### What problem does this PR solve?
- Update version tags in README files (including translations) from
v0.20.2 to v0.20.3
- 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?
Fix: Fixed the issue where the model configuration page could not be
scrolled #9572
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix home card not responding to click events
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix (next search): Optimize the search problem interface and related
functions #3221
-Add search_id to the retrievval_test interface
-Optimize handleSearchStrChange and handleSearch callbacks to determine
whether to enable AI search based on search configuration
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Reset all data except the first one on the chat page shared with
others #3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Fixed an issue where renaming a chat would create a new chat #3221
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Switch the root route to the new page #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix (search): Search application list supports renaming function #3221
-Update the search application list page and add a renaming operation
entry
-Modify the search application details interface to support obtaining
detailed information
-Optimize search settings page layout and style
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Update version tags in README files (including translations) from
v0.20.1 to v0.20.2
- 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?
Fix: Fixed the issue where clicking the SQL tool test button did not
request the interface #9541
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Refactor OpenAI to enable audio parsing.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
Allow Retrieval kb_ids param use kb_id,and allow list kb_name or kb_id。
- Add judgment on whether the knowledge base name is a list and support
batch queries
-When the knowledge base name does not exist, try using the ID for
querying
-If both query methods fail, throw an exception
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Move stop_event.wait(6) into finally block so that even when an
exception occurs, the loop still sleeps before retrying. This prevents
busy looping and excessive error logs when Redis connection fails.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Allow agent operators to select speech-to-text models #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
feat(search): Optimized search functionality and user interface #3221
### Type of change
- Added similarity threshold adjustment function
- Optimized mind map display logic
- Adjusted search settings interface layout
- Fixed related search and document viewing functions
- Optimized time display and node selection logic
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Update search_app.py to use SearchService instead of
KnowledgebaseService for duplicate
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Displays the embedded page of the chat module #3221
Feat: Let the agen operator support the selection of tts model #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix Gemini parameters error.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Fix (search): Optimize the search page functionality and UI #3221
- Add a search list component
- Implement search settings
- Optimize search result display
- Add related search functionality
- Adjust the search input box style
- Unify internationalized text
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add embedded search functionality.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
- Update httpx dependency to include socks support in pyproject.toml
- Update lockfile with new socksio dependency
### Type of change
- [x] Update dependencies for proxy support
### What problem does this PR solve?
Feat: Fixed the chat model setting echo issue
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
1. Use input length to prepare res
2. Adjust torch_empty_cache code location
### Type of change
- [x] Refactoring
- [x] Performance Improvement
### What problem does this PR solve?
There is a problem with the implementation of the Agent begin-form:
although the enablePrologue switch and the prologue input box are hidden
in Task mode, these values are still saved in the form data. If the user
first enables the opening and sets the content in Conversational mode,
and then switches to Task mode, these values will still be saved and may
be used in some scenarios.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
feat(search): Added app embedding functionality and optimized search
page #3221
- Added an Embed App button and related functionality
- Optimized the layout and interaction of the search settings interface
- Adjusted the search result display method
- Refactored some code to support new features
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add SMTP support for user invitation emails
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Conversation completion can specify different model
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Add metadata configuration for new chats #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Handle unexpected truncated Excel files.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- Unified configuration format: All services now use the same image
configuration structure for consistency.
- Private registry support: Added imagePullSecrets to enable pulling
images from private registries.
- Per-service flexibility: Each service can override image-related
parameters independently.
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
When calling HTTP to request data, if the JSON string returned by the
interface contains an unasked back slash like '\u', Python's RE module
will escape 'u' as Unicode, but there is no valid 4-digit hexadecimal
number at the end, so it will directly report an error. Error: re.
error: bad escape \ u at position 26
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Delete or filter conversations #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Upload files in the chat box #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
…e connecting line (#9226)
### What problem does this PR solve?
Can directly generate an agent node by dragging and dropping the
connecting line (#9226)
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
fix: preserve correct MIME & unify data URL handling for vision inputs
(relates #9248)
- Updated image2base64() to return a full data URL
(data:image/<fmt>;base64,...) with accurate MIME
- Removed hardcoded image/jpeg in Base._image_prompt(); pass through
data URLs and default raw base64 to image/png
- Set AnthropicCV._image_prompt() raw base64 media_type default to
image/png
- Ensures MIME type matches actual image content, fixing “cannot process
base64 image” errors on vLLM/OpenAI-compatible backends
### What problem does this PR solve?
This PR fixes a compatibility issue where base64-encoded images sent to
vision models (e.g., vLLM/OpenAI-compatible backends) were rejected due
to mismatched MIME type or incorrect decoding.
Previously, the backend:
- Always converted raw base64 into data:image/jpeg;base64,... even if
the actual content was PNG.
- In some cases, base64 decoding was attempted on the full data URL
string instead of the pure base64 part.
This caused errors like:
```
cannot process base64 image
failed to decode base64 string: illegal base64 data at input byte 0
```
by strict validators such as vLLM.
With this fix, the MIME type in the request now matches the actual image
content, and data URLs are correctly handled or passed through, ensuring
vision models can decode and process images reliably.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Send data to compare the performance of different models' answers
#3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
