### What problem does this PR solve?
Summary:
This PR addresses critical indexing issues in
deepdoc/parser/pdf_parser.py that occur when parsing long PDFs with
chunk-based pagination:
Normalize rotated table page numbering: Rotated-table re-OCR now writes
page_number in chunk-local 1-based form, eliminating double-addition of
page_from offset that caused misalignment between table positions and
document boxes.
Convert absolute positions to chunk-local coordinates: When inserting
tables/figures extracted via _extract_table_figure, positions are now
converted from absolute (0-based) to chunk-local indices before distance
matching and box insertion. This prevents IndexError and out-of-range
accesses during paged parsing of long documents.
Root Cause:
The parser mixed absolute (0-based, document-global) and relative
(1-based, chunk-local) page numbering systems. Table/figure positions
from layout extraction carried absolute page numbers, but insertion
logic expected chunk-local coordinates aligned with self.boxes and
page_cum_height.
Testing(I do):
Manual verification: Parse a 200+ page PDF with from_page > 0 and table
rotation enabled. Confirm that:
Tables and figures appear on correct pages
No IndexError or position mismatches occur
Page numbers in output match expected chunk-local offsets
Automated testing: 我没做
## Separate Discussion: Memory Optimization Strategy(from codex-5.2-max
and claude 4.5 opus and me)
### Context
The current implementation loads entire page ranges into memory
(`__images__`, `page_chars`, intermediates), which can cause RAM
exhaustion on large documents. While the page numbering fix resolves
correctness issues, scalability remains a concern.
### Proposed Architecture
**Pipeline-Driven Chunking with Explicit Resource Management:**
1. **Authoritative chunk planning**: Accept page-range specifications
from upstream pipeline as the single source of truth. The parser should
be a stateless worker that processes assigned chunks without making
independent pagination decisions.
2. **Granular memory lifecycle**:
```python
for chunk_spec in chunk_plan:
# Load only chunk_spec.pages into __images__
page_images = load_page_range(chunk_spec.start, chunk_spec.end)
# Process with offset tracking
results = process_chunk(page_images, offset=chunk_spec.start)
# Explicit cleanup before next iteration
del page_images, page_chars, layout_intermediates
gc.collect() # Force collection of large objects
```
3. **Persistent lightweight state**: Keep model instances (layout
detector, OCR engine), document metadata (outlines, PDF structure), and
configuration across chunks to avoid reinitialization overhead (~2-5s
per chunk for model loading).
4. **Adaptive fallback**: Provide `max_pages_per_chunk` (default: 50)
only when pipeline doesn't supply a plan. Never exceed
pipeline-specified ranges to maintain predictable memory bounds.
5. **Optional: Dynamic budgeting**: Expose a memory budget parameter
that adjusts chunk size based on observed image dimensions and format
(e.g., reduce chunk size for high-DPI scanned documents).
### Benefits
- **Predictable memory footprint**: RAM usage bounded by `chunk_size ×
avg_page_size` rather than total document size
- **Horizontal scalability**: Enables parallel chunk processing across
workers
- **Failure isolation**: Page extraction errors affect only current
chunk, not entire document
- **Cloud-friendly**: Works within container memory limits (e.g., 2-4GB
per worker)
### Trade-offs
- **Increased I/O**: Re-opening PDF for each chunk vs. keeping file
handle (mitigated by page-range seeks)
- **Complexity**: Requires careful offset tracking and stateful
coordination between pipeline and parser
- **Warmup cost**: Model initialization overhead amortized across chunks
(acceptable for documents >100 pages)
### Implementation Priority
This optimization should be **deferred to a separate PR** after the
current correctness fix is merged, as:
1. It requires broader architectural changes across the pipeline
2. Current fix is critical for correctness and can be backported
3. Memory optimization needs comprehensive benchmarking on
representative document corpus
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: PDF chunking issue for single-page documents
Refactor: Change the default refresh frequency to 5
Fix: Add a 0-degree threshold; require other rotation angles to exceed
it by at least 0.2
Fix: Put connector name tips to correct place
Fix: incorrect example response in delete datasets.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
### What problem does this PR solve?
This PR introduces automatic table orientation detection and correction
within the PDF parser. This ensures that tables in PDFs are correctly
oriented before structure recognition, improving overall parsing
accuracy.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
Fix: duplicate content in chunk #12336
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Treat MinerU as an OCR model.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
issue:
#10427
change:
new component Loop
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- Add whitespace validation to the PDF English text checking regex
- Reduce false negatives in English PDF content recognition
### What problem does this PR solve?
The core idea is to **expand the regex content used for English text
detection** so it can accommodate more valid characters commonly found
in English PDFs. The modifications include:
- Adding support for **space** in the regex.
- Ensuring the update does not reduce existing detection accuracy.
### Type of change
- [✅] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
change:
improve multi-column document detection
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Introduced gpu profile in .env
Added Dockerfile_tei
fix datrie
Removed LIGHTEN flag
### Type of change
- [x] Documentation Update
- [x] Refactoring
### 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?
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?
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?
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
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?
Add VLM-boosted PDF parser if VLM is set.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add vision LLM PDF parser
### 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?
The `ocr.res` file is already included in the model directory
`rag/res/deepdoc`, but it doesn't seem to be utilized here.
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
close#5277 by make sure the file close
### Type of change
- [x] Performance Improvement
---------
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
