mirror of
https://github.com/open-webui/open-webui.git
synced 2026-07-16 06:03:26 -05:00
[GH-ISSUE #14302] issue: uploading a pdf triggers rapidocr-onnxruntime package not found despite package being installed
#136932
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#136932
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @abcd678 on GitHub (May 25, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14302
Check Existing Issues
Installation Method
Other
Open WebUI Version
v0.6.10
Ollama Version (if applicable)
No response
Operating System
Ubuntu 22.04
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
When adding a PDF with default content extraction engine options, should receive no errors
Actual Behavior
Instantly receive error below
rapidocr-onnxruntimepackage not found, please install it withpip install rapidocr-onnxruntimepip package is installed
Requirement already satisfied: rapidocr-onnxruntime in /home/OpenWebUI/venv/lib/python3.11/site-packages (1.4.4) Requirement already satisfied: pyclipper>=1.2.0 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (1.3.0.post6) Requirement already satisfied: opencv-python>=4.5.1.48 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (4.11.0.86) Requirement already satisfied: numpy<3.0.0,>=1.19.5 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (1.26.4) Requirement already satisfied: six>=1.15.0 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (1.17.0) Requirement already satisfied: Shapely!=2.0.4,>=1.7.1 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (2.1.1) Requirement already satisfied: PyYAML in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (6.0.2) Requirement already satisfied: Pillow in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (11.1.0) Requirement already satisfied: onnxruntime>=1.7.0 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (1.20.1) Requirement already satisfied: tqdm in /home/OpenWebUI/venv/lib/python3.11/site-packages (from rapidocr-onnxruntime) (4.67.1) Requirement already satisfied: coloredlogs in /home/OpenWebUI/venv/lib/python3.11/site-packages (from onnxruntime>=1.7.0->rapidocr-onnxruntime) (15.0.1) Requirement already satisfied: flatbuffers in /home/OpenWebUI/venv/lib/python3.11/site-packages (from onnxruntime>=1.7.0->rapidocr-onnxruntime) (25.2.10) Requirement already satisfied: packaging in /home/OpenWebUI/venv/lib/python3.11/site-packages (from onnxruntime>=1.7.0->rapidocr-onnxruntime) (23.2) Requirement already satisfied: protobuf in /home/OpenWebUI/venv/lib/python3.11/site-packages (from onnxruntime>=1.7.0->rapidocr-onnxruntime) (5.29.4) Requirement already satisfied: sympy in /home/OpenWebUI/venv/lib/python3.11/site-packages (from onnxruntime>=1.7.0->rapidocr-onnxruntime) (1.14.0) Requirement already satisfied: humanfriendly>=9.1 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from coloredlogs->onnxruntime>=1.7.0->rapidocr-onnxruntime) (10.0) Requirement already satisfied: mpmath<1.4,>=1.1.0 in /home/OpenWebUI/venv/lib/python3.11/site-packages (from sympy->onnxruntime>=1.7.0->rapidocr-onnxruntime) (1.3.0)Steps to Reproduce
Install open-webUI with python+venv installation instructions
upload pdf to chat
Logs & Screenshots
2025-05-25 00:13:12.405 | INFO | open_webui.routers.files:upload_file:91 - file.content_type: application/pdf - {} 2025-05-25 00:13:12.483 | ERROR | open_webui.routers.retrieval:process_file:1260 -rapidocr-onnxruntimepackage not found, please install it withpip install rapidocr-onnxruntime` - {}Traceback (most recent call last):
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/images.py", line 102, in _analyze_image
from rapidocr_onnxruntime import RapidOCR
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/rapidocr_onnxruntime/init.py", line 4, in
from .main import RapidOCR
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/rapidocr_onnxruntime/main.py", line 8, in
import cv2
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/cv2/init.py", line 181, in
bootstrap()
└ <function bootstrap at 0x77ae00614e00>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/cv2/init.py", line 153, in bootstrap
native_module = importlib.import_module("cv2")
│ └ <function import_module at 0x77af0ba6eac0>
└ <module 'importlib' from '/usr/lib/python3.11/importlib/init.py'>
File "/usr/lib/python3.11/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
│ │ │ │ │ └ 0
│ │ │ │ └ None
│ │ │ └ 0
│ │ └ 'cv2'
│ └ <function _gcd_import at 0x77af0bc07d80>
└ <module '_frozen_importlib' (frozen)>
ImportError: libGL.so.1: cannot open shared object file: No such file or directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.11/threading.py", line 1002, in _bootstrap
self._bootstrap_inner()
│ └ <function Thread._bootstrap_inner at 0x77af0bb149a0>
└ <WorkerThread(AnyIO worker thread, started 131588855682624)>
File "/usr/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function WorkerThread.run at 0x77ae02cc1a80>
└ <WorkerThread(AnyIO worker thread, started 131588855682624)>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
result = context.run(func, *args)
│ │ │ └ ()
│ │ └ functools.partial(<function upload_file at 0x77ae3057fec0>, user=UserModel(id='4e510679-2e06-40f6-a5bc-fae05d975901', name='p...
