### 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?
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: 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)
## 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?
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?
Fix: Fixed the error on the login page.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Add a web search button to the chat box on the chat page.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: The minimum size of the historical message window for the
classification operator is 1. #12778
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Allow classification operators to be followed by other
classification operators. #9082
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Add a think button to the chat box. #12742
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
```
$ python admin/client/ragflow_cli.py -t user -u aaa@aaa.com -p 9380
ragflow> list datasets;
ragflow> list default models;
ragflow> show version;
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit fixes multiple issues preventing PDF Generator (Docs
Generator) output variables from being visible in the Output section and
available to downstream nodes.
### What problem does this PR solve?
Issues Fixed:
1. PDF Generator nodes initialized with empty object instead of proper
initial values
2. Output structure mismatch (had 'value' property that system doesn't
expect)
3. Missing 'download' output in form schema
4. Output list computed from static values instead of form state
5. Added null/undefined guard to transferOutputs function
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Changes:
- web/src/pages/agent/constant/index.tsx: Fixed output structure in
initialPDFGeneratorValues
- web/src/pages/agent/hooks/use-add-node.ts: Initialize PDF Generator
with proper values
- web/src/pages/agent/form/pdf-generator-form/index.tsx: Fixed schema
and use form.watch
- web/src/pages/agent/form/components/output.tsx: Added null guard and
spacing
### What problem does this PR solve?
Fix: In the agent loop, if the await response is selected as the
variable, the operator cannot be selected. #12656
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Editing the agent greeting causes the greeting to be continuously
added to the message list. #12635
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: Unable to copy category node. #12607
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Exported Agent JSON Should Include Conversation Variables
Configuration #11796
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Refactor: UmiJs -> Vite+React
### Type of change
- [x] Refactoring
---------
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Feat: Fixed the issue where the newly created agent begin node displayed
"undefined". #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display mode at the begin node #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Remove the code that outputs jsonschema from the webhook.#10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display the selected list of memories in the retrieval node. #4213
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: The agent can only retrieve content from the knowledge base or
memory. #4213
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix several text issues.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Feat: Hide the autoplay switch for message operators in webhook mode.
#10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Dragging down a downstream node of a Switch operator will cause the
end_cpn_ids to contain the ID of the placeholder operator. #12177
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add image table context to pipeline splitter.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Support Markdown Rendering for tips in user-fill-up Component
#11825
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add optional chaining operators to prevent runtime errors when formData
is undefined or null in useShowWebhookResponseStatus hook.
This fixes a potential crash when accessing mode and execution_mode
properties before formData is initialized or when the Begin node doesn't
exist in the graph.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Claude <noreply@anthropic.com>
### What problem does this PR solve?
Fix incorrect prompt texts in **Agent** canvas > **Transformer** >
**Result destination: Table of contents**
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Translate the text of the webhook debugging interface. #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: balibabu <assassin_cike@163.com>
### What problem does this PR solve?
Feat: Add memory multi-select dropdown to recall and message operator
forms. #4213
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Hide part of the message field in webhook mode #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: balibabu <assassin_cike@163.com>
### What problem does this PR solve?
Images that appear consecutively in the dialogue are displayed using a
carousel. #12076
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: When the webhook returns a field in streaming format, the message
displays the status field. #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: balibabu <assassin_cike@163.com>
### What problem does this PR solve?
Add support for multiple Retrieval tools under an agent
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Display error messages from intermediate nodes. #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Remove HMAC from the webhook #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add TOC (Table of contents) option in Ingestion Pipeline canvas >
Transformer node
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add children delimiters for Ingestion pipeline config
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### PR details
feat: Add Excel export support and fix variable reference regex
Changes:
- Add Excel export output format option to Message component
- Apply nest_asyncio patch to handle nested event loops
- Fix async generator iteration in canvas_app.py debug endpoint
- Add underscore support in variable reference regex pattern
### What problem does this PR solve?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Shivam Johri <shivamjohri@Shivams-MacBook-Air.local>
### What problem does this PR solve?
- Change the message format from 'key: value' to 'name: value' when user
submits the fillup form in agent chat.
- This resolves#11865
- I think this change makes sense, better aligning the form and the
replied message.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Set the return value of the webhook to a string. #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Displaying the file option in the webhook's request body #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR introduces a new Docs Generator agent component for producing
downloadable PDF, DOCX, or TXT files from Markdown content generated
within a RAGFlow workflow.
### **Key Features**
**Backend**
- New component: DocsGenerator (agent/component/docs_generator.py)
-
- Markdown → PDF/DOCX/TXT conversion
-
- Supports tables, lists, code blocks, headings, and rich formatting
-
- Configurable document style (fonts, margins, colors, page size,
orientation)
-
- Optional header logo and footer with page numbers/timestamps
-
**Frontend**
- New configuration UI for the Docs Generator
-
- Download button integrated into the chat interface
-
- Output wired to the Message component
-
- Full i18n support
**Documentation**
Added component guide:
docs/guides/agent/agent_component_reference/docs_generator.md
**Usage**
Add the Docs Generator to a workflow, connect Markdown output from an
upstream component, configure metadata/style, and feed its output into
the Message component. Users will see a document download button
directly in the chat.
**Contributor Note**
We have been following RAGFlow since more than a year and half now and
have worked extensively on personalizing the framework and integrating
it into several of our internal systems. Over the past year and a half,
we have built multiple platforms that rely on RAGFlow as a core
component, which has given us a strong appreciation for how flexible and
powerful the project is.
We also previously contributed the full Italian translation, and we were
glad to see it accepted. This new Docs Generator component was created
for our own production needs, and we believe that it may be useful for
many others in the community as well.
We want to sincerely thank the entire RAGFlow team for the remarkable
work you have done and continue to do. If there are opportunities to
contribute further, we would be glad to help whenever we have time
available. It would be a pleasure to support the project in any way we
can.
If appropriate, we would be glad to be listed among the project’s
contributors, but in any case we look forward to continuing to support
and contribute to the project.
PentaFrame Development Team
---------
Co-authored-by: PentaFrame <info@pentaframe.it>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Feat: Flatten the request schema of the webhook #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
