### What problem does this PR solve?
Skip duplicate errors to avoid 'create_idx' failures caused by slow
metadata refresh or external modifications.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes Infinity-specific API regressions: preserves ```important_kwd```
round‑trip for ```[""]```, restores required highlight key in retrieval
responses, and enforces Infinity guards for unsupported
```parser_id=tag``` and pagerank in ```/v1/kb/update```. Also removes a
slow/buggy pandas row-wise apply that was throwing ```ValueError``` and
causing flakiness.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Problem
The \`important_kwd\` field in Infinity connector was using mismatched
separators:
- **Storage**: \`list2str(v)\` uses space as default separator
- **Reading**: \`v.split()\` splits by all whitespace
This causes multi-word keywords like \`\"Senior Fund Manager\"\` to be
incorrectly split into \`[\"Senior\", \"Fund\", \"Manager\"]\`.
## Solution
Use comma \`,\` as separator for both storing and reading, consistent
with:
1. The LLM output format in \`keyword_prompt.md\` (\"delimited by
ENGLISH COMMA\")
2. The \`cached.split(\",\")\` in \`task_executor.py\`
## Changes
- \`insert()\`: \`list2str(v)\` → \`list2str(v, \",\")\`
- \`update()\`: \`list2str(v)\` → \`list2str(v, \",\")\`
- \`get_fields()\`: \`v.split()\` → \`v.split(\",\") if v else []\`
## Impact
This bug affects:
- Python-level reranking weight calculation (\`important_kwd * 5\`)
- API response keyword display
- Search precision due to fragmented keywords
## Summary
Fixes#12520 - Deleted chunks should not appear in retrieval/reference
results.
## Changes
### Core Fix
- **api/apps/chunk_app.py**: Include \doc_id\ in delete condition to
properly scope the delete operation
### Improved Error Handling
- **api/db/services/document_service.py**: Better separation of concerns
with individual try-catch blocks and proper logging for each cleanup
operation
### Doc Store Updates
- **rag/utils/es_conn.py**: Updated delete query construction to support
compound conditions
- **rag/utils/opensearch_conn.py**: Same updates for OpenSearch
compatibility
### Tests
- **test/testcases/.../test_retrieval_chunks.py**: Added
\TestDeletedChunksNotRetrievable\ class with regression tests
- **test/unit/test_delete_query_construction.py**: Unit tests for delete
query construction
## Testing
- Added regression tests that verify deleted chunks are not returned by
retrieval API
- Tests cover single chunk deletion and batch deletion scenarios
### What problem does this PR solve?
Fix regex pattern validation in split_with_pattern (#12605)
- Add try-except block to validate user-provided regex patterns before
use
- Gracefully fallback to single chunk when invalid regex is provided
- Prevent server crash during DOCX parsing with malformed delimiters
## Problem
Parsing DOCX files with custom regex delimiters crashes with `re.error:
nothing to repeat at position 9` when users provide invalid regex
patterns.
Closes#12605
## Solution
Validate and compile regex pattern before use. On invalid pattern, log
warning and return content as single chunk instead of crashing.
## Changes
- `rag/nlp/__init__.py`: Add regex validation in `split_with_pattern()`
function
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=42954461
### What problem does this PR solve?
Feat: Hash doc id to avoid duplicate name.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fixes#12604 - DOCX files containing hyperlinks to internal bookmarks
(e.g., `#_文档目录`) cause a `KeyError` during parsing:
```
KeyError: "There is no item named 'word/#_文档目录' in the archive"
```
This happens because python-docx incorrectly tries to read internal
bookmark references as files from the ZIP archive. Internal bookmarks
are relationship targets starting with `#` and are not actual files.
This PR extends the existing `load_from_xml_v2` workaround (which
already handles `NULL` targets) to also skip relationship targets
starting with `#`.
Related upstream issue:
https://github.com/python-openxml/python-docx/issues/902
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---
Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=94194147
### Issue
When using Qwen3 models (`qwen3-32b`, `qwen3-max`) through the
Tongyi-Qianwen provider for non-streaming calls (e.g., knowledge graph
generation), the API fails with:
Closes#12424
```
parameter.enable_thinking must be set to false for non-streaming calls
```
### Root Cause
In `LiteLLMBase.async_chat()`, the `extra_body={"enable_thinking":
False}` was set in `kwargs` but never forwarded to
`_construct_completion_args()`.
### What problem does this PR solve?
Pass merged kwargs to `_construct_completion_args()` using
`**{**gen_conf, **kwargs}` to safely handle potential duplicate
parameters.