│ └ <method 'run' of '_contextvars.Context' objects>
└ <_contextvars.Context object at 0x77ae02d3b580>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/open_webui/routers/files.py", line 162, in upload_file
process_file(request, ProcessFileForm(file_id=id), user=user)
│ │ │ │ └ UserModel(id='4e510679-2e06-40f6-a5bc-fae05d975901', name='redacted', email='redacted@hotmail.com', role='admin', profile_ima...
│ │ │ └ '59250849-4166-46d6-a38d-a453032e8f78'
│ │ └ <class 'open_webui.routers.retrieval.ProcessFileForm'>
│ └ <starlette.requests.Request object at 0x77ae02c24fd0>
└ <function process_file at 0x77ae2d3e5da0>
ImportError:
rapidocr-onnxruntimepackage not found, please install it withpip install rapidocr-onnxruntime2025-05-25 00:13:12.487 | ERROR | open_webui.routers.files:upload_file:171 - 400:
rapidocr-onnxruntimepackage not found, please install it withpip install rapidocr-onnxruntime- {}Traceback (most recent call last):
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/images.py", line 102, in _analyze_image
from rapidocr_onnxruntime import RapidOCR
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/rapidocr_onnxruntime/init.py", line 4, in
from .main import RapidOCR
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/rapidocr_onnxruntime/main.py", line 8, in
import cv2
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/cv2/init.py", line 181, in
bootstrap()
└ <function bootstrap at 0x77ae00614e00>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/cv2/init.py", line 153, in bootstrap
native_module = importlib.import_module("cv2")
│ └ <function import_module at 0x77af0ba6eac0>
└ <module 'importlib' from '/usr/lib/python3.11/importlib/init.py'>
File "/usr/lib/python3.11/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
│ │ │ │ │ └ 0
│ │ │ │ └ None
│ │ │ └ 0
│ │ └ 'cv2'
│ └ <function _gcd_import at 0x77af0bc07d80>
└ <module '_frozen_importlib' (frozen)>
ImportError: libGL.so.1: cannot open shared object file: No such file or directory
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/open_webui/routers/retrieval.py", line 1179, in process_file
docs = loader.load(
│ └ <function Loader.load at 0x77ae2e1ad620>
└ <open_webui.retrieval.loaders.main.Loader object at 0x77ae02bfb590>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/open_webui/retrieval/loaders/main.py", line 201, in load
docs = loader.load()
│ └ <function BaseLoader.load at 0x77ae2e84f100>
└ <langchain_community.document_loaders.pdf.PyPDFLoader object at 0x77ae0333b5d0>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_core/document_loaders/base.py", line 32, in load
return list(self.lazy_load())
│ └ <function PyPDFLoader.lazy_load at 0x77ae2e178900>
└ <langchain_community.document_loaders.pdf.PyPDFLoader object at 0x77ae0333b5d0>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/pdf.py", line 305, in lazy_load
yield from self.parser.lazy_parse(blob)
│ │ │ └ Blob 131589275275888 /home/OpenWebUI/venv/lib/python3.11/site-packages/open_webui/data/uploads/59250849-4166-46d6-a38d-a45303...
