### 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?
Correct metadata update behavior. #11912
When update `value` is omitted, the corresponding keys are updated to
`"value"` regardless of their current values.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### 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)
## Overview
This PR adds support for **Single Bucket Mode** in RAGFlow, allowing
users to configure MinIO/S3 to use a single bucket with a directory
structure instead of creating multiple buckets per Knowledge Base and
user folder.
## Problem Statement
The current implementation creates one bucket per Knowledge Base and one
bucket per user folder, which can be problematic when:
- Cloud providers charge per bucket
- IAM policies restrict bucket creation
- Organizations want centralized data management in a single bucket
## Solution
Added a `prefix_path` configuration option to the MinIO connector that
enables:
- Using a single bucket with directory-based organization
- Backward compatibility with existing multi-bucket deployments
- Support for MinIO, AWS S3, and other S3-compatible storage backends
## Changes
- **`rag/utils/minio_conn.py`**: Enhanced MinIO connector to support
single bucket mode with prefix paths
- **`conf/service_conf.yaml`**: Added new configuration options
(`bucket` and `prefix_path`)
- **`docker/service_conf.yaml.template`**: Updated template with single
bucket configuration examples
- **`docker/.env.single-bucket-example`**: Added example environment
variables for single bucket setup
- **`docs/single-bucket-mode.md`**: Comprehensive documentation covering
usage, migration, and troubleshooting
## Configuration Example
```yaml
minio:
user: "access-key"
password: "secret-key"
host: "minio.example.com:443"
bucket: "ragflow-bucket" # Single bucket name
prefix_path: "ragflow" # Optional prefix path
```
## Backward Compatibility
✅ Fully backward compatible - existing deployments continue to work
without any changes
- If `bucket` is not configured, uses default multi-bucket behavior
- If `bucket` is configured without `prefix_path`, uses bucket root
- If both are configured, uses `bucket/prefix_path/` structure
## Testing
- Tested with MinIO (local and cloud)
- Verified backward compatibility with existing multi-bucket mode
- Validated IAM policy restrictions work correctly
## Documentation
Included comprehensive documentation in `docs/single-bucket-mode.md`
covering:
- Configuration examples
- Migration guide from multi-bucket to single-bucket mode
- IAM policy examples
- Troubleshooting guide
---
**Related Issue**: Addresses use cases where bucket creation is
restricted or costly
### What problem does this PR solve?
Feat: Add mineru as a model manufacturer to the system. #10621
### 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 DeepseekV3.2 of Tongyi-Qianwen and remove unused code
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
change：
async issue and sensitive logging
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Retrieval metadata filtering adds semi-automatic mode, and users can
manually check the metadata key that participates in LLM to generate
filter conditions.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR fixes a startup crash in the data_sync_0 service caused by an
incorrect asyncio.run call. The main coroutine was being passed as a
function reference instead of being invoked, which raised:
`ValueError: a coroutine was expected, got <function main ...>
`
What I changed
- Updated the entrypoint in sync_data_source.py to correctly invoke the
coroutine with `asyncio.run(main())`.
Testing
- No tested.
Related Issue
Fixes https://github.com/infiniflow/ragflow/issues/11878
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
MinerU new version supports for the new backend
vlm-mlx-engine，https://github.com/opendatalab/MinerU .
### Type of change
- [ x ] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add metadata condition in document list.
Add metadata bulk update.
Add metadata summary.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
Fix RuntimeError when calling mindmap endpoint by converting
`gen_mindmap()` to async function and using `await` instead of
`asyncio.run()`.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Feat: Add configuration for webhook to the begin node. #10427
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Enhance OBConnection.search for better performance. Main changes:
1. Use string type of vector array in distance func for better parsing
performance.
2. Manually set max_connections as pool size instead of using default
value.
3. Set 'fulltext_search_columns' when starting.
4. Cache the results of the table existence check (we will never drop
the table).
5. Remove unused 'group_results' logic.
6. Add the `USE_FULLTEXT_FIRST_FUSION_SEARCH` flag, and the
corresponding fusion search SQL when it's false.
### Type of change
- [x] Performance Improvement
### What problem does this PR solve?
Fix:Modify the name of the Overlapped percent field
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Manage and display memory datasets.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The docker version(24.0.7) installed in the executor manager image is
incompatible with the latest stable docker (29.1.3). The minmum api
v29.1.3 can use is 1.4.4 api version, but 24.0.7 uses api version 1.4.3.
### Type of change
- [X] Other (please describe):
This could break things for people who still have an old docker
installed on their system. A better approach could be a setting to share
### What problem does this PR solve?
Fix: duplicate output by async_chat_streamly
Refact: revert manual modification
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Treat MinerU as an OCR model.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
Fix: The variables in the message node are not displaying correctly.
