### What problem does this PR solve?
Trivial fix log creation, follow on PR:
https://github.com/infiniflow/ragflow/pull/14136
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Resolve#14115 .
## Problem
On the shared chat link page (`/chats/share?shared_id=...`), querying
the knowledge base returns "no relevant information was found", while
the same query works correctly on the editor chat page.
## Root Cause
Knowledge base retrieval in `async_chat()` is gated by the check `if
"knowledge" in param_keys` (line 598), where `param_keys` is derived
from `prompt_config["parameters"]`. If `parameters` is empty or missing
the `{"key": "knowledge", "optional": false}` entry, retrieval is
entirely skipped.
This can happen because `_apply_prompt_defaults()` — which ensures
`parameters` contains the `knowledge` entry — is only called in the
`create` (POST) and `update_chat` (PUT) handlers, but **not** in
`patch_chat` (PATCH). If a chat's `prompt_config` was updated via PATCH
without including `parameters`, the `knowledge` entry would be absent.
Additionally, `prompt_config["parameters"]` would raise a `KeyError` if
the key was missing entirely.
## Fix
Added a defensive safety net in `async_chat()`
(`api/db/services/dialog_service.py`) that auto-injects the `knowledge`
parameter when:
- `dialog.kb_ids` is set (knowledge bases are configured)
- `"knowledge"` is not already in `param_keys`
- `{knowledge}` placeholder exists in the system prompt
Also changed `prompt_config["parameters"]` to
`prompt_config.get("parameters", [])` to prevent `KeyError` when the key
is absent.
## Files Changed
- `api/db/services/dialog_service.py` — added auto-injection of
`knowledge` parameter and safe `.get()` access for `parameters`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: noob <yixiao121314@outlook.com>
## What's the problem
Both `async_chat()` and `async_ask()` call `decorate_answer()` to build
the final SSE payload — it inserts citation markers (`##N$$`) into the
answer text and prunes `doc_aggs` to only the cited documents.
Immediately after, both functions overwrite `final["answer"]` with `""`:
```python
# async_chat(), line ~774 (issue #13828)
final = decorate_answer(thought + full_answer)
final["final"] = True
final["audio_binary"] = None
final["answer"] = "" # discards decorated text
yield final
# async_ask(), line ~1444 (same bug, different path)
final = decorate_answer(full_answer)
final["final"] = True
final["answer"] = "" # discards decorated text
yield final
```
The client receives filtered references (built for a citation-decorated
answer it never sees) while displaying the raw, undecorated streaming
text. Citations can never match.
## Root cause
`final["answer"] = ""` was left over from an earlier design where
clients were meant to reconstruct the full answer purely from delta
events. Once `decorate_answer()` started placing citation markers, this
blank-out broke the contract: the final event is where the decorated
answer should land.
## Fix
Remove the two blank-override lines — one in `async_chat()`, one in
`async_ask()`:
```diff
- final["answer"] = ""
```
`decorate_answer()` already sets `final["answer"]` to the correct
decorated string; there is nothing to override.
## Relation to #13828
Issue #13828 and PR #13835 identify the bug in `async_chat()`. This PR
absorbs that fix and also corrects the identical pattern in
`async_ask()` (used by the `/retrieval` route in `chat_api.py`), which
PR #13835 does not touch.
## Regression test
Added
`test/unit_test/api/db/services/test_dialog_service_final_answer.py`
with three tests:
| Test | Purpose |
|------|---------|
| `test_buggy_pattern_drops_answer` | Documents the old behaviour:
blank-override empties the final answer |
| `test_fixed_pattern_preserves_decorated_answer` | Core invariant:
final event carries the decorated text from `decorate_answer()` |
| `test_final_event_reference_matches_decorated_result` | Citation
markers in the answer must match the pruned `doc_aggs` in the same event
|
Local run result:
```
test_dialog_service_final_answer.py::test_buggy_pattern_drops_answer PASSED
test_dialog_service_final_answer.py::test_fixed_pattern_preserves_decorated_answer PASSED
test_dialog_service_final_answer.py::test_final_event_reference_matches_decorated_result PASSED
3 passed in 0.04s
```
`ruff check` passes with no issues on all changed files.
---------
Co-authored-by: edenfunf <edenfunf@gmail.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
## What problem does this PR solve?
Add a warning log when `get_flatted_meta_by_kbs` returns 10,000 results,
which indicates the query limit has been reached and metadata may be
silently truncated.
## Type of change
- [x] Improvement (non-breaking change which improves observability)
### What problem does this PR solve?
Fixes#14051.
The chat UI already sends an `internet` flag with each request, but the
backend previously triggered Tavily web retrieval whenever
`prompt_config.tavily_api_key` was configured. As a result, web search
could still run even when the internet toggle was off.
