:
- Maximum image size: `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`
- Maximum number of attachments per chunk: `SINGLE_CHUNK_ATTACHMENT_LIMIT`
</Tip>
<Note>
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
For self-hosted deployments, you can adjust this limit via the environment variable `SINGLE_CHUNK_ATTACHMENT_LIMIT`.
</Note>
If you select a multimodal embedding model (indicated by the **Vision** icon) in subsequent index settings, the extracted images will be embedded and indexed for retrieval.
</Accordion>
@@ -419,7 +419,7 @@ In the Economical method, each block uses 10 keywords for retrieval without call
| Economical | Inverted Index | Common search engine retrieval method, matches queries with key content |
<Note>
If candidate chunks may include image attachments, select a multimodal rerank model (indicated by the **Vision** icon). Otherwise, images will be excluded from reranking and the retrieval results.
If the selected embedding model is multimodal, select a multimodal rerank model (indicated by the **Vision** icon) as well. Otherwise, retrieved images will be excluded from reranking and the retrieval results.
</Note>
You can also refer to the table below for information on configuring chunk structure, index methods, parameters, and retrieval settings.

4
en/use-dify/knowledge/knowledge-request-rate-limit.mdx
View File

@@ -4,11 +4,9 @@ icon: "gauge"
tag: "CLOUD"
---
We will implement Knowledge Request Rate Limits starting **February 24, 2025**, to ensure optimal service performance and a better knowledge experience for all users.
## What is Knowledge Request Rate Limit?
Knowledge Request Rate Limit refers to the maximum number of actions that a workspace can perform in the knowledge base within one minute. These actions include creating datasets, managing documents, and running queries in apps or workflows.
On Dify Cloud, the knowledge request rate limit refers to the maximum number of actions that a workspace can perform in the knowledge base within one minute. These actions include creating datasets, managing documents, and running queries in apps or workflows.
## Limitations of Different Subscription Versions

10
en/use-dify/monitor/logs.mdx
View File

@@ -50,15 +50,17 @@ Team members can add internal notes and improved responses directly in the log i
**Feedback Analysis**
Identify common complaint patterns, successful interaction types, and areas needing improvement.
## Data Retention
## Log Retention
<Warning>
Ensure your application complies with local data privacy regulations. Publish a privacy policy and obtain user consent where required.
</Warning>
**Free Plans:** Logs are retained for 30 days
**Paid Plans:** Extended retention based on plan tier
**Self-Hosted:** Configurable retention policy
- **Sandbox**: Logs are retained for 30 days.
- **Professional & Team**: Unlimited log retention during active subscription.
- **Self-hosted**: Unlimited by default; configurable via environment variables `WORKFLOW_LOG_CLEANUP_ENABLED`, `WORKFLOW_LOG_RETENTION_DAYS`, and `WORKFLOW_LOG_CLEANUP_BATCH_SIZE`.
## Improving Applications with Logs