### What problem does this PR solve?
Fix: Metadata mult-selected display error
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Use negative lookbehind (?<![a-zA-Z]) so \] and \) inside commands
(e.g. \right], \big)) are not treated as block/inline delimiters
- Use greedy matching to capture up to the last valid delimiter, fixing
truncated formulas (e.g. C_{seq}(y|x) = \frac{1}{|y|} ...)
- Add unit tests for preprocessLaTeX
Closes#13134
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
RAGFlow supports 12 UI languages but does not include Bulgarian. This PR
adds Bulgarian (`bg` / `Български`) as the 13th supported language,
covering the full UI translation (2001 keys across all 26 sections) and
OCR/PDF parser language mapping.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Changes
- **`web/src/constants/common.ts`** — Registered Bulgarian in all 5
language data structures (`LanguageList`, `LanguageMap`,
`LanguageAbbreviation` enum, `LanguageAbbreviationMap`,
`LanguageTranslationMap`)
- **`web/src/locales/config.ts`** — Added lazy-loading dynamic import
for the `bg` locale
- **`web/src/locales/bg.ts`** *(new)* — Full Bulgarian translation file
with all 26 sections, matching the English source (`en.ts`). All
interpolation placeholders, HTML tags, and technical terms are preserved
as-is
- **`deepdoc/parser/mineru_parser.py`** — Mapped `'Bulgarian'` to
`'cyrillic'` in `LANGUAGE_TO_MINERU_MAP` for OCR/PDF parser support
### How it works
The language selector automatically picks up the new entry. When a user
selects "Български", the translation bundle is lazy-loaded on demand.
The preference is persisted to the database and localStorage across
sessions.
### 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
- [x] Refactoring
### What problem does this PR solve?
Fix: replace session page icons and fix nested list search functionality
in filters
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Bugs fixed (#13109)
- chat pdf preview error
- data source add box error
- change route next-chat -> chat , next-search->search ...
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes SSO/OIDC login persistence after the Vite migration
#12568. Because wrappers are ignored by React Router, the OAuth callback
never stored the auth token in localStorage, causing auth to only work
while ?auth= stayed in the URL. We move that logic into a route loader
and remove the Bearer prefix for the signed token so the backend accepts
it.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Contribution during my time at RAGcon GmbH.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
### What problem does this PR solve?
Fix: Bugs fixed
- metadata icon error
- search page's image not display
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Add authentication validation to the document API interface for
embedded pages and modify the document display styles.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
- add resizable support to shared textarea component
- enable vertical resizing for chat inputs in chat and share surfaces
- preserve autosize behavior while honoring manual resize height
## Test plan
- not run (not requested)
Fixes#12803
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
## Description
This PR fixes an issue where the input and variable configuration tables
in the Agent Canvas (specifically for **Begin**, **UserFillUp**, and
**Invoke** nodes) were truncated at 10 items.
**Root Cause:**
The tables utilized `@tanstack/react-table` with
`getPaginationRowModel()` enabled. Since the default page size is 10 and
no pagination UI controls were implemented, users could not access items
beyond the 10th row.
**Solution:**
Removed `getPaginationRowModel` from the table configurations. These
lists (inputs/variables) are typically short, so rendering all items in
a single scrollable view is the intended behavior.
* Modified `query-table.tsx`
* Modified `variable-table.tsx`
## How to verify
1. Create a **Begin**, **UserFillUp**, or **Invoke** node in the Agent
Canvas.
2. Add more than 10 input items or variables.
3. Verify that all items are visible in the list and not truncated at
the 10th item.
## What kind of change does this PR introduce?
* [x] Bugfix
### What problem does this PR solve?
Fix: Lazy loading adds a loading state to the page
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix dataset page enter key to save
Fix the warnings and optimize the code.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Control interface documentation directory display and hiding
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
## Summary
- keep assistant message containers stretched to available width
- avoid width collapse during streaming by allowing flex items to shrink
## Test plan
- not run (not requested)
Fixes#12985
Made with [Cursor](https://cursor.com)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Liu An <asiro@qq.com>
…, clicking "Parse" will still ask if you want to clear the chunks of
the already parsed files.
