Add PaddleOCR-VL multimodal model support with Docker dependencies - #2

Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom
copilot/add-paddleocr-vl-support
Draft

Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom
copilot/add-paddleocr-vl-support

Conversation

CopilotAI commented Feb 26, 2026•
edited
Loading

Copy link
Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.

Changes

Dependency Management

  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps

Docker Configuration

  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup

Log Cleanup

  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only

Documentation

  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless

Usage

# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5

Backward Compatibility

Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.

Original prompt

Implemente as seguintes melhorias:

  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:

    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.

  2. Documentação:

    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).

  3. Testes:

    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.

Exemplo de parâmetros válidos:
detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]
recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]

Importante:

  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.

This pull request was created from Copilot chat.

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.

CopilotAIand others added 4 commits February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI changed the title [WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes

tpraxedes commented Feb 26, 2026

Copy link
Copy Markdown

@copilot verifique para corrigir os erros:

2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m
2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.
2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(
2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
2026-02-26T19:05:09.802Z warnings.warn(warning_message)
2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m
2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m
2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]
Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]
Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]
Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]
2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m
2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m
2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]
Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]
Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]
Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]
2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m
2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m
2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]
Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]
Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]
Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]
2026-02-26T19:05:28.095Z INFO: Started server process [1]
2026-02-26T19:05:28.095Z INFO: Waiting for application startup.
2026-02-26T19:05:28.095Z INFO: Application startup complete.
2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK
2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK
2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK
2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error
2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application
2026-02-26T19:05:48.942Z Traceback (most recent call last):
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline
2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline
2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper
2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra
2026-02-26T19:05:48.942Z raise DependencyError(msg)
2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.
2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:
2026-02-26T19:05:48.942Z Traceback (most recent call last):
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call
2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call
2026-02-26T19:05:48.942Z await super().call(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call
2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call
2026-02-26T19:05:48.942Z raise exc
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call
2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call
2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response
2026-02-26T19:05:48.942Z await self.app(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call
2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
2026-02-26T19:05:48.942Z raise exc
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
2026-02-26T19:05:48.942Z await app(scope, receive, sender)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call
2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app
2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle
2026-02-26T19:05:48.942Z await self.app(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app
2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
2026-02-26T19:05:48.942Z raise exc
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
2026-02-26T19:05:48.942Z await app(scope, receive, sender)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app
2026-02-26T19:05:48.942Z response = await f(request)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app
2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function
2026-02-26T19:05:48.942Z return await dependant.call(**values)
2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file
2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)
2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance
2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init
2026-02-26T19:05:48.942Z super().init(**kwargs)
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init
2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()
2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline
2026-02-26T19:05:48.942Z raise RuntimeError(
2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.

@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>

CopilotAI commented Feb 26, 2026

Copy link
Copy Markdown
Author

@copilot verifique para corrigir os erros:

2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...

Fixed in commit c5e3593.

The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.

Changes made:

  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error

To use VL models, install:

pip install 'paddlex[ocr]'

The API now returns a helpful error message instead of crashing:

{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}

Traditional PP-OCR models continue to work without any additional dependencies.

@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes

tpraxedes commented Feb 26, 2026

Copy link
Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose

@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>

CopilotAI commented Feb 26, 2026

Copy link
Copy Markdown
Author

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose

Fixed in commit 9b85cb6.

Changes made:

  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:
    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions

Usage:

docker-compose up -d

VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.

CopilotAIand others added 2 commits February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI changed the title Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others added 3 commits February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI changed the title Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

@tpraxedestpraxedes

Copilot code reviewCopilot

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Add PaddleOCR-VL multimodal model support with Docker dependencies - #2
Draft
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Draft
Add PaddleOCR-VL multimodal model support with Docker dependencies#2
tpraxedes with Copilot wants to merge 13 commits into
masterfrom 
copilot/add-paddleocr-vl-support
Conversation
CopilotAI
commented
Feb 26, 2026•

