## Summary
- **Lazy img_np loading**: `np.array(img)` is now deferred until the
first OCR text extraction is actually needed, avoiding unnecessary
memory allocation for pages that already have text.
- **Chunked parse_into_bboxes**: Large PDFs (>50 pages, configurable via
`PDF_PARSER_PAGE_BATCH_SIZE`) are processed in batches. Each chunk's
boxes are normalized with `_to_global_boxes` to produce globally
consistent page numbers and position tags.
- **DLA early init**: Move remote-client initialization before model
loading in `LayoutRecognizer.__init__` so `DEEPDOC_URL` (or legacy
`TENSORRT_DLA_SVR`) short-circuits unnecessary model download for parser
containers relying on remote inference.
- **Fix outline regression**: Restore `self.outlines =
extract_pdf_outlines(fnm)` in `parse_into_bboxes`; this was dropped
during refactoring and is required by downstream `remove_toc` and
metadata handling in `rag/flow/parser/parser.py`.
## Test plan
- [ ] Small PDF (<=50 pages): verify parse succeeds and `self.outlines`
is populated
- [ ] Large PDF (>50 pages): verify chunked processing produces globally
consistent page numbers
- [ ] With `DEEPDOC_URL` set: verify remote DLA client is used and local
model is not downloaded
- [ ] With legacy `TENSORRT_DLA_SVR` set: verify backward compatibility
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
### What problem does this PR solve?
Fixes#14196
## Problem
When using DeepDOC to parse large PDFs (over 1000 pages), the parser
silently truncated processing at 300 pages due to a hardcoded default
`page_to=299` in `RAGFlowPdfParser.__images__()`. This caused:
- **Errors** on pages beyond the limit
- **Poor image quality** as the parser attempted to compensate with
missing page data
- **Inconsistent chunk splitting** between full PDF imports and partial
imports
Additionally, the codebase scattered magic numbers (`299`, `600`,
`10000`, `100000`, `100000000`, `10000000000`, `10**9`) across 22 files
as sentinel values for "parse all pages", making future maintenance
error-prone.
## Root Cause
```python
# deepdoc/parser/pdf_parser.py (before)
def __images__(self, fnm, zoomin=3, page_from=0, page_to=299, callback=None):
# Only the first 300 pages were rendered; everything beyond was silently dropped
```
While most callers in `rag/app/*.py` correctly passed `to_page=100000`,
the base class `RAGFlowPdfParser.__call__()` and `parse_into_bboxes()`
invoked `__images__` **without** forwarding `page_from`/`page_to`,
falling back to the restrictive default of 299.
## Solution
### 1. Define constants in `common/constants.py`
```python
MAXIMUM_PAGE_NUMBER = 100000 # Used by the parsing layer
MAXIMUM_TASK_PAGE_NUMBER = MAXIMUM_PAGE_NUMBER * 1000 # Used by the task/DB layer
```
### 2. Replace all hardcoded sentinel values
| Layer | Files Changed | Old Values | New Value |
|---|---|---|---|
| **Deepdoc parsers** | `pdf_parser.py`, `mineru_parser.py`,
`docling_parser.py`, `opendataloader_parser.py`, `paddleocr_parser.py`,
`docx_parser.py` | `299`, `600`, `10**9`, `100000000` |
`MAXIMUM_PAGE_NUMBER` |
| **Chunk parsers** | `naive.py`, `book.py`, `qa.py`, `one.py`,
`manual.py`, `paper.py`, `presentation.py`, `laws.py`, `resume.py`,
`email.py`, `table.py` | `100000`, `10000`, `10000000000` |
`MAXIMUM_PAGE_NUMBER` |
| **Task/DB layer** | `db_models.py`, `task_service.py`,
`document_service.py`, `file_service.py` | `100000000` |
`MAXIMUM_TASK_PAGE_NUMBER` |
### 3. Fix `parse_into_bboxes()` missing parameters
Added `from_page`/`to_page` parameters to `parse_into_bboxes()` so that
the `rag/flow/parser/parser.py` DeepDOC path no longer falls back to the
restrictive default.