### What problem does this PR solve?
Fix: After selecting all and then unchecking the already parsed files,
clicking "Parse" will still ask if you want to clear the chunks of the
already parsed files.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix ingestion pipeline
Only 1 file is acceptable for ingestion pipeline.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Add model verify
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Fix: adressing style without a default value #12396#11510
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Fixed the issue where deleted images in the agent chat box would
still be sent to the backend.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Closes: #12921
### What problem does this PR solve?
Previously, multi-file upload was not working correctly across the
application:
- **Chat**: UI displayed "Upload max 5 files" but only the first file
was actually uploaded
- **Agent conversational mode**: Frontend sent multiple files but
backend only processed one
- **Agent task-mode file inputs**: Explicitly limited to single file
only
This PR enables proper multi-file upload support for both chat and agent
workflows, allowing users to upload and process multiple files (up to 5)
as the UI originally suggested.
**Changes:**
- `web/src/pages/next-chats/hooks/use-upload-file.ts`: Process all files
instead of only `files[0]`
- `api/apps/canvas_app.py`: Handle multiple files via
`files.getlist("file")`
- `web/src/pages/agent/debug-content/uploader.tsx`: Allow up to 5 files
with `multiple={true}`
- `agent/component/begin.py` & `fillup.py`: Support file arrays while
maintaining backward compatibility
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: Variables within multiple parentheses cannot be displayed
correctly. #12987
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: PDF chunking issue for single-page documents
Refactor: Change the default refresh frequency to 5
Fix: Add a 0-degree threshold; require other rotation angles to exceed
it by at least 0.2
Fix: Put connector name tips to correct place
Fix: incorrect example response in delete datasets.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
This PR adds MySQL and PostgreSQL as data source connectors, allowing
users to import data directly from relational databases into RAGFlow for
RAG workflows.
Many users store their knowledge in databases (product catalogs,
documentation, FAQs, etc.) and currently have no way to sync this data
into RAGFlow without exporting to files first. This feature lets them
connect directly to their databases, run SQL queries, and automatically
create documents from the results.
Closes#763Closes#11560
### 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):
### What this PR does
**New capabilities:**
- Connect to MySQL and PostgreSQL databases
- Run custom SQL queries to extract data
- Map database columns to document content (vectorized) and metadata
(searchable)
- Support incremental sync using a timestamp column
- Full frontend UI with connection form and tooltips
**Files changed:**
Backend:
- `common/constants.py` - Added MYSQL/POSTGRESQL to FileSource enum
- `common/data_source/config.py` - Added to DocumentSource enum
- `common/data_source/rdbms_connector.py` - New connector (368 lines)
- `common/data_source/__init__.py` - Exported the connector
- `rag/svr/sync_data_source.py` - Added MySQL and PostgreSQL sync
classes
- `pyproject.toml` - Added mysql-connector-python dependency
Frontend:
- `web/src/pages/user-setting/data-source/constant/index.tsx` - Form
fields
- `web/src/locales/en.ts` - English translations
- `web/src/assets/svg/data-source/mysql.svg` - MySQL icon
- `web/src/assets/svg/data-source/postgresql.svg` - PostgreSQL icon
### Testing done
Tested with MySQL 8.0 and PostgreSQL 16:
- Connection validation works correctly
- Full sync imports all query results as documents
- Incremental sync only fetches rows updated since last sync
- Custom SQL queries filter data as expected
- Invalid credentials show clear error messages
- Lint checks pass (`ruff check` returns no errors)
---------
Co-authored-by: mkdev11 <YOUR_GITHUB_ID+MkDev11@users.noreply.github.com>
### What problem does this PR solve?
Fix: If the agent debug sheet contains too much content, some of it will
not be displayed. #12974
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR adds **Seafile** as a new data source connector for RAGFlow.
[Seafile](https://www.seafile.com/) is an open-source, self-hosted file
sync and share platform widely used by enterprises, universities, and
organizations that require data sovereignty and privacy. Users who store
documents in Seafile currently have no way to index and search their
content through RAGFlow.
