### What problem does this PR solve?
issue:
[#7472](https://github.com/infiniflow/ragflow/issues/7472)
change:
Vision Model Image Enhancement in Manual chunker
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add MinerU parser. #3945, #8092.
Set `MINERU_EXECUTABLE` to the MinerU executable path, defaults to
`mineru`.
Set `MINERU_DELETE_OUTPUT=0` to preserve MinerU's output, default is 1,
which deletes temporary output.
Set `MINERU_OUTPUT_DIR` to choose the MinerU output directory (uses the
temporary directory if unset).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix: Agent.reset() argument wrong #10463 & Unable to converse with agent
through Python API. #10415
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Running DeepDoc OCR on large PDFs inside the GPU docker-compose setup
would intermittently fail with
[ONNXRuntimeError] ... p2o.Clip.6 ... Available memory of 0 is smaller
than requested bytes ...
- Root cause: load_model() in deepdoc/vision/ocr.py treated
device_id=None as-is.
torch.cuda.device_count() > device_id then raised a TypeError, the
helper returned False, and ONNXRuntime quietly fell back to
CPUExecutionProvider with
the hard-coded 512 MB limit, which then triggered the allocator failure.
- Environment where this reproduces: Windows 11, AMD 5900x, 64 GB RAM,
RTX 3090 (24 GB), docker-compose-gpu.yml from upstream, default DeepDoc
+ GraphRAG
parser settings, ingesting heavy PDF such as 《内科学》（第10版）.pdf (~180 MB).
Fixes:
- Normalize device_id to 0 when it is None before calling any CUDA APIs,
so the GPU path is considered available.
- Allow configuring the CUDA provider’s memory cap via
OCR_GPU_MEM_LIMIT_MB (default 2048 MB) and expose
OCR_ARENA_EXTEND_STRATEGY; the calculated byte
limit is logged to confirm the effective settings.
After the change, ragflow_server.log shows for example
load_model ... uses GPU (device 0, gpu_mem_limit=21474836480,
arena_strategy=kNextPowerOfTwo) and the same document finishes OCR
without allocator errors.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Refactor import modules.
### Type of change
- [x] Refactoring
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fix broken imports
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Handle zero and nan in calculate.
#10125
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Dataflow support audio. And fix giteeAI's sequence2text model.
### 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?
issue:
[Bug]: Agent component (HTTP Request) "'>' not supported between
instances of 'int' and 'NoneType'"
[#10096](https://github.com/infiniflow/ragflow/issues/10096)
Change:
When the Invoke class instantiates HtmlParser without providing the
chunk_token_num parameter, the value defaults to None, leading to a
comparison error with block_token_count.
This change sets the default chunk_token_num to 512 to prevent such
errors.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: BadwomanCraZY <511528396@qq.com>
### What problem does this PR solve?
Add support for the Ascend table structure recognizer.
Use the environment variable `TABLE_STRUCTURE_RECOGNIZER_TYPE=ascend` to
enable the Ascend table structure recognizer.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Supports Ascend layout recognizer.
Use the environment variable `LAYOUT_RECOGNIZER_TYPE=ascend` to enable
the Ascend layout recognizer, and `ASCEND_LAYOUT_RECOGNIZER_DEVICE_ID=n`
(for example, n=0) to specify the Ascend device ID.
Ensure that you have installed the [ais
tools](https://gitee.com/ascend/tools/tree/master/ais-bench_workload/tool/ais_bench)
properly.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
judge not empty before delete session.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
terminate onnx inference session and release memory manually.
Issue #5050
Issue #9992
Issue #8805
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Dataflow supports Spreadsheet and Word processor document
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
- [x] Performance Improvement
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
### What problem does this PR solve?
Handle unexpected truncated Excel files.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fix "File contains no valid workbook part"
stacktrace:
```
Traceback (most recent call last):
File "/ragflow/deepdoc/parser/excel_parser.py", line 54, in _load_excel_to_workbook
return RAGFlowExcelParser._dataframe_to_workbook(df)
File "/ragflow/deepdoc/parser/excel_parser.py", line 69, in _dataframe_to_workbook
ws.cell(row=row_num, column=col_num, value=value)
File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/worksheet/worksheet.py", line 246, in cell
cell.value = value
File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/cell/cell.py", line 218, in value
self._bind_value(value)
File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/cell/cell.py", line 197, in _bind_value
value = self.check_string(value)
File "/ragflow/.venv/lib/python3.10/site-packages/openpyxl/cell/cell.py", line 165, in check_string
raise IllegalCharacterError(f"{value} cannot be used in worksheets.")