edited

Loading

Copy link


Copy Markdown

PaddleOCR-VL models require paddlex[ocr] dependencies that weren't in the Docker build, causing runtime DependencyError when attempting to use VL models via API parameters.
Changes
Dependency Management
  • Added paddlex[ocr]>=3.4.0 to requirements.in and requirements.txt
  • Ensures VL models work in Docker deployments without additional installation steps
Docker Configuration
  • Created /root/.paddlex directory in Dockerfile for VL model cache
  • Added paddlex_models persistent volume in docker-compose.yml
  • Increased memory limit to 10GB (VL models require 4-6GB vs 2-3GB for traditional models)
  • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable for faster startup
Log Cleanup
  • Suppressed expected PaddlePaddle/PaddleOCR library warnings in main.py using module-specific filters
  • Warnings about ignored parameters, missing ccache, PyTorch API compatibility are informational only
Documentation
  • Added Docker deployment section to PADDLEOCR_VL_GUIDE.md with volume management and troubleshooting
  • Updated README.md to position Docker as recommended deployment method for VL models
  • Clarified that warnings in logs are expected and harmless
Usage
# docker-compose.ymlvolumes:
- paddleocr_models:/root/.paddleocr # Traditional models
- paddlex_models:/root/.paddlex # VL models
docker-compose up -d
# API call with VL modelGET/ocr/predict-by-path?image_path=doc.jpg&detection_model=PaddleOCR-VL-1.5
Backward Compatibility
Traditional PP-OCR models unaffected. VL models purely additive via optional query parameters.
Original prompt
Implemente as seguintes melhorias:
  1. Suporte opcional ao PaddleOCR-VL-1.5 e PaddleOCR-VL:
    • Permita que os endpoints atuais aceitem, opcionalmente, o uso dos modelos "PaddleOCR-VL-1.5" ou "PaddleOCR-VL" através de detection_model e/ou recognition_model.
    • Se o usuário passar um desses nomes de modelo (ex: detection_model='PaddleOCR-VL-1.5'), o endpoint deve executar a inferência usando a interface nativa do PaddleOCR-VL (ex: PaddleOCRVL), aproveitando as capacidades do modelo VL (incluindo layout, tabelas, gráficos, selos, multilinguagem, etc.).
    • Se os parâmetros detection_model/recognition_model não forem passados ou receberem valores tradicionais (PP-OCR*), o funcionamento permanece inalterado.
    • Não remova nem modifique a lógica dos modelos existentes; apenas adicione o caminho alternativo para PaddleOCR-VL.
  2. Documentação:
    • Atualize a documentação dos endpoints para listar explicitamente os valores válidos para detection_model e recognition_model, incluindo as novas opções PaddleOCR-VL-1.5 e PaddleOCR-VL, além das já suportadas (ex: PP-OCRv5_server_det, PP-OCRv5_server_rec, etc.).
    • Inclua descrição sucinta das características-chave dos modelos VL (suporte a tabelas, fórmulas, selos, 111 idiomas, etc).
  3. Testes:
    • Adicione testes automáticos básicos (ou exemplos de uso em docstring) que comprovem o uso dos modelos VL dentro dos endpoints existentes.
Exemplo de parâmetros válidos:

detection_model: [PP-OCRv5_server_det, PP-OCRv5_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_det, PaddleOCR-VL-1.5, PaddleOCR-VL]

recognition_model: [PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, PP-OCRv4_server_rec, PP-OCRv4_mobile_rec, PaddleOCR-VL-1.5, PaddleOCR-VL]
Importante:
  • Não altere o fluxo padrão das rotas já existentes para quem não usa os modelos VL.
  • Toda lógica de fallback/caminho alternativo deve ser adicionada de forma segura e inofensiva para compatibilidade retroativa.
  • Siga o padrão e arquitetura já existente no projeto.
This pull request was created from Copilot chat.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.
CopilotAIand others
added 4 commits
February 26, 2026 18:57
@tpraxedes
Add PaddleOCR-VL model support to all endpoints
2a30d75
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add comprehensive documentation for VL model support
9f99053
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add implementation summary and prepare for code review
47ec7fe
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Fix VL version detection logic per code review
295423f
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
[WIP] Add optional support for PaddleOCR-VL modelsAdd optional PaddleOCR-VL multimodal model support to all endpointsFeb 26, 2026
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK to True.�[0m

2026-02-26T19:05:09.230Z /app/routers/ocr.py:111: UserWarning: lang and ocr_version will be ignored when model names or model directories are not None.