This PR makes web search an explicit opt-in at request time:
- `tavily_api_key` only indicates that web search is available
- Tavily retrieval runs only when `internet` is explicitly enabled
- the same behavior now applies to both the normal retrieval path and
the deep-research / reasoning path
This also fixes the no-KB fallback case so chats without KBs fall back
to normal solo chat when `internet` is off.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
As title
### Type of change
- [x] Refactoring
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Chores**
* Improved authentication error logging to better distinguish between
JWT and API token failures.
* Enhanced code documentation with clarifying comments for better
maintainability.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Feat: enable sync deleted files for connector
1. first comes with github
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added "sync deleted files" feature for data sources, enabling
automatic removal of files deleted from the source system.
* Added multilingual support for the new sync deleted files setting
across multiple languages.
* **UI Improvements**
* Improved checkbox form field rendering and layout.
* Enhanced full-width display for authentication token input fields.
### What problem does this PR solve?
Implements automatic adjustment of knowledge base chunk recall weights
based on user feedback (upvotes/downvotes). When users upvote or
downvote a response, the system locates the corresponding knowledge
snippets and adjusts their recall weight to improve future retrieval
quality.
**Closes #12670**
**How it works:**
1. User upvotes/downvotes a response via `POST /thumbup`
2. System extracts chunk IDs from the conversation reference
3. For each referenced chunk:
- Reads current `pagerank_fea` value from document store
- Increments (+1) for upvote or decrements (-1) for downvote
- Clamps weight to [0, 100] range
- Updates chunk in ES/Infinity/OceanBase
4. Future retrievals score these chunks higher/lower based on
accumulated feedback
**Files changed:**
- `api/db/services/chunk_feedback_service.py` - New service for updating
chunk pagerank weights
- `api/apps/conversation_app.py` - Integrated feedback service into
thumbup endpoint
- `test/testcases/test_web_api/test_chunk_feedback/` - Unit tests
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Chat message feedback now updates per-chunk relevance weights
(feature-flag gated), with configurable weighting and atomic updates
across storage backends.
* **Bug Fixes**
* Stricter validation for message feedback inputs and more robust
handling of feedback transitions.
* **Tests**
* Expanded test coverage for chunk-feedback behavior, weighting
strategies, storage backends, and thumb-flip scenarios.
* **Chores**
* CI workflow extended to run the new chunk-feedback web API tests.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: mkdev11 <YOUR_GITHUB_ID+MkDev11@users.noreply.github.com>
Co-authored-by: mkdev11 <MkDev11@users.noreply.github.com>
### What problem does this PR solve?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
---------
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
fixes issue #13799 where team members get model not authorized when
running RAG on an admin-shared knowledge base after the admin changes
the KB embedding model (for example to bge-m3).
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
1. Split dataset api to gateway and service, and modify web UI to use
restful http api.
2. Old KB releated APIs are commented.
### Type of change
- [x] Refactoring
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Fixes [#13505](https://github.com/infiniflow/ragflow/issues/13505): Jira
incremental sync could miss updated issues after initial sync,
especially near time boundaries.
Root cause:
- Jira JQL uses minute-level precision for `updated` filters.
- Incremental windows had no overlap buffer, so boundary updates could
be skipped.
- Sync log cursor tracking used a backward-facing update for
`poll_range_start`.
- Existing-doc updates in `upload_document` lacked a KB ownership guard
for doc-id collisions.
What changed:
- Added Jira incremental overlap buffer (`time_buffer_seconds`,
defaulting to `JIRA_SYNC_TIME_BUFFER_SECONDS`) when building JQL
lower-bound time.
- Preserved second-level post-filtering to avoid duplicate reprocessing
while still catching boundary updates.
- Improved Jira sync logging to include start/end window and overlap
configuration.
- Updated sync cursor tracking in `increase_docs` to keep
`poll_range_start` moving forward with max update time.
- Added KB ID safety check before updating existing document records in
`upload_document`.
Verification performed:
- Python syntax compile checks passed for modified files.
- Manual verification flow:
1. Run full Jira sync.
2. Edit an already-indexed Jira issue.
3. Run next incremental sync.
4. Confirm updated content is re-ingested into KB.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
### What problem does this PR solve?
Feat: Export Agent Logs.
### 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?
1. Split dataset api to gateway and service, and modify web UI to use
restful http api.
2. Old KB releated APIs are commented.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
1. Split dataset api to gateway and service, and modify web UI to use
restful http api.