This connector enables RAGFlow users to:
- Connect to self-hosted Seafile servers via API token
- Index documents from personal and shared libraries
- Support incremental polling for updated files
- Seamlessly integrate Seafile-stored documents into their RAG pipelines
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Changes included
- `SeaFileConnector` implementing `LoadConnector` and `PollConnector`
interfaces
- Support for API token
- Recursive file traversal across libraries
- Time-based filtering for incremental updates
- Seafile logo (sourced from Simple Icons, CC0)
- Connector configuration and registration
### Testing
- Tested against self-hosted Seafile Community Edition
- Verified authentication (token)
- Verified document ingestion from personal and shared libraries
- Verified incremental polling with time filters
### What problem does this PR solve?
Fix:Optimize metadata and optimize the empty state style of the agent
page.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add memory status indicator and detail message dialog
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
#### Summary
This PR enhances the Semi-automatic metadata filtering mode by allowing
users to explicitly pre-define operators (e.g., contains, =, >, etc.)
for selected metadata keys. While the LLM still dynamically extracts the
filter value from the user's query, it is now strictly constrained to
use the operator specified in the UI configuration.
Using this feature is optional. By default the operator selection is set
to "automatic" resulting in the LLM choosing the operator (as
presently).
#### Rationale & Use Case
This enhancement was driven by a concrete challenge I encountered while
working with technical documentation.
In my specific use case, I was trying to filter for software versions
within a technical manual. In this dataset, a single document chunk
often applies to multiple software versions. These versions are stored
as a combined string within the metadata for each chunk.
When using the standard semi-automatic filter, the LLM would
inconsistently choose between the contains and equals operators. When it
chose equals, it would exclude every chunk that applied to more than one
version, even if the version I was searching for was clearly included in
that metadata string. This led to incomplete and frustrating retrieval
results.
By extending the semi-automatic filter to allow pre-defining the
operator for a specific key, I was able to force the use of contains for
the version field. This change immediately led to significantly improved
and more reliable results in my case.
I believe this functionality will be equally useful for others dealing
with "tagged" or multi-value metadata where the relationship between the
query and the field is known, but the specific value needs to remain
dynamic.
#### Key Changes
##### Backend & Core Logic
- `common/metadata_utils.py`: Updated apply_meta_data_filter to support
a mixed data structure for semi_auto (handling both legacy string arrays
and the new object-based format {"key": "...", "op": "..."}).
- `rag/prompts/generator.py`: Extended gen_meta_filter to accept and
pass operator constraints to the LLM.
- `rag/prompts/meta_filter.md`: Updated the system prompt to instruct
the LLM to strictly respect provided operator constraints.
##### Frontend
- `web/src/components/metadata-filter/metadata-semi-auto-fields.tsx`:
Enhanced the UI to include an operator dropdown for each selected
metadata key, utilizing existing operator constants.
- `web/src/components/metadata-filter/index.tsx`: Updated the validation
schema to accommodate the new state structure.
#### Test Plan
- Backward Compatibility: Verified that existing semi-auto filters
stored as simple strings still function correctly.
- Prompt Verification: Confirmed that constraints are correctly rendered
in the LLM system prompt when specified.
- Added unit tests as
`test/unit_test/common/test_apply_semi_auto_meta_data_filter.py`
- Manual End-to-End:
- Configured a "Semi-automatic" filter for a "Version" key with the
"contains" operator.
- Asked a version-specific query.
- Result
<img width="1173" height="704" alt="Screenshot 2026-02-02 145359"
src="https://github.com/user-attachments/assets/510a6a61-a231-4dc2-a7fe-cdfc07219132"
/>
### 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):
---------
Co-authored-by: Philipp Heyken Soares <philipp.heyken-soares@am.ai>
## Description
This PR focuses on API performance optimization and refining the model
capability detection logic in the Agent/Canvas module.
### 1. Performance Optimization (Backend)
- **Changes**: Removed `cls.model.dsl` from query fields in
`UserCanvasService.get_by_tenant_ids`.
- **Reasoning**: The `dsl` object is large and unnecessary for the Agent
list view. Excluding it reduces the payload size of the
`/v1/canvas/list` API, leading to faster serialization and reduced
network latency.
- **Consistency**: Full DSL data remains accessible via the individual
`/v1/canvas/get/<id>` endpoint used in the detail view.
### 2. Multimodal Detection Refinement (Frontend)
- **Changes**: Replaced `model_type === LlmModelType.Image2text` with
`tags?.includes('IMAGE2TEXT')`.