## Files Changed (22)
- `common/constants.py`
- `deepdoc/parser/pdf_parser.py`
- `deepdoc/parser/mineru_parser.py`
- `deepdoc/parser/docling_parser.py`
- `deepdoc/parser/opendataloader_parser.py`
- `deepdoc/parser/paddleocr_parser.py`
- `deepdoc/parser/docx_parser.py`
- `rag/app/naive.py`
- `rag/app/book.py`
- `rag/app/qa.py`
- `rag/app/one.py`
- `rag/app/manual.py`
- `rag/app/paper.py`
- `rag/app/presentation.py`
- `rag/app/laws.py`
- `rag/app/resume.py`
- `rag/app/email.py`
- `rag/app/table.py`
- `api/db/db_models.py`
- `api/db/services/task_service.py`
- `api/db/services/document_service.py`
- `api/db/services/file_service.py`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
---------
Signed-off-by: noob <yixiao121314@outlook.com>
fix: support dense_vector from ES fields response (ES 9.x compatibility)
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Configuration Chore (non-breaking change which updates
configuration)
## Summary by CodeRabbit
* **Bug Fixes**
* More accurate handling and unwrapping of dense-vector fields so
returned values have correct shapes.
* Field selection reliably limits returned data and falls back to
alternate result locations when needed.
* Use of consistent result IDs and tolerant handling when score values
are missing.
* **Chores / Configuration**
* Increased build memory and adjusted build-time flags for the frontend
build.
* Simplified runtime model/GPU checks and removed an automated runtime
GPU-install attempt.
* **Build Fixes**
* `web/vite.config.ts`: make `build.minify` and `build.sourcemap`
respect `VITE_MINIFY` and `VITE_BUILD_SOURCEMAP` env vars from
Dockerfile instead of hardcoding `terser` and `true`.
* **Environment**
* Allow stack version override and default the runtime image tag to
"latest".
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Correct unwrapping of dense-vector fields and reliable field selection
with fallback locations.
* Consistent use of hit-level IDs and tolerant handling when score
values are missing.
* **Chores / Configuration**
* Increased frontend build memory and added build-time minify/sourcemap
flags; build minification and sourcemap now configurable.
* Removed runtime GPU detection for model initialization; force CPU
initialization.
* **Environment**
* Allow stack version override and default runtime image tag to
"latest".
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Summary
- Fix `a image` → `an image` in README and log message
- Fix `colomn` → `column` in table structure recognizer comment
- Fix `formated` → `formatted` in confluence connector docstring
- Fix `tabel of content` → `table of contents` in TOC prompt
## Test plan
- [ ] Documentation and comment changes, no functional impact
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: yuj <yuj@ztjzsoft.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.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?
Fix: image pdf in ingestion pipeline #13550
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Problem
When PDF fonts lack ToUnicode/CMap mappings, pdfplumber (pdfminer)
cannot map CIDs to correct Unicode characters, outputting PUA characters
(U+E000~U+F8FF) or `(cid:xxx)` placeholders. The original code fully
trusted pdfplumber text without any garbled detection, causing garbled
output in the final parsed result.
Relates to #13366
## Solution
### 1. Garbled text detection functions
- `_is_garbled_char(ch)`: Detects PUA characters (BMP/Plane 15/16),
replacement character U+FFFD, control characters, and
unassigned/surrogate codepoints
- `_is_garbled_text(text, threshold)`: Calculates garbled ratio and
detects `(cid:xxx)` patterns
### 2. Box-level fallback (in `__ocr()`)
When a text box has ≥50% garbled characters, discard pdfplumber text and
fallback to OCR recognition.
### 3. Page-level detection (in `__images__()`)
Sample characters from each page; if garbled rate ≥30%, clear all
pdfplumber characters for that page, forcing full OCR.
### 4. Layout recognizer CID filtering
Filter out `(cid:xxx)` patterns in `layout_recognizer.py` text
processing to prevent them from polluting layout analysis.
## Testing
- 29 unit tests covering: normal CJK/English text, PUA characters, CID
patterns, mixed text, boundary thresholds, edge cases
- All 85 existing project unit tests pass without regression
### 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>