2. Old KB releated APIs are commented.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Fix: model selecton rule in get_model_config_by_type_and_name
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Modify the style of the release confirmation box.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: balibabu <assassin_cike@163.com>
Co-authored-by: 6ba3i <isbaaoui09@gmail.com>
### What problem does this PR solve?
Fixes#13285
When an LLM returns a transient error (e.g. overloaded) during parsing,
the task progress is set to -1. Previously, the progress could never be
updated again, leaving the document permanently stuck in FAIL status
even after the task successfully recovered and completed.
Three coordinated changes address this:
1. task_service.update_progress: relax the progress update guard to
accept prog >= 1 even when current progress is -1, so a task that
recovers from a transient failure can report completion.
2. document_service.get_unfinished_docs: include documents that are
marked FAIL (progress == -1) but still have at least one non-failed task
(task.progress >= 0) in the polling set, so their status can be
re-synced once a task recovers. Documents where all tasks have
permanently failed are excluded to avoid unnecessary polling.
3. document_service.update_progress: explicitly set document status to
RUNNING when not all tasks have finished, instead of preserving whatever
stale status (potentially FAIL) the document previously had.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
Fix knowledge-base chat retrieval when no individual document IDs are
selected.
## Root Cause
`async_chat()` initialized `doc_ids` as an empty list when the request
did not explicitly select documents. That empty list was then forwarded
into retrieval as an active `doc_id` filter, effectively becoming
`doc_id IN []` and suppressing all chunk matches.
## Changes
- treat missing selected document IDs as `None` instead of `[]`
- keep explicit document filtering when IDs are actually provided
- add regression coverage for the shared chat retrieval path
## Validation
- `python3 -m py_compile api/db/services/dialog_service.py
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py`
- `.venv/bin/python -m pytest
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py`
- manually verified that chat completions again inject retrieved
knowledge into the prompt
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Add delete all support for delete operations.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
---------
Co-authored-by: writinwaters <cai.keith@gmail.com>
### What problem does this PR solve?
Fix https://github.com/infiniflow/ragflow/issues/13388
Call get_flatted_meta_by_kbs in dify retrieval. Remove get_meta_by_kbs.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
- scope normal document-list metadata lookups to the current page's
document IDs
- keep the `return_empty_metadata=True` path dataset-wide because it
needs full knowledge of docs that already have metadata
- add unit tests for both paged listing paths and the unchanged
empty-metadata behavior
## Why
`DocumentService.get_list()` and the normal `get_by_kb_id()` path were
calling `DocMetadataService.get_metadata_for_documents(None, kb_id)`,
which loads metadata for the entire dataset on every page request.
That becomes especially problematic on large datasets. The metadata scan
path paginates through the full metadata index without an explicit sort,
while the ES helper only switches to `search_after` beyond `10000`
results when a sort is present. In practice this can lead to unnecessary
full-dataset metadata work, slower document-list loading, and unreliable
`meta_fields` in list responses for large KBs.
This change keeps the existing empty-metadata filter behavior intact,
but scopes normal list responses to metadata for the current page only.
### What problem does this PR solve?
Support getting aggregated parsing status to dataset via the API
Issue: #12810
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: heyang.why <heyang.why@alibaba-inc.com>
### What problem does this PR solve?
Feat: Display release status in agent version history.
### 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?
Avoid getting doc in function delete_document_metadata as the doc might
have been removed.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Closes: #12889
### What problem does this PR solve?
When syncing external data sources (e.g., Jira, Confluence, Google
Drive), updated documents were not being re-chunked. The raw content was
correctly updated in blob storage, but the vector database retained
stale chunks, causing search results to return outdated information.
**Root cause:** The task digest used for chunk reuse optimization was
calculated only from parser configuration fields (`parser_id`,
`parser_config`, `kb_id`, etc.), without any content-dependent fields.
When a document's content changed but the parser configuration remained
the same, the system incorrectly reused old chunks instead of
regenerating new ones.
**Example scenario:**
1. User syncs a Jira issue: "Meeting scheduled for Monday"
2. User updates the Jira issue to: "Meeting rescheduled to Friday"
3. User triggers sync again
4. Raw content panel shows updated text ✓
5. Chunk panel still shows old text "Monday" ✗
**Solution:**
1. Include `update_time` and `size` in the chunking config, so the task
digest changes when document content is updated
2. Track updated documents separately in `upload_document()` and return
them for processing
3. Process updated documents through the re-parsing pipeline to
regenerate chunks
[1.webm](https://github.com/user-attachments/assets/d21d4dcd-e189-4d39-8700-053bae0ca5a0)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Add id for table tenant_llm and apply in LLMBundle.
### Type of change
- [x] Refactoring
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Feat: published agent version control
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR aims to:
1. Enable file uploads for the public API, similarly to what
/document/upload_info accomplishes for the frontend;
2. Enable files sent to the /chat/:chat_id/completions endpoint to be
used within the conversation.
