### 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?
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):
i use PdfParser in local(refer to this case:
https://github.com/infiniflow/ragflow/blob/main/rag/app/paper.py) like
this:
```
import re
import openpyxl
from ragflow.api.db import ParserType
from ragflow.rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, \
title_frequency, \
tokenize_chunks
from ragflow.rag.utils import num_tokens_from_string
from ragflow.deepdoc.parser import PdfParser, ExcelParser, DocxParser,PlainParser
def logger(prog=None, msg=""):
print(msg)
class Pdf(PdfParser):
def __init__(self):
self.model_speciess = ParserType.MANUAL.value
super().__init__()
def __call__(self, filename, binary=None, from_page=0,
to_page=100000, zoomin=3, callback=None):
from timeit import default_timer as timer
start = timer()
callback(msg="OCR is running...")
self.__images__(
filename if not binary else binary,
zoomin,
from_page,
to_page,
callback
)
callback(msg="OCR finished.")
print("OCR:", timer() - start)
self._layouts_rec(zoomin)
callback(0.65, "Layout analysis finished.")
print("layouts:", timer() - start)
self._table_transformer_job(zoomin)
callback(0.67, "Table analysis finished.")
self._text_merge()
tbls = self._extract_table_figure(True, zoomin, True, True)
self._concat_downward()
self._filter_forpages()
callback(0.68, "Text merging finished")
# clean mess
for b in self.boxes:
b["text"] = re.sub(r"([\t ]|\u3000){2,}", " ", b["text"].strip())
return [(b["text"], b.get("layout_no", ""), self.get_position(b, zoomin))
for i, b in enumerate(self.boxes)], tbls
```
show err like this:
```
File "xxxxx/third_party/ragflow/deepdoc/parser/pdf_parser.py", line 1039, in __images__
self.pdf.close()
AttributeError: 'PdfReader' object has no attribute 'close'
```
i found ragflow source code use
`pdfplumber.open`（https://github.com/infiniflow/ragflow/blob/main/deepdoc/parser/pdf_parser.py#L1007C28-L1007C43）
and replace` self.pdf `with ` pdf2_read` （from pypdf import PdfReader as
pdf2_read）in line 1024
(https://github.com/infiniflow/ragflow/blob/main/deepdoc/parser/pdf_parser.py#L1024)
```
self.pdf = pdf2_read
```
---
and I found that `pdfplumber` can be used in this way：
```
file_path="xxx.pdf"
res = pdfplumber.open(file_path)
res.close()
```
but `pypdf.PdfReader` source code do not has `close` func, source code
use like this
```
with open(stream, "rb") as fh:
stream = BytesIO(fh.read())
self._stream_opened = True
```
> https://github.com/py-pdf/pypdf/blob/main/pypdf/_reader.py#L156
so I moved the `self.pdf.close` function call and fixed this problem
hoping to help the project😊
### What problem does this PR solve?
Fix: When Excel is a formula, the parsed result is a formula, but cannot
be correctly parsed as a value type
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: tangyu <1@1.com>
### What problem does this PR solve?
support pic base bullet for PPT
modify one mistake in document
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add VLM-boosted PDF parser if VLM is set.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