│ │ └ <function PyPDFParser.lazy_parse at 0x77ae2e347380>
│ └ <langchain_community.document_loaders.parsers.pdf.PyPDFParser object at 0x77ae02c356d0>
└ <langchain_community.document_loaders.pdf.PyPDFLoader object at 0x77ae0333b5d0>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/pdf.py", line 397, in lazy_parse
images_from_page = self.extract_images_from_page(page)
│ │ └ {'/Type': '/Page', '/Parent': IndirectObject(180, 0, 131589982620880), '/Resources': IndirectObject(207, 0, 131589982620880),...
│ └ <function PyPDFParser.extract_images_from_page at 0x77ae2e347420>
└ <langchain_community.document_loaders.parsers.pdf.PyPDFParser object at 0x77ae02c356d0>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/pdf.py", line 462, in extract_images_from_page
image_text = next(self.images_parser.lazy_parse(blob)).page_content
│ │ │ └ Blob 131589214222560
│ │ └ <function BaseImageBlobParser.lazy_parse at 0x77ae2e346020>
│ └ <langchain_community.document_loaders.parsers.images.RapidOCRBlobParser object at 0x77ae02d1ab10>
└ <langchain_community.document_loaders.parsers.pdf.PyPDFParser object at 0x77ae02c356d0>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/images.py", line 63, in lazy_parse
content = self._analyze_image(img)
│ │ └ <PIL.PngImagePlugin.PngImageFile image mode=RGB size=707x707 at 0x77AE005B7D10>
│ └ <function RapidOCRBlobParser._analyze_image at 0x77ae2e346160>
└ <langchain_community.document_loaders.parsers.images.RapidOCRBlobParser object at 0x77ae02d1ab10>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/images.py", line 106, in _analyze_image
raise ImportError(
ImportError:
rapidocr-onnxruntimepackage not found, please install it withpip install rapidocr-onnxruntimeDuring handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib/python3.11/threading.py", line 1002, in _bootstrap
self._bootstrap_inner()
│ └ <function Thread._bootstrap_inner at 0x77af0bb149a0>
└ <WorkerThread(AnyIO worker thread, started 131588855682624)>
File "/usr/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
self.run()
│ └ <function WorkerThread.run at 0x77ae02cc1a80>
└ <WorkerThread(AnyIO worker thread, started 131588855682624)>
File "/home/OpenWebUI/venv/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 967, in run
result = context.run(func, *args)
│ │ │ └ ()
│ │ └ functools.partial(<function upload_file at 0x77ae3057fec0>, user=UserModel(id='4e510679-2e06-40f6-a5bc-fae05d975901', name='p...
│ └ <method 'run' of '_contextvars.Context' objects>
└ <_contextvars.Context object at 0x77ae02d3b580>
fastapi.exceptions.HTTPException: 400:
rapidocr-onnxruntimepackage not found, please install it withpip install rapidocr-onnxruntime2025-05-25 00:13:12.489 | ERROR | open_webui.routers.files:upload_file:172 - Error processing file: 59250849-4166-46d6-a38d-a453032e8f78 - {}`
Additional Information
No response
@rgaricano commented on GitHub (May 25, 2025):
it seem as requirement isn't installed properly
what's your openwebui install method?
did you "pip install backend/requirements.txt" without errors?
@abcd678 commented on GitHub (May 25, 2025):
I installed using the python + venv instructions here: https://docs.openwebui.com/getting-started/quick-start/
This does not come with backend folder for openwebui or a requirements.txt (using find / as root)
In my initial message I already showed that rapidocr-onnxruntime is installed, running pip list inside of the venv also shows that the correct version is installed.
(venv) root@OpenWebUI:/home/OpenWebUI/venv# pip show rapidocr-onnxruntime
Name: rapidocr-onnxruntime
Version: 1.4.4
Summary: A cross platform OCR Library based on OnnxRuntime.
Home-page: https://github.com/RapidAI/RapidOCR
Author: SWHL
Author-email: liekkaskono@163.com
License: Apache-2.0
Location: /home/OpenWebUI/venv/lib/python3.11/site-packages
Requires: numpy, onnxruntime, opencv-python, Pillow, pyclipper, PyYAML, Shapely, six, tqdm
Required-by: open-webui
it's also owned by openwebui:openwebui