## Summary
- Replace hardcoded CST (UTC+8) expected values in `test_time_utils.py`
with dynamically computed local-time expectations using
`time.localtime()` and `time.mktime()`
- Tests previously failed in any timezone other than UTC+8; they now
pass regardless of the system's local timezone
## Test plan
- [x] `uv run pytest test/unit_test/ -v` — 317 passed, 25 skipped
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Jim Smith <jhsmith0@me.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Problem
RAGFlow was using incorrect model names for Google Gemini embeddings:
- `embedding-001` (missing `gemini-` prefix)
- `text-embedding-004` (OpenAI model name, not Gemini)
This caused API errors when users tried to use Gemini embeddings.
## Solution
- Updated `conf/llm_factories.json` to use the correct model name:
`gemini-embedding-001`
- Removed the incorrect `text-embedding-004` entry
- Added volume mount in `docker-compose.yml` to ensure config changes
persist
## Testing
Tested with a valid Gemini API key and confirmed embeddings now work
correctly.
## Changes
- Modified `conf/llm_factories.json`
- Modified `docker/docker-compose.yml`
---------
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
- Update version tags in README files (including translations) from
v0.23.1 to v0.24.0
- Modify Docker image references and documentation to reflect new
version
- Update version badges and image descriptions
- Maintain consistency across all language variants of README files
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
Judge table created with current infinity mapping before migrate db.
#13089
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
When match_expressions contains coroutine objects (from GraphRAG's
Dealer.get_vector()), the code cannot identify this type because it only
checks for MatchTextExpr, MatchDenseExpr, or FusionExpr.
As a result:
score_func remains initialized as an empty string ""
This empty string is appended to the output list
The output list is passed to Infinity SDK's table_instance.output()
method
Infinity's SQL parser (via sqlglot) fails to parse the empty string,
throwing a ParseError
### 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>
### What problem does this PR solve?
Fix parameter of calling self.dataStore.get() and warning info during
parser
https://github.com/infiniflow/ragflow/issues/13036
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Adjust highlight parsing, add row-count SQL override, tweak retrieval
thresholding, and update tests with engine-aware skips/utilities.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## 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
## Description
Upgrade dashscope package to support text-embedding-v4 model.
## Changes
- Update dashscope version from 1.20.11 to 1.25.11 in pyproject.toml
## Reason
The text-embedding-v4 model requires dashscope >= 1.25.0 to function
properly. This upgrade ensures compatibility with the latest embedding
models.
Co-authored-by: Clint-chan <Clint-chan@users.noreply.github.com>
### What problem does this PR solve?
MCP host mode supports STREAMABLE-HTTP endpoint
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### 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)
Fix RDBMS field separation after chunking by wrapping field names in
brackets (【field】: value). This ensures fields remain distinguishable
even when TxtParser strips newline delimiters during chunk merging.
Closes #13001
Co-authored-by: mkdev11 <YOUR_GITHUB_ID+MkDev11@users.noreply.github.com>
### What problem does this PR solve?
Some Excel files have abnormal `max_row` metadata (e.g.,
`max_row=1,048,534` with only 300 actual data rows). This causes:
- `row_number()` returns incorrect count, creating 350+ tasks instead of
1
- `list(ws.rows)` iterates through millions of empty rows, causing
system hang
This PR uses binary search to find the actual last row with data.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement
Co-authored-by: Cursor <cursoragent@cursor.com>
### 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?
Fix: correct llm_id for graphrag #13030
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Bug: When a filter key doesn't exist in metas or has no matching values,
the filter was skipped entirely, causing AND logic to fail.
Example:
- Filter 1: meeting_series = '宏观早8点' (matches doc1, doc2, doc3)
- Filter 2: date = '2026-03-05' (no matches)
- Expected: [] (AND should return empty)
- Actual: [doc1, doc2, doc3] (Filter 2 was skipped)
Root cause:
Old logic iterated metas.items() first, then filters. If a filter's key
wasn't in metas, it was never processed.
Fix:
Iterate filters first, then look up in metas. If key not found, treat as
no match (empty result), which correctly applies AND logic.
Changes:
- Changed loop order from 'for k in metas: for f in filters' to 'for f
in filters: if f.key in metas'
- Explicitly handle missing keys as empty results
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Clint-chan <Clint-chan@users.noreply.github.com>
### What problem does this PR solve?
Fixed vulnerabilities CVE-2025-53859 & CVE-2025-23419 by updating nginx
to 1.29.5-1~noble
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
<img width="709" height="54" alt="image"
src="https://github.com/user-attachments/assets/d8c3518f-bca4-4314-a85c-1aed1678f72e"
/>
### 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>
## Description
This PR fixes the issue where date metadata conditions with comparison
operators (`>=`, `<=`, `>`, `<`) did not work correctly in the
`/api/v1/retrieval` endpoint.
## Problem
When using metadata conditions like:
```json
{
"metadata_condition": {
"conditions": [
{
"name": "date",
"comparison_operator": ">=",
"value": "2027-01-13"
}
]
}
}
The filtering did not work as expected because:
1. Operators >= and <= were not mapped to internal symbols ≥ and ≤
2. Date strings like "2027-01-13" failed to parse with
ast.literal_eval()
3. Non-standard date formats were incorrectly compared as strings
Solution
Changes in common/metadata_utils.py:
1. Added operator mapping in convert_conditions():
- >= → ≥
- <= → ≤
- != → ≠
2. Implemented strict date format detection in meta_filter():
- Only processes dates in YYYY-MM-DD format (10 characters, properly
formatted)
- When query value is a date, only matches data in the same standard
format
- Non-standard formats (e.g., "2026年1月13日", "2026-1-22") are skipped
3. Maintained backward compatibility:
- Numeric comparisons still work
- String comparisons still work
- Only affects date-formatted queries
Testing
All test cases pass (8/8):
- ✅ Date >= comparison
- ✅ Date > comparison
- ✅ Date < comparison
- ✅ Date <= comparison
- ✅ Date = comparison
- ✅ Date range queries
- ✅ Non-date string comparison (backward compatibility)
- ✅ Numeric comparison (backward compatibility)
Example Usage
{
"dataset_ids": ["xxx"],
"question": "test",
"metadata_condition": {
"conditions": [
{
"name": "date",
"comparison_operator": ">=",
"value": "2027-01-13"
}
]
}
}
Notes
- Only supports standard YYYY-MM-DD format
- Non-standard date formats in data are treated as data quality issues
and will not match
- Users should ensure their date metadata is in the correct format
---------
Co-authored-by: Clint-chan <Clint-chan@users.noreply.github.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?
Update stepfun list.
Add TTS and Sequence2Text functionalities.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR adds an opt‑in way to include document‑level metadata in
OpenAI‑compatible reference chunks. Until now, metadata could be used
for filtering but wasn’t returned in responses. The change enables
clients to show richer citations (author/year/source, etc.) while
keeping payload size and privacy under control via an explicit request
flag and optional field allowlist.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Contribution during my time at RAGcon GmbH.
