zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-06-29 15:31:05 +08:00
Code Issues Packages Projects Releases Wiki Activity
7,019 Commits 2 Branches 56 Tags
main
Commit Graph

16 Commits

Author SHA1 Message Date
wdeveloper16
78188ce9e9 Feat: add OpenDataLoader PDF parser backend (#14058) (#14097) 
### What problem does this PR solve?

Closes #14058.

RAGFlow supports multiple PDF parsing backends (DeepDOC, MinerU,
Docling, TCADP, PaddleOCR). This PR adds **OpenDataLoader**
([opendataloader-project/opendataloader-pdf](https://github.com/opendataloader-project/opendataloader-pdf))
as a new optional backend, giving users a deterministic, local-first
alternative with competitive table extraction accuracy.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update

---

### Changes

#### Backend
- `deepdoc/parser/opendataloader_parser.py` — new `OpenDataLoaderParser`
class inheriting `RAGFlowPdfParser`. Implements `check_installation()`
(guards Python package + Java 11+ runtime), `parse_pdf()` with
JSON-first extraction (heading/paragraph/table/list/image/formula) and
Markdown fallback, position-tag generation compatible with the shared
`@@page\tx0\tx1\ty0\ty1##` format, and temp-dir lifecycle with cleanup.
- `rag/app/naive.py` — new `by_opendataloader()` wrapper, registered in
`PARSERS` dict, added to `chunk_token_num=0` override list.
- `rag/flow/parser/parser.py` — `"opendataloader"` branch in the
pipeline PDF handler + check validation list.

#### Infrastructure
- `docker/entrypoint.sh` — `ensure_opendataloader()` function: opt-in
via `USE_OPENDATALOADER=true`, skips gracefully if Java is not on PATH.

#### Frontend
- `web/src/components/layout-recognize-form-field.tsx` —
`OpenDataLoader` added to `ParseDocumentType` enum and parser dropdown.
Cascades automatically to the pipeline editor's Parser component.

#### Docs
- `docs/guides/dataset/select_pdf_parser.md` — added OpenDataLoader
entry and full env-var reference.

---

### Environment variables

| Variable | Default | Description |
|---|---|---|
| `USE_OPENDATALOADER` | `false` | Set `true` to install
`opendataloader-pdf` on container startup |
| `OPENDATALOADER_VERSION` | latest | Pin the PyPI release (e.g.
`==2.2.1`) |
| `OPENDATALOADER_HYBRID` | _(unset)_ | Enable hybrid AI mode (e.g.
`docling-fast`) |
| `OPENDATALOADER_IMAGE_OUTPUT` | _(unset)_ | `off` / `embedded` /
`external` |
| `OPENDATALOADER_OUTPUT_DIR` | _(tmp)_ | Persistent output dir; temp
dir used + cleaned if unset |
| `OPENDATALOADER_DELETE_OUTPUT` | `1` | `0` to retain intermediate
files for debugging |
| `OPENDATALOADER_SANITIZE` | _(unset)_ | `1` to filter prompt-injection
patterns from output |

---

### Dependencies

- **Runtime**: `opendataloader-pdf` (PyPI, Apache 2.0) — opt-in, not
added to `pyproject.toml` core deps. Installed by
`ensure_opendataloader()` at container startup when
`USE_OPENDATALOADER=true`.
- **System**: Java 11+ on PATH (JVM is the underlying engine). The
installer skips with a warning if `java` is not found.

---

### How to test

**Standalone parser:**
```bash
source .venv/bin/activate
uv pip install opendataloader-pdf
python3 -c "
import sys; sys.path.insert(0, '.')
from deepdoc.parser.opendataloader_parser import OpenDataLoaderParser
p = OpenDataLoaderParser()
print('available:', p.check_installation())
s, t = p.parse_pdf('path/to/test.pdf', parse_method='pipeline')
print(f'sections={len(s)} tables={len(t)}')
"

```
### Benchmark vs Docling
```
file                      parser            secs  sections  tables
----------------------------------------------------------------------
text-heavy.pdf            docling           45.29       148      10
text-heavy.pdf            opendataloader     3.14       559       0
table-heavy.pdf           docling           7.05        76       3
table-heavy.pdf           opendataloader     3.71        90       0
complex.pdf               docling            42.67       114       8
complex.pdf               opendataloader     3.51       180       0
```
 2026-04-25 00:33:02 +08:00
NeedmeFordev
387b0b27c4 feat(parser): support external Docling server via DOCLING_SERVER_URL (#13527) 
### What problem does this PR solve?

This PR adds support for parsing PDFs through an external Docling
server, so RAGFlow can connect to remote `docling serve` deployments
instead of relying only on local in-process Docling.

It addresses the feature request in
[#13426](https://github.com/infiniflow/ragflow/issues/13426) and aligns
with the external-server usage pattern already used by MinerU.