- **Reasoning**: In RAGFlow, `model_type` defines the primary role of a
model (e.g., `chat`). However, many advanced Chat models are also
vision-capable. Since `model_type` is a single-value field, it cannot
represent these multiple capabilities.
- **Solution**: Utilizing the `tags` field (which supports multiple
attributes) to check for `IMAGE2TEXT` ensures that models like
`gpt-5.2-pro` correctly display multimodal input options.
## Type of Change
- [x] Bug fix (logic correction for multimodal detection)
- [x] Optimization (performance improvement for list API)
## Main Changes
- `api/db/services/canvas_service.py`: Optimized DB query by excluding
heavy DSL fields.
- `web/src/pages/agent/form/agent-form/index.tsx`: Enhanced capability
detection using the tags system.
## Verification
- [x] Verified Agent list loads faster with reduced response payload.
- [x] Confirmed that `chat` models with the `IMAGE2TEXT` tag now
correctly enable the multimodal input UI.
### What problem does this PR solve?
Fix Gitee AI links and update the reranker model configuration
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: franco <1787003204@q.comq>
### What problem does this PR solve?
Close#12768.
This PR adds OceanBase support to RAGFlow’s Text-to-SQL (ExeSQL)
component.
OceanBase is integrated via MySQL compatibility mode, and the UI
`db_type` options are updated accordingly.
### 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):
### Changes
**Backend**
- Add `oceanbase` `db_type` validation and connection logic in
`exesql.py` and reuse existing MySQL compatibility mode
**Frontend**
- Add OceanBase option to the ExeSQL `db_type` selector
### How to test
1. Configure OceanBase connection in ExeSQL node
(host/port/user/password/database)
2. Input: “Show 10 rows from test table”
3. Generated SQL: `SELECT * FROM test LIMIT 10;`
4. Query executes successfully and results are returned
### Screenshots
- ExeSQL db_type includes OceanBase
<img width="649" height="1015" alt="2"
src="https://github.com/user-attachments/assets/e0a5f7b9-e282-402a-8639-64c1aef8fce6"
/>
- ExeSQL test OceanBase connection
<img width="2247" height="1140" alt="test_ob"
src="https://github.com/user-attachments/assets/f16ebd93-b48e-4d18-b53f-8496581e755d"
/>
- Query results from OceanBase shown in UI
<img width="2550" height="1351" alt="1"
src="https://github.com/user-attachments/assets/b44163dc-baab-420d-b31e-b644bdcb77a9"
/>
Closes#12762
### What problem does this PR solve?
**Line break issue in Agent prompt editor:**
- Text with blank lines in `system_prompt` or `user_prompt` would have
extra/fewer blank lines after save/reload or paste
- Root cause: Mismatch between Lexical editor's paragraph nodes (`\n\n`
separator) and line break nodes (`\n` separator)
**Auto-save issue:**
- Changes were only saved after 20-second debounce, causing data loss on
page refresh before timer completed
### Solution
1. **Line break fix**: Use `LineBreakNode` consistently for all line
breaks (typing Enter, paste, load)
2. **Auto-save**: Save immediately when prompt editor loses focus
[1.webm](https://github.com/user-attachments/assets/eb2c2428-54a3-4d4e-8037-6cc34a859b83)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Fix wrong data rendered in task executor bar chart
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Closes#12803
### What problem does this PR solve?
The chat input textarea in the Chat UI (and Embed UI) has a fixed height
and cannot be resized, causing poor UX when users type messages longer
than 2 sentences. The input becomes cramped and difficult to read/edit.
**Root cause:** The `Textarea` component in
[NextMessageInput](cci:1://file:///ragflow/web/src/components/message-input/next.tsx:62:0-290:1)
had `resize-none` and `field-sizing-content` CSS classes that prevented
resizing, and the existing `autoSize` prop was not being utilized.
**Solution:**
- Removed `resize-none` and `field-sizing-content` classes
- Added `autoSize={{ minRows: 1, maxRows: 8 }}` to enable auto-expand
- Added `max-h-40` class to limit maximum height to 160px
The textarea now auto-expands from 1 to 8 rows as users type longer
messages.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