2026-02-26T19:05:09.231Z ocr_instance = PaddleOCR(

2026-02-26T19:05:09.802Z /usr/local/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md

2026-02-26T19:05:09.802Z warnings.warn(warning_message)

2026-02-26T19:05:10.268Z �[32mCreating model: ('PP-LCNet_x1_0_textline_ori', None)�[0m

2026-02-26T19:05:10.269Z �[32mUsing official model (PP-LCNet_x1_0_textline_ori), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.�[0m

2026-02-26T19:05:14.109Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 6.37it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.34it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.69it/s]

2026-02-26T19:05:14.508Z �[32mCreating model: ('PP-OCRv5_server_det', None)�[0m

2026-02-26T19:05:14.509Z �[32mUsing official model (PP-OCRv5_server_det), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_det.�[0m

2026-02-26T19:05:18.067Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:00, 5.66it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.40it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.76it/s]

2026-02-26T19:05:20.719Z �[32mCreating model: ('PP-OCRv5_server_rec', None)�[0m

2026-02-26T19:05:20.719Z �[32mUsing official model (PP-OCRv5_server_rec), the model files will be automatically downloaded and saved in /root/.paddlex/official_models/PP-OCRv5_server_rec.�[0m

2026-02-26T19:05:24.179Z Fetching 6 files: 0%| | 0/6 [00:00<?, ?it/s]

Fetching 6 files: 17%|█▋ | 1/6 [00:00<00:01, 4.74it/s]

Fetching 6 files: 83%|████████▎ | 5/6 [00:03<00:00, 1.45it/s]

Fetching 6 files: 100%|██████████| 6/6 [00:03<00:00, 1.81it/s]

2026-02-26T19:05:28.095Z INFO: Started server process [1]

2026-02-26T19:05:28.095Z INFO: Waiting for application startup.

2026-02-26T19:05:28.095Z INFO: Application startup complete.

2026-02-26T19:05:28.095Z INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

2026-02-26T19:05:31.274Z INFO: 127.0.0.1:57354 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.633Z INFO: 172.16.1.76:55649 - "GET /docs HTTP/1.1" 200 OK

2026-02-26T19:05:34.717Z INFO: 172.16.1.76:55649 - "GET /openapi.json HTTP/1.1" 200 OK

2026-02-26T19:05:48.939Z INFO: 172.16.1.76:62063 - "POST /ocr/predict-by-file?detection_model=PaddleOCR-VL-1.5&recognition_model=PaddleOCR-VL-1.5 HTTP/1.1" 500 Internal Server Error

2026-02-26T19:05:48.942Z ERROR: Exception in ASGI application

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 105, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z return create_pipeline(config=self._merged_paddlex_config, **kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/inference/pipelines/init.py", line 168, in create_pipeline

2026-02-26T19:05:48.942Z pipeline = BasePipeline.get(pipeline_name)(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 207, in _wrapper

2026-02-26T19:05:48.942Z require_extra(extra, obj_name=pipeline_name, alt=alt)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddlex/utils/deps.py", line 200, in require_extra

2026-02-26T19:05:48.942Z raise DependencyError(msg)

2026-02-26T19:05:48.942Z paddlex.utils.deps.DependencyError: PaddleOCR-VL-1.5 requires additional dependencies. To install them, run pip install "paddlex[ocr]==<PADDLEX_VERSION>" if you’re installing paddlex from an index, or pip install -e "/path/to/PaddleX[ocr]" if you’re installing paddlex locally.

2026-02-26T19:05:48.942Z The above exception was the direct cause of the following exception:

2026-02-26T19:05:48.942Z Traceback (most recent call last):

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi

2026-02-26T19:05:48.942Z result = await app( # type: ignore[func-returns-value]

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call

2026-02-26T19:05:48.942Z return await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/applications.py", line 1054, in call

2026-02-26T19:05:48.942Z await super().call(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/applications.py", line 112, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 187, in call

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/errors.py", line 165, in call

2026-02-26T19:05:48.942Z await self.app(scope, receive, _send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 93, in call

2026-02-26T19:05:48.942Z await self.simple_response(scope, receive, send, request_headers=headers)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/cors.py", line 144, in simple_response

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/middleware/exceptions.py", line 62, in call

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 714, in call

2026-02-26T19:05:48.942Z await self.middleware_stack(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 734, in app

2026-02-26T19:05:48.942Z await route.handle(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 288, in handle

2026-02-26T19:05:48.942Z await self.app(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 76, in app

2026-02-26T19:05:48.942Z await wrap_app_handling_exceptions(app, request)(scope, receive, send)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app

2026-02-26T19:05:48.942Z raise exc

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app

2026-02-26T19:05:48.942Z await app(scope, receive, sender)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/starlette/routing.py", line 73, in app

2026-02-26T19:05:48.942Z response = await f(request)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 301, in app

2026-02-26T19:05:48.942Z raw_response = await run_endpoint_function(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/fastapi/routing.py", line 212, in run_endpoint_function