We classify the first item as a new future, while classifying the second
one as a bug fix.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
*The work related to this PR was co-authored by*
[Bruno Ferreira](https://github.com/brunopferreira): Custom Solutions
Manager @ [Orbcom](https://orbcom.pt/)
[Pedro Ferreira](https://github.com/sirj0k3r): Lead Software Developer @
[Orbcom](https://orbcom.pt/)
[Pedro Cardoso](https://github.com/pedromiguel4560): Associate Software
Developer @ [Orbcom](https://orbcom.pt/)
*This PR replaces #13248*
---------
Co-authored-by: Pedro Cardoso <pedrocardoso@orbcom.pt>
Co-authored-by: Pedro Ferreira <pedroferreira@orbcom.pt>
### What problem does this PR solve?
this pr adds new tests, for the full configuration tab in datasests
### Type of change
- [x] Other (please describe): new tests
### Issue: #12756
### What problem does this PR solve?
When users upload files through Agent's Begin or Await Response
components, the parsing is hardcoded to "Plain Text", ignoring all other
available parsers (DeepDOC, TCADP, Docling, MinerU, PaddleOCR). This PR
adds a PDF parser dropdown to these components so users can select the
appropriate parser for their file inputs.
### Changes
**Backend**
- `agent/component/fillup.py` - Added `layout_recognize` param to
`UserFillUpParam`, forwarded to `FileService.get_files()`
- `agent/component/begin.py` - Same forwarding in `Begin._invoke()`
- `agent/canvas.py` - Extract Begin's `layout_recognize` for `sys.files`
parsing, added param to `get_files_async()` / `get_files()`
- `api/db/services/file_service.py` - Added `layout_recognize` param to
`parse()` and `get_files()`, replacing hardcoded `"Plain Text"`
- `rag/app/naive.py` - Added `"plain text"` and `"tcadp parser"` aliases
to PARSERS dict to match dropdown values after `.lower()`
**Frontend**
- `web/src/pages/agent/form/begin-form/index.tsx` - Show
`LayoutRecognizeFormField` dropdown when file inputs exist
- `web/src/pages/agent/form/begin-form/schema.ts` - Added
`layout_recognize` to Zod schema
- `web/src/pages/agent/form/user-fill-up-form/index.tsx` - Same dropdown
for Await Response component
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR adds comprehensive **Right-to-Left (RTL) language support**,
primarily targeting Arabic and other RTL scripts (Hebrew, Persian, Urdu,
etc.).
Previously, RTL content had multiple rendering issues:
- Incorrect sentence splitting for Arabic punctuation in citation logic
- Misaligned text in chat messages and markdown components
- Improper positioning of blockquotes and “think” sections
- Incorrect table alignment
- Citation placement ambiguity in RTL prompts
- UI layout inconsistencies when mixing LTR and RTL text
This PR introduces backend and frontend improvements to properly detect,
render, and style RTL content while preserving existing LTR behavior.
#### Backend
- Updated sentence boundary regex in `rag/nlp/search.py` to include
Arabic punctuation:
- `،` (comma)
- `؛` (semicolon)
- `؟` (question mark)
- `۔` (Arabic full stop)
- Ensures citation insertion works correctly in RTL sentences.
- Updated citation prompt instructions to clarify citation placement
rules for RTL languages.
#### Frontend
- Introduced a new utility: `text-direction.ts`
- Detects text direction based on Unicode ranges.
- Supports Arabic, Hebrew, Syriac, Thaana, and related scripts.
- Provides `getDirAttribute()` for automatic `dir` assignment.
- Applied dynamic `dir` attributes across:
- Markdown rendering
- Chat messages
- Search results
- Tables
- Hover cards and reference popovers
- Added proper RTL styling in LESS:
- Text alignment adjustments
- Blockquote border flipping
- Section indentation correction
- Table direction switching
- Use of `<bdi>` for figure labels to prevent bidirectional conflicts
#### DevOps / Environment
- Added Windows backend launch script with retry handling.
- Updated dependency metadata.
- Adjusted development-only React debugging behavior.
---
### Type of change
- [x] Bug Fix (non-breaking change which fixes RTL rendering and
citation issues)
- [x] New Feature (non-breaking change which adds RTL detection and
dynamic direction handling)
---------
Co-authored-by: 6ba3i <isbaaoui09@gmail.com>
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
Co-authored-by: Ahmad Intisar <168020872+ahmadintisar@users.noreply.github.com>
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Fix [#13210](https://github.com/infiniflow/ragflow/issues/13210)
Remove limit in _search_metadata, use pagination in _search_metadata.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fixes AttributeError in _remove_reasoning_content() when LLM returns
None, and improves JSON parsing regex for markdown code fences in
agent_with_tools.py