#11839
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Add complete Italian translation file with all UI sections
- Register Italian in LanguageAbbreviation enum and language maps
- Configure Italian translation in i18n config
- Add Italiano to language selector dropdown
### Type of change
- [x] Other (please describe):
## What
Added complete Italian language translation support to RAGFlow
## Changes
- Added comprehensive Italian translation file
([it.ts](ragflow/web/src/locales/it.ts:0:0-0:0)) with all UI sections
(1239 lines)
- Registered Italian in `LanguageAbbreviation` enum and all language
maps
- Configured Italian translation in i18n configuration
- Added "Italiano" to language selector dropdown
## Impact
- Italian users can now use RAGFlow in their native language
- All major UI components are translated including:
- Login/registration screens
- Knowledge base management
- Chat interface
- Settings and configuration
- Admin console
- Error messages and notifications
## Testing
- Verified all translation keys are present
- Confirmed language selector shows "Italiano" correctly
- Tested that no translation keys are missing
- All UI sections properly translated
Co-authored-by: PentaFrame <info@pentaframe.it>
## What changes were proposed in this pull request?
Added a return statement after the successful completion of the async
for loop in async_chat_streamly.
## Why are the changes needed?
Previously, the code lacked a break/return mechanism inside the try
block. This caused the retry loop (for attempt in range...) to continue
executing even after the LLM response was successfully generated and
yielded, resulting in duplicate requests (up to max_retries times).
## Does this PR introduce any user-facing change?
No (it fixes an internal logic bug).
### What problem does this PR solve?
Feature: Memory interface integration testing
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Migrate CV model chat to Async. #11750
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
## What's changed
fix: unify embedding model fallback logic for both TEI and non-TEI
Docker deployments
> This fix targets **Docker / `docker-compose` deployments**, ensuring a
valid default embedding model is always set—regardless of the compose
profile used.
## Changes
| Scenario | New Behavior |
|--------|--------------|
| **Non-`tei-` profile** (e.g., default deployment) | `EMBEDDING_MDL` is
now correctly initialized from `EMBEDDING_CFG` (derived from
`user_default_llm`), ensuring custom defaults like `bge-m3@Ollama` are
properly applied to new tenants. |
| **`tei-` profile** (`COMPOSE_PROFILES` contains `tei-`) | Still
respects the `TEI_MODEL` environment variable. If unset, falls back to
`EMBEDDING_CFG`. Only when both are empty does it use the built-in
default (`BAAI/bge-small-en-v1.5`), preventing an empty embedding model.
|
## Why This Change?
- **In non-TEI mode**: The previous logic would reset `EMBEDDING_MDL` to
an empty string, causing pre-configured defaults (e.g., `bge-m3@Ollama`
in the Docker image) to be ignored—leading to tenant initialization
failures or silent misconfigurations.
- **In TEI mode**: Users need the ability to override the model via
`TEI_MODEL`, but without a safe fallback, missing configuration could
break the system. The new logic adopts a **“config-first,
env-var-override”** strategy for robustness in containerized
environments.
## Implementation
- Updated the assignment logic for `EMBEDDING_MDL` in
`rag/common/settings.py` to follow a unified fallback chain:
EMBEDDING_CFG → TEI_MODEL (if tei- profile active) → built-in default
## Testing
Verified in Docker deployments:
1. **`COMPOSE_PROFILES=`** (no TEI)
→ New tenants get `bge-m3@Ollama` as the default embedding model
2. **`COMPOSE_PROFILES=tei-gpu` with no `TEI_MODEL` set**
→ Falls back to `BAAI/bge-small-en-v1.5`
3. **`COMPOSE_PROFILES=tei-gpu` with `TEI_MODEL=my-model`**
→ New tenants use `my-model` as the embedding model
Closes#8916fix#11522fix#11306
### What problem does this PR solve?
Our HTTP wrapper still passed proxies to httpx.Client/AsyncClient, which
expect proxy. As a result, configured proxies were ignored and calls
could fail with ValueError("Failed to fetch OIDC metadata:
Client.__init__() got an unexpected keyword argument 'proxies'"). This
PR switches to the correct proxy kwarg so proxies are honored and the
runtime error is resolved.
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
---
Contribution during my time at RAGcon GmbH.
### What problem does this PR solve?
Fix: Changed 'HightLightMarkdown' to 'HighLightMarkdown', and replaced
the private component with a public component.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Default start admin when start with docker-compose.yml
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
This commit resolves an incorrect import path for `ToastProps` and
`ToastActionElement` types within the `use-toast.tsx` hook.
The current path, `@/registry/default/ui/toast`, does not reflect the
actual file location in this repository.
The import in `src/components/hooks/use-toast.tsx` has been updated from
`@/registry/default/ui/toast` to the correct alias path:
`@/components/ui/toast`.
This ensures the types are resolved correctly and the codebase remains
clean and functional.
### What problem does this PR solve?
Features: Memory page rendering and other bug fixes
- Rendering of the Memory list page
- Rendering of the message list page in Memory
- Fixed an issue where the empty state was incorrectly displayed when
search criteria were applied
- Added a web link for the API-Key
- modifying the index_mode attribute of the Confluence data source.
### 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?
When a script has a block like this at the top, then uv run
download_deps.py ignores the [project].dependencies in pyproject.toml
and only uses that dependencies = [...] list.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Cleanup synchronous functions in chat_model and implement
synchronization for conversation and dialog chats.
### Type of change
- [x] Refactoring
- [x] Performance Improvement
### What problem does this PR solve?
- typos
- IDE warnings
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