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
add fallback to `calamine` engine when parse error raised using the
default `openpyxl` / `xlrd` engine.
e.g. the following error can be fixed:
```
Traceback (most recent call last):
File "/ragflow/deepdoc/parser/excel_parser.py", line 53, in _load_excel_to_workbook
df = pd.read_excel(file_like_object)
File "/ragflow/.venv/lib/python3.10/site-packages/pandas/io/excel/_base.py", line 495, in read_excel
io = ExcelFile(
File "/ragflow/.venv/lib/python3.10/site-packages/pandas/io/excel/_base.py", line 1567, in __init__
self._reader = self._engines[engine](
File "/ragflow/.venv/lib/python3.10/site-packages/pandas/io/excel/_xlrd.py", line 46, in __init__
super().__init__(
File "/ragflow/.venv/lib/python3.10/site-packages/pandas/io/excel/_base.py", line 573, in __init__
self.book = self.load_workbook(self.handles.handle, engine_kwargs)
File "/ragflow/.venv/lib/python3.10/site-packages/pandas/io/excel/_xlrd.py", line 63, in load_workbook
return open_workbook(file_contents=data, **engine_kwargs)
File "/ragflow/.venv/lib/python3.10/site-packages/xlrd/__init__.py", line 172, in open_workbook
bk = open_workbook_xls(
File "/ragflow/.venv/lib/python3.10/site-packages/xlrd/book.py", line 68, in open_workbook_xls
bk.biff2_8_load(
File "/ragflow/.venv/lib/python3.10/site-packages/xlrd/book.py", line 641, in biff2_8_load
cd.locate_named_stream(UNICODE_LITERAL(qname))
File "/ragflow/.venv/lib/python3.10/site-packages/xlrd/compdoc.py", line 398, in locate_named_stream
result = self._locate_stream(
File "/ragflow/.venv/lib/python3.10/site-packages/xlrd/compdoc.py", line 429, in _locate_stream
raise CompDocError("%s corruption: seen[%d] == %d" % (qname, s, self.seen[s]))
xlrd.compdoc.CompDocError: Workbook corruption: seen[2] == 4
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
…eType'"
### What problem does this PR solve?
fix "TypeError: '<' not supported between instances of 'Emu' and
'NoneType'"
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Supports jsonl or ldjson format. Feature request from
[discussion](https://github.com/orgs/infiniflow/discussions/8774).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix context loss caused by separating markdown tables from original
text. #6871, #8804.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
1. rename var
2. update if statement
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Enhanced the image rotation handling by evaluating the original
orientation, clockwise 90°, and counter-clockwise 90° rotations. The
image with the highest text recognition score is now selected, improving
accuracy for text detection in images with aspect ratios >= 1.5.
#8166
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: wenrui.cao <wenrui.cao@univers.com>
### What problem does this PR solve?
it would be fail if PARALLEL_DEVICES = None in OCR class , because it
pass 0 to TextDetector and TextRecognizer init method.
and It would be simpler to set 0 as the default value for
PARALLEL_DEVICES.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
This small PR resolves the regex library warnings showing in Python3.11:
```python
DeprecationWarning: 'count' is passed as positional argument
```
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
### What problem does this PR solve?
Fixed uncaptured figure data with position information. #7466, #7681
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
When the PDF uses vector fonts, the rendered text in the captured page
image often has missing strokes, leading to numerous OCR errors and
incorrect characters. Similar issues also occur in the extracted chart
images.
**Before**
**After**
You can use the following document for testing.
[Casio说明书.pdf](https://github.com/user-attachments/files/20119690/Casio.pdf)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
### What problem does this PR solve?
https://github.com/infiniflow/ragflow/issues/7466
I think due to some times we can not get position
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
When parsing documents containing images, the current code uses a
single-threaded approach to call the VL model, resulting in extremely
slow parsing speed (e.g., parsing a Word document with dozens of images
takes over 20 minutes).
By switching to a multithreaded approach to call the VL model, the
parsing speed can be improved to an acceptable level.
### Type of change
- [x] Performance Improvement
---------
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
### What problem does this PR solve?
When parsing pptx files, some shapes do not contain the `shape_type`
attribute, which causes the original code to throw an exception during
extraction, leading to failure in content extraction. This optimization
introduces handling logic for such anomalous shapes, providing a safer
and more robust processing mechanism.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [x] Performance Improvement
- [ ] Other (please describe):
