host.today/ht-docker-ai
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(paddleocr-vl): add structured HTML output and table parsing for PaddleOCR-VL, update API, tests, and README

Browse Source
This commit is contained in:
Jürgen Kunz
2026-01-18 00:11:17 +00:00
parent 0d8a1ebac2
commit f0d88fcbe0
4 changed files with 486 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

302
readme.md
View File

@@ -1,23 +1,40 @@
# @host.today/ht-docker-ai
# @host.today/ht-docker-ai 🚀
Docker images for AI vision-language models, starting with MiniCPM-V 4.5.
Production-ready Docker images for state-of-the-art AI Vision-Language Models. Run powerful multimodal AI locally with GPU acceleration or CPU fallback—no cloud API keys required.
## Overview
## Issue Reporting and Security
This project provides ready-to-use Docker containers for running state-of-the-art AI vision-language models. Built on Ollama for simplified model management and a consistent REST API.
For reporting bugs, issues, or security vulnerabilities, please visit [community.foss.global/](https://community.foss.global/). This is the central community hub for all issue reporting. Developers who sign and comply with our contribution agreement and go through identification can also get a [code.foss.global/](https://code.foss.global/) account to submit Pull Requests directly.
## Available Images
## 🎯 What's Included
| Tag | Description | Requirements |
|-----|-------------|--------------|
| `minicpm45v` | MiniCPM-V 4.5 with GPU support | NVIDIA GPU, 9-18GB VRAM |
| `minicpm45v-cpu` | MiniCPM-V 4.5 CPU-only | 8GB+ RAM |
| `latest` | Alias for `minicpm45v` | NVIDIA GPU |
| Model | Parameters | Best For | API |
|-------|-----------|----------|-----|
| **MiniCPM-V 4.5** | 8B | General vision understanding, image analysis, multi-image | Ollama-compatible |
| **PaddleOCR-VL** | 0.9B | Document parsing, table extraction, OCR | OpenAI-compatible |
## Quick Start
## 📦 Available Images
### GPU (Recommended)
```
code.foss.global/host.today/ht-docker-ai:<tag>
```
| Tag | Model | Hardware | Port |
|-----|-------|----------|------|
| `minicpm45v` / `latest` | MiniCPM-V 4.5 | NVIDIA GPU (9-18GB VRAM) | 11434 |
| `minicpm45v-cpu` | MiniCPM-V 4.5 | CPU only (8GB+ RAM) | 11434 |
| `paddleocr-vl` / `paddleocr-vl-gpu` | PaddleOCR-VL | NVIDIA GPU | 8000 |
| `paddleocr-vl-cpu` | PaddleOCR-VL | CPU only | 8000 |
---
## 🖼️ MiniCPM-V 4.5
A GPT-4o level multimodal LLM from OpenBMB—handles image understanding, OCR, multi-image analysis, and visual reasoning across 30+ languages.
### Quick Start
**GPU (Recommended):**
```bash
docker run -d \
--name minicpm \
@@ -27,8 +44,7 @@ docker run -d \
code.foss.global/host.today/ht-docker-ai:minicpm45v
```
### CPU Only
**CPU Only:**
```bash
docker run -d \
--name minicpm \
@@ -37,18 +53,16 @@ docker run -d \
code.foss.global/host.today/ht-docker-ai:minicpm45v-cpu
```
## API Usage
> 💡 **Pro tip:** Mount the volume to persist downloaded models (~5GB). Without it, models re-download on every container start.
The container exposes the Ollama API on port 11434.
### List Available Models
### API Examples
**List models:**
```bash
curl http://localhost:11434/api/tags
```
### Generate Text from Image
**Analyze an image:**
```bash
curl http://localhost:11434/api/generate -d '{
"model": "minicpm-v",
@@ -57,60 +71,128 @@ curl http://localhost:11434/api/generate -d '{
}'
```
### Chat with Vision
**Chat with vision:**
```bash
curl http://localhost:11434/api/chat -d '{
"model": "minicpm-v",
"messages": [
{
"role": "user",
"content": "Describe this image in detail",
"images": ["<base64-encoded-image>"]
}
]
"messages": [{
"role": "user",
"content": "Describe this image in detail",
"images": ["<base64-encoded-image>"]
}]
}'
```
## Environment Variables
### Hardware Requirements
| Variable | Default | Description |
|----------|---------|-------------|
| `MODEL_NAME` | `minicpm-v` | Model to pull on startup |
| `OLLAMA_HOST` | `0.0.0.0` | Host address for API |
| `OLLAMA_ORIGINS` | `*` | Allowed CORS origins |
| Variant | VRAM/RAM | Notes |
|---------|----------|-------|
| GPU (int4 quantized) | 9GB VRAM | Recommended for most use cases |
| GPU (full precision) | 18GB VRAM | Maximum quality |
| CPU (GGUF) | 8GB+ RAM | Slower but accessible |
## Hardware Requirements
---
### GPU Variant (`minicpm45v`)
## 📄 PaddleOCR-VL
- NVIDIA GPU with CUDA support
- Minimum 9GB VRAM (int4 quantized)
- Recommended 18GB VRAM (full precision)
- NVIDIA Container Toolkit installed