2026-02-26T19:05:48.942Z return await dependant.call(**values)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 332, in predict_by_file

2026-02-26T19:05:48.942Z ocr_instance = get_ocr_instance(detection_model, recognition_model)

2026-02-26T19:05:48.942Z File "/app/routers/ocr.py", line 79, in get_ocr_instance

2026-02-26T19:05:48.942Z ocr_instance = PaddleOCRVL(

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/paddleocr_vl.py", line 86, in init

2026-02-26T19:05:48.942Z super().init(**kwargs)

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 67, in init

2026-02-26T19:05:48.942Z self.paddlex_pipeline = self._create_paddlex_pipeline()

2026-02-26T19:05:48.942Z File "/usr/local/lib/python3.9/site-packages/paddleocr/_pipelines/base.py", line 107, in _create_paddlex_pipeline

2026-02-26T19:05:48.942Z raise RuntimeError(

2026-02-26T19:05:48.942Z RuntimeError: A dependency error occurred during pipeline creation. Please refer to the installation documentation to ensure all required dependencies are installed.
@tpraxedes
Add error handling and documentation for VL model dependencies
c5e3593
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot verifique para corrigir os erros:
2026-02-26T19:04:57.037Z �[33mChecking connectivity to the model hosters, this may take a while. To bypass this check, set `PADDLE_PDX_D...
Fixed in commit c5e3593.
The error occurred because PaddleOCR-VL models require additional dependencies that weren't installed.
Changes made:
  1. Added proper error handling that returns HTTP 501 with clear installation instructions
  2. Updated documentation (PADDLEOCR_VL_GUIDE.md, README.md) with prominent warnings about the dependency requirement
  3. Added troubleshooting section for this specific error
To use VL models, install:
pip install 'paddlex[ocr]'
The API now returns a helpful error message instead of crashing:
{
"detail": "PaddleOCR-VL requires additional dependencies. Install with: pip install 'paddlex[ocr]'"
}
Traditional PP-OCR models continue to work without any additional dependencies.
@tpraxedes
Improve error handling robustness per code review
95df911
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
tpraxedes
commented
Feb 26, 2026

Copy link


Copy Markdown

@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
@tpraxedes
Add VL dependencies to Docker setup and update documentation
9b85cb6
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
commented
Feb 26, 2026

Copy link


Copy Markdown

Author
@copilot ajuste o projeto para resolver as dependências necessárias, como o Dockerfile e docker-compose
Fixed in commit 9b85cb6.
Changes made:
  1. requirements.in / requirements.txt: Added paddlex[ocr] dependency so VL models work by default
  2. Dockerfile: Creates /root/.paddlex directory and includes VL dependencies in build
  3. docker-compose.yml:

    • Added paddlex_models volume for VL model persistence
    • Increased memory limit to 8GB (VL models need more resources)
    • Added optional PADDLE_PDX_DISABLE_MODEL_SOURCE_CHECK environment variable
  4. Documentation: Updated PADDLEOCR_VL_GUIDE.md and README.md with Docker deployment instructions
Usage:
docker-compose up -d
VL models now work out of the box in Docker. Models are cached in persistent volumes (paddleocr_models and paddlex_models) so they don't need to be re-downloaded after container restarts.
CopilotAIand others
added 2 commits
February 26, 2026 19:17
@tpraxedes
Clarify Docker resource limits and VL dependency notes
6a66f6b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Add version constraint to paddlex and improve documentation clarity
56e600c
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support to all endpointsAdd optional PaddleOCR-VL multimodal model support with complete Docker integrationFeb 26, 2026
CopilotAIand others
added 3 commits
February 26, 2026 19:31
@tpraxedes
Add warning suppression for expected library warnings
91abf9b
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Make warning filters more specific to paddle modules
0894d60
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
@tpraxedes
Use more specific regex patterns and add verification steps
6fb2fc8
Co-authored-by: tpraxedes <53882938+tpraxedes@users.noreply.github.com>
CopilotAI
changed the title
Add optional PaddleOCR-VL multimodal model support with complete Docker integrationAdd PaddleOCR-VL multimodal model support with Docker dependenciesFeb 26, 2026
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment

Reviewers


No reviews


Assignees

@tpraxedestpraxedes
Copilot code reviewCopilot

Labels


None yet


Projects


None yet


Milestone


No milestone


Development

Successfully merging this pull request may close these issues.

2 participants

@tpraxedes