### 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):

### What is changed?

- Add external Docling server support in `DoclingParser`:
  - Use `DOCLING_SERVER_URL` to enable remote parsing mode.
- Try `POST /v1/convert/source` first, and fallback to
`/v1alpha/convert/source`.
- Keep existing local Docling behavior when `DOCLING_SERVER_URL` is not
set.
- Wire Docling env settings into parser invocation paths:
  - `rag/app/naive.py`
  - `rag/flow/parser/parser.py`
- Add Docling env hints in constants and update docs:
  - `docs/guides/dataset/select_pdf_parser.md`
  - `docs/guides/agent/agent_component_reference/parser.md`
  - `docs/faq.mdx`

### Why this approach?

This keeps the change focused on one issue and one capability (external
Docling connectivity), without introducing unrelated provider-model
plumbing.

### Validation

- Static checks:
  - `python -m py_compile` on changed Python files
  - `python -m ruff check` on changed Python files
- Functional checks:
  - Remote v1 endpoint path works
  - v1alpha fallback works
  - Local Docling path remains available when server URL is unset

### Related links

- Feature request: [Support external Docling server (issue
#13426)](https://github.com/infiniflow/ragflow/issues/13426)
- Compare view for this branch:
[main...feat/docling-server](https://github.com/infiniflow/ragflow/compare/main...spider-yamet:ragflow:feat/docling-server?expand=1)

##### Fixes [#13426](https://github.com/infiniflow/ragflow/issues/13426)
 2026-03-12 17:09:03 +08:00
Jimmy Ben Klieve
867ec94258 revert white-space changes in docs (#12557) 
### What problem does this PR solve?

Trailing white-spaces in commit 6814ace1aa
got automatically trimmed by code editor may causes documentation
typesetting broken.

Mostly for double spaces for soft line breaks.  

### Type of change

- [x] Documentation Update
 2026-01-13 09:41:02 +08:00
Jimmy Ben Klieve
6814ace1aa docs: update docs icons (#12465) 
### What problem does this PR solve?

Update icons for docs.
Trailing spaces are auto truncated by the editor, does not affect real
content.

### Type of change

- [x] Documentation Update
 2026-01-07 10:00:09 +08:00
writinwaters
c2e9064474 Docs: v0.23.0 release notes (#12251) 
### What problem does this PR solve?


### Type of change


- [x] Documentation Update

---------

Co-authored-by: Yingfeng Zhang <yingfeng.zhang@gmail.com>
 2025-12-26 19:11:10 +08:00
writinwaters
8683a5b1b7 Docs: How to call MinerU as a remote service (#12004) 
### Type of change

- [x] Documentation Update
 2025-12-19 17:06:32 +08:00
Yongteng Lei
03f9be7cbb Refa: only support MinerU-API now (#11977) 
### What problem does this PR solve?

Only support MinerU-API now, still need to complete frontend for
pipeline to allow the configuration of MinerU options.

### Type of change

- [x] Refactoring
 2025-12-17 12:58:48 +08:00
Jin Hai
8406a5ea47 Fix typos (#11208) 
### What problem does this PR solve?

As title

### Type of change

- [x] Documentation Update

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2025-11-12 14:20:04 +08:00
writinwaters
2c727a4a9c Docs: parser behavior change (#11176) 
### What problem does this PR solve?


### Type of change


- [x] Documentation Update
 2025-11-11 21:10:06 +08:00
writinwaters
de24e74b4c Docs: How to use MinerU to parse pdf documents (#10763) 
### What problem does this PR solve?



### Type of change

- [x] Documentation Update
 2025-10-23 18:56:09 +08:00
writinwaters
74c195cd36 Doc: Added Long context RAG guide (#10591) 
### What problem does this PR solve?

### Type of change


- [x] Documentation Update
 2025-10-15 21:00:19 +08:00
writinwaters
4058715df7 Docs: Knowledge base renamed to dataset. (#10269) 
### What problem does this PR solve?

### Type of change

- [x] Documentation Update
 2025-09-25 09:45:27 +08:00
writinwaters
4f92af3cd4 Docs: Updated Auto-question Auto-keyword (#8168) 
### What problem does this PR solve?

### Type of change

- [x] Documentation Update
 2025-06-10 19:38:28 +08:00
writinwaters
add4b13856 Docs: Miscellaneous editorial updates (#7865) 
### What problem does this PR solve?



### Type of change


- [x] Documentation Update
 2025-05-26 19:36:35 +08:00
writinwaters
1fd92e6bee Docs: RAGFlow does not suppport batch metadata setting (#7795) 
### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change


- [x] Documentation Update
 2025-05-22 17:02:23 +08:00
writinwaters
76b278af8e 0519 pdfparser (#7747) 
### What problem does this PR solve?


### Type of change


- [x] Documentation Update
 2025-05-20 19:41:55 +08:00