**Context and Purpose:**
This PR automatically remediates a security vulnerability:
- **Description:** h11: h11 accepts some malformed Chunked-Encoding
bodies
- **Rule ID:** CVE-2025-43859
- **Severity:** CRITICAL
- **File:** uv.lock
- **Lines Affected:** None - None
This change is necessary to protect the application from potential
security risks associated with this vulnerability.
**Solution Implemented:**
The automated remediation process has applied the necessary changes to
the affected code in `uv.lock` to resolve the identified issue.
Please review the changes to ensure they are correct and integrate as
expected.
### What problem does this PR solve?
Feat: New Agent startup parameters add knowledge base parameter #9194
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
fix "out of memory" if slide.get_thumbnail() to a huge image
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
…eType'"
### What problem does this PR solve?
fix "TypeError: '<' not supported between instances of 'Emu' and
'NoneType'"
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix#8424 NPE in dify_retrieval.py, add log exception
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix:
```bash
'Langfuse' object has no attribute 'trace'
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/9177
The reason should be due to the gemin internal use a different parameter
name
`
max_output_tokens (int):
Optional. The maximum number of tokens to include in a
response candidate.
Note: The default value varies by model, see the
``Model.output_token_limit`` attribute of the ``Model``
returned from the ``getModel`` function.
This field is a member of `oneof`_ ``_max_output_tokens``.
`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
The index name of the tag chunks is generated by the tenant id of the
knowledge base, so it should use the tenant id instead of the current
user id in the listing tags API.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR adds a data backup and migration solution for RAGFlow Docker
Compose deployments. Currently, users lack a standardized way to backup
and restore RAGFlow data volumes (MySQL, MinIO, Redis, Elasticsearch),
which is essential for data safety and environment migration.
**Solution:**
- **Migration Script** (`docker/migration.sh`) - Automates
backup/restore operations for all RAGFlow data volumes
- **Documentation**
(`docs/guides/migration/migrate_from_docker_compose.md`) - Usage guide
and best practices
- **Safety Features** - Container conflict detection and user
confirmations to prevent data loss
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
Co-authored-by: treedy <treedy2022@icloud.com>
### What problem does this PR solve?
- Update version tags in README files (including translations) from
v0.19.1 to v0.20.0
- Modify Docker image references and documentation to reflect new
version
- Update version badges and image descriptions
- Maintain consistency across all language variants of README files
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
Feat: Adjust the style of the note node #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: Fixed share-log UI issues and log-template bugs #3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Modify the style of the agent page bright theme #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add industry-related search keyword generation function
- When generating search keywords, support for specific industries has
been added
- If the "industry" parameter is provided, industry-specific
restrictions will be added to the prompt
- This change can help users generate more precise search keywords
within specific industries
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add a series of qwen3 latest SOTA models:
qwen3-coder-480b-a35b-instruct, qwen3-30b-a3b-instruct-2507,
qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b-instruct-2507,
qwen3-235b-a22b-thinking-2507
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Remove the exception comment field from the agent form #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix kimi-latest is not authorized.
Add kimi-thinking-preview.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
```bash
Traceback (most recent call last):
File "/home/infiniflow/workspace/ragflow/api/db/services/document_service.py", line 635, in update_progress
info["progress_msg"] = "%d tasks are ahead in the queue..."%get_queue_length(priority)
File "/home/infiniflow/workspace/ragflow/api/db/services/document_service.py", line 686, in get_queue_length
return int(group_info.get("lag", 0))
TypeError: int() argument must be a string, a bytes-like object or a real number, not 'NoneType'
```
This issue can happen very rare. When a `stream` is first created, the
`lag` value may be nil, which can cause this issue. However, once any
message is synced, the `lag` will become `0` afterwards.
```bash
> XINFO GROUPS rag_flow_svr_queue
1) 1) "name"
2) "rag_flow_svr_task_broker"
3) "consumers"
4) (integer) 0
5) "pending"
6) (integer) 0
7) "last-delivered-id"
8) "1753952489937-0"
9) "entries-read"
10) (nil)
11) "lag"
12) (nil)
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Delete the operator node and hide the corresponding sheet #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display operator icons on the agent form #3221
Fix: Fixed the issue where the form corresponding to the tool operator
icon could not appear after clicking it #3211
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: Improve Agent templates functionality and fix some UI style issues
#3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Displays the tool operator icon #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
add Kimi-K2-Instruct from Tongyi-Qianwen API
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Automatically save agent canvas content
Feat: Replace the link of the old version of the agent module #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
- Add Generator return type annotation for tts method
- Import typing.Generator for type hints
### Type of change
- [x] Refactoring
### What problem does this PR solve?
This code allows user chat to auto-scroll down when entered, but if user
scrolls up away from the generative feedback, autoscroll is disabled.
Close#9062
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Charles Copley <ccopley@ancera.com>
### What problem does this PR solve?
Feat: Make the agent dialog window exposed to the outside world fill in
the begin form #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
#9082#6365
<u> **WARNING: it's not compatible with the older version of `Agent`
module, which means that `Agent` from older versions can not work
anymore.**</u>
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Handling abnormal anchor points of agent operators #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Add log-detail page,Improve the style of chat boxes #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Translate operator names and allow mailboxes to reference operator
names #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Replace the placeholder test image in base64_image.py with a new sample
image data string.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Feat: Add wencai operator #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
doc_ids is a list , should use request.args.getlist("doc_ids")
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Add invoke and github operators #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