### Changes
- `rag/llm/chat_model.py`: Forward kwargs containing `extra_body` to
`_construct_completion_args()` in `async_chat()`
_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] Bug Fix (non-breaking change which fixes an issue)
Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=42954461
### What problem does this PR solve?
This PR eliminates unnecessary debug print statements that were left in
hot paths of the codebase.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
When there are multiple users, parsing a document for a new user can
trigger the reuse of column objects, leading to the error
`sqlalchemy.exc.ArgumentError: Column object 'id' already assigned to
Table xxx`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix image not displaying thumbnails when using pipeline.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
1. PaddleOCR PDF parser supports thumnails and positions.
2. Add FAQ documentation for PaddleOCR PDF parser.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
- API server
- Ingestion server
- Data sync server
- Admin server
### Type of change
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Add PaddleOCR as a new PDF parser.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
If we delete the password in kwargs, func 'init_db_config' will fail, so
we need to keep this field.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: support context window for docx
#12303
Done:
- [x] naive.py
- [x] one.py
TODO:
- [ ] book.py
- [ ] manual.py
Fix: incorrect image position
Fix: incorrect chunk type tag
### 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?
- Fixes the health check failure in multi-bucket MinIO environments.
Previously, health checks would fail because the default
"ragflow-bucket" did not exist. This caused false negatives for system
health.
- Also removes the _health_check write in single-bucket mode to avoid
side effects (minor optimization).
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Refactor TOC building logic to use enumerate instead of while loop, add
comprehensive error handling for missing/invalid chunk_id values, and
improve logging with more specific error messages. The changes make the
code more robust against malformed TOC data while maintaining the same
functionality for valid inputs.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
PDF vision figure parser supports reading context.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Improve task executor heartbeat handling and cleanup.
### What problem does this PR solve?
- **Reduce lock contention during executor cleanup**: The cleanup lock
is acquired only when removing expired executors, not during regular
heartbeat reporting, reducing potential lock contention.
- **Optimize own heartbeat cleanup**: Each executor removes its own
expired heartbeat using `zremrangebyscore` instead of `zcount` +
`zpopmin`, reducing Redis operations and improving efficiency.
- **Improve cleanup of other executors' heartbeats**: Expired executors
are detected by checking their latest heartbeat, and stale entries are
removed safely.
- **Other improvements**: IP address and PID are captured once at
startup, and unnecessary global declarations are removed.
### Type of change
- [x] Performance Improvement
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Eliminates SQL injection vectors in the OpenDAL MySQL initialization
logic by implementing strict input validation and explicit type casting.
**Modifications:**
1. **`init_db_config`**: Enforced integer casting for
`max_allowed_packet` before formatting it into the SQL string.
2. **`init_opendal_mysql_table`**: Implemented regex-based validation
for `table_name` to ensure only alphanumeric characters and underscores
are permitted, preventing arbitrary SQL command injection through
configuration parameters.
These changes ensure that even if configuration values are sourced from
untrusted environments, the database initialization remains secure.
### What problem does this PR solve?
Feat: Bitbucket connector NOT READY TO MERGE
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
issue:
#12313
change:
add Zendesk data source integration with configuration and sync
capabilities
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
- Simplified and consolidated extraction rules
- Emphasized strict evidence-based extraction only
- Strengthened enum handling and hallucination prevention
- Clarified output requirements for empty results
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
issue:
#12217 [#12313](https://github.com/infiniflow/ragflow/issues/12313)
change:
add IMAP data source integration with configuration and sync
capabilities
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Use async task to save memory.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Feat: Gitlab connector
Fix: submit button in darkmode
### 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?
change: Add Asana data source integration and configuration options
### 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?
Improve image table context.
Current strategy in attach_media_context:
- Order by position when possible: if any chunk has page/position info,
sort by (page, top, left), otherwise keep original order.
- Apply only to media chunks: images use image_context_size, tables use
table_context_size.
- Primary matching: on the same page, choose a text chunk whose vertical
span overlaps the media, then pick the one with the closest vertical
midpoint.
- Fallback matching: if no overlap on that page, choose the nearest text
chunk on the same page (page-head uses the next text; page-tail uses the
previous text).
- Context extraction: inside the chosen text chunk, find a mid-sentence
boundary near the text midpoint, then take context_size tokens split
before/after (total budget).
- No multi-chunk stitching: context comes from a single text chunk to
avoid mixing unrelated segments.
### Type of change
- [x] Refactoring
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Manage message and use in agent.
Issue #4213
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
