You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: en/use-dify/knowledge/create-knowledge/import-text-data/readme.mdx
+17-13Lines changed: 17 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,30 +12,34 @@ When quick-creating a knowledge base, you can upload local files as its data sou
12
12
13
13
2. Select **Import from file** as the data source, then upload your files.
14
14
15
-
- Maximum file size: 15 MB
16
-
17
15
- Maximum number of files per upload: 5
18
16
19
-
<Info>
20
-
On Dify Cloud, **batch uploading** is only available on [the **Professional** and **Team** plans](https://dify.ai/pricing).
21
-
</Info>
17
+
<Info>
18
+
On Dify Cloud, **batch uploading** (up to 50 files per upload) is only available on [paid plans](https://dify.ai/pricing).
19
+
</Info>
20
+
21
+
- Maximum file size: 15 MB
22
+
23
+
<Tip>
24
+
For self-hosted deployments, you can adjust these two limits via the environment variables `UPLOAD_FILE_SIZE_LIMIT` and `UPLOAD_FILE_BATCH_LIMIT`.
25
+
</Tip>
22
26
23
27
---
24
28
25
29
**For Images in Uploaded Files**
26
30
27
-
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.
31
+
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.
32
+
33
+
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
28
34
29
35
<Tip>
30
-
For self-hosted deployments, you can adjust the size limit via the environment variable `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`.
36
+
For self-hosted deployments, you can adjust the following limits via environment variables:
37
+
38
+
- Maximum image size: `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`
39
+
40
+
- Maximum number of attachments per chunk: `SINGLE_CHUNK_ATTACHMENT_LIMIT`
31
41
</Tip>
32
42
33
-
<Note>
34
-
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
35
-
36
-
For self-hosted deployments, you can adjust this limit via the environment variable `SINGLE_CHUNK_ATTACHMENT_LIMIT`.
Copy file name to clipboardExpand all lines: en/use-dify/knowledge/create-knowledge/setting-indexing-methods.mdx
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,10 +10,6 @@ Similar to the search engines use efficient indexing algorithms to match search
10
10
11
11
The knowledge base offers two index methods: **High-Quality** and **Economical**, each with different retrieval setting options.
12
12
13
-
<Note>
14
-
The original **Q\&A mode (available only for the Community Edition)** is now an optional feature under the High Quality index method.
15
-
</Note>
16
-
17
13
<Tabs>
18
14
<Tabtitle="High Quality">
19
15
@@ -35,8 +31,12 @@ The knowledge base offers two index methods: **High-Quality** and **Economical**
35
31
36
32
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).
37
33
38
-
### Enable Q&A Mode (Optional, Community Edition Only)
39
-
34
+
### Q&A Mode
35
+
36
+
<Info>
37
+
Q&A mode is available for self-hosted deployments only.
38
+
</Info>
39
+
40
40
When this mode is enabled, the system segments the uploaded text and automatically generates Q\&A pairs for each segment after summarizing its content.
41
41
42
42
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).
Copy file name to clipboardExpand all lines: en/use-dify/knowledge/knowledge-pipeline/knowledge-pipeline-orchestration.mdx
+8-8Lines changed: 8 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -196,22 +196,22 @@ You can choose Dify's Doc Extractor to process files, or select tools based on y
196
196
197
197
<Accordiontitle="For images in documents">
198
198
199
-
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.
199
+
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.
200
+
201
+
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
200
202
201
203
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:
202
204
203
205
-``
204
206
-``
205
207
206
208
<Tip>
207
-
For self-hosted deployments, you can adjust the size limit via the environment variable `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`.
208
-
</Tip>
209
+
For self-hosted deployments, you can adjust these limits via environment variables:
209
210
210
-
<Note>
211
-
Each chunk supports up to 10 image attachments; images beyond this limit will not be extracted.
211
+
- Maximum image size: `ATTACHMENT_IMAGE_FILE_SIZE_LIMIT`
212
212
213
-
For self-hosted deployments, you can adjust this limit via the environment variable `SINGLE_CHUNK_ATTACHMENT_LIMIT`.
214
-
</Note>
213
+
- Maximum number of attachments per chunk: `SINGLE_CHUNK_ATTACHMENT_LIMIT`
214
+
</Tip>
215
215
216
216
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.
217
217
@@ -419,7 +419,7 @@ In the Economical method, each block uses 10 keywords for retrieval without call
419
419
| Economical | Inverted Index | Common search engine retrieval method, matches queries with key content |
420
420
421
421
<Note>
422
-
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.
422
+
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.
423
423
</Note>
424
424
425
425
You can also refer to the table below for information on configuring chunk structure, index methods, parameters, and retrieval settings.
Copy file name to clipboardExpand all lines: en/use-dify/knowledge/knowledge-request-rate-limit.mdx
+1-3Lines changed: 1 addition & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,11 +4,9 @@ icon: "gauge"
4
4
tag: "CLOUD"
5
5
---
6
6
7
-
We will implement Knowledge Request Rate Limits starting **February 24, 2025**, to ensure optimal service performance and a better knowledge experience for all users.
8
-
9
7
## What is Knowledge Request Rate Limit?
10
8
11
-
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.
9
+
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.
Copy file name to clipboardExpand all lines: en/use-dify/monitor/logs.mdx
+6-4Lines changed: 6 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -50,15 +50,17 @@ Team members can add internal notes and improved responses directly in the log i
50
50
**Feedback Analysis**
51
51
Identify common complaint patterns, successful interaction types, and areas needing improvement.
52
52
53
-
## Data Retention
53
+
## Log Retention
54
54
55
55
<Warning>
56
56
Ensure your application complies with local data privacy regulations. Publish a privacy policy and obtain user consent where required.
57
57
</Warning>
58
58
59
-
**Free Plans:** Logs are retained for 30 days
60
-
**Paid Plans:** Extended retention based on plan tier
61
-
**Self-Hosted:** Configurable retention policy
59
+
-**Sandbox**: Logs are retained for 30 days.
60
+
61
+
-**Professional & Team**: Unlimited log retention during active subscription.
62
+
63
+
-**Self-hosted**: Unlimited by default; configurable via environment variables `WORKFLOW_LOG_CLEANUP_ENABLED`, `WORKFLOW_LOG_RETENTION_DAYS`, and `WORKFLOW_LOG_CLEANUP_BATCH_SIZE`.
このモードを有効にすると、システムはアップロードされたテキストを分割し、各分割のコンテンツを要約して自動的にQ\&Aマッチングペアを生成します。一般的な「Q to P」(ユーザーの質問がテキスト段落にマッチング)戦略とは異なり、QAモードでは「Q to Q」(質問が質問にマッチング)戦略を採用しています。
0 commit comments