A specialized 0.9B Vision-Language Model optimized for document parsing. Native support for tables, formulas, charts, and text extraction in 109 languages.
### CPU Variant (`minicpm45v-cpu`)
### Quick Start
- Minimum 8GB RAM
- Recommended 16GB+ RAM for better performance
- No GPU required
**GPU:**
```bash
docker run -d \
--name paddleocr \
--gpus all \
-p 8000:8000 \
-v hf-cache:/root/.cache/huggingface \
code.foss.global/host.today/ht-docker-ai:paddleocr-vl
```
## Model Information
**CPU:**
```bash
docker run -d \
--name paddleocr \
-p 8000:8000 \
-v hf-cache:/root/.cache/huggingface \
code.foss.global/host.today/ht-docker-ai:paddleocr-vl-cpu
```
**MiniCPM-V 4.5** is a GPT-4o level multimodal large language model developed by OpenBMB.
### OpenAI-Compatible API
- **Parameters**: 8B (Qwen3-8B + SigLIP2-400M)
- **Capabilities**: Image understanding, OCR, multi-image analysis
- **Languages**: 30+ languages including English, Chinese, French, Spanish
PaddleOCR-VL exposes a fully OpenAI-compatible `/v1/chat/completions` endpoint:
## Docker Compose Example
```bash
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "paddleocr-vl",
"messages": [{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "data:image/png;base64,<base64>"}},
{"type": "text", "text": "Table Recognition:"}
]
}],
"max_tokens": 8192
}'
```
### Task Prompts
| Prompt | Output | Use Case |
|--------|--------|----------|
| `OCR:` | Plain text | General text extraction |
| `Table Recognition:` | Markdown table | Invoices, bank statements, spreadsheets |
| `Formula Recognition:` | LaTeX | Math equations, scientific notation |
| `Chart Recognition:` | Description | Graphs and visualizations |
### API Endpoints
| Endpoint | Method | Description |
|----------|--------|-------------|
| `/health` | GET | Health check with model/device info |
| `/formats` | GET | Supported image formats and input methods |
| `/v1/models` | GET | List available models |
| `/v1/chat/completions` | POST | OpenAI-compatible chat completions |
| `/ocr` | POST | Legacy OCR endpoint |
### Image Input Methods
PaddleOCR-VL accepts images in multiple formats:
```javascript
// Base64 data URL
"data:image/png;base64,iVBORw0KGgo..."
// HTTP URL
"https://example.com/document.png"
// Raw base64
"iVBORw0KGgo..."
```
**Supported formats:** PNG, JPEG, WebP, BMP, GIF, TIFF
**Optimal resolution:** 1080p–2K. Images are automatically scaled for best results.
### Performance
| Mode | Speed per Page |
|------|----------------|
| GPU (CUDA) | 2–5 seconds |
| CPU | 30–60 seconds |
---
## 🐳 Docker Compose
```yaml
version: '3.8'
services:
# General vision tasks
minicpm:
image: code.foss.global/host.today/ht-docker-ai:minicpm45v
container_name: minicpm
ports:
- "11434:11434"
volumes:
@@ -124,11 +206,50 @@ services:
capabilities: [gpu]
restart: unless-stopped
# Document parsing / OCR
paddleocr:
image: code.foss.global/host.today/ht-docker-ai:paddleocr-vl
ports:
- "8000:8000"
volumes:
- hf-cache:/root/.cache/huggingface
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
restart: unless-stopped
volumes:
ollama-data:
hf-cache:
```
## Building Locally
---
## ⚙️ Environment Variables
### MiniCPM-V 4.5
| Variable | Default | Description |
|----------|---------|-------------|
| `MODEL_NAME` | `minicpm-v` | Ollama model to pull on startup |
| `OLLAMA_HOST` | `0.0.0.0` | API bind address |
| `OLLAMA_ORIGINS` | `*` | Allowed CORS origins |
### PaddleOCR-VL
| Variable | Default | Description |
|----------|---------|-------------|
| `MODEL_NAME` | `PaddlePaddle/PaddleOCR-VL` | HuggingFace model ID |
| `SERVER_HOST` | `0.0.0.0` | API bind address |
| `SERVER_PORT` | `8000` | API port |
---
## 🔧 Building from Source
```bash
# Clone the repository
@@ -142,6 +263,77 @@ cd ht-docker-ai
./test-images.sh
```
## License
---
MIT - Task Venture Capital GmbH
## 🏗️ Architecture Notes
### Dual-VLM Consensus Strategy
For production document extraction, consider using both models together:
1. **Pass 1:** MiniCPM-V visual extraction (images → JSON)
2. **Pass 2:** PaddleOCR-VL table recognition (images → markdown → JSON)
3. **Consensus:** If results match → Done (fast path)
4. **Pass 3+:** Additional visual passes if needed
This dual-VLM approach catches extraction errors that single models miss.
### Why This Works
- **Different architectures:** Two independent models cross-validate each other
- **Specialized strengths:** PaddleOCR-VL excels at tables; MiniCPM-V handles general vision
- **Native processing:** Both VLMs see original images—no intermediate HTML/structure loss
---
## 🔍 Troubleshooting
### Model download hangs
```bash
docker logs -f <container-name>
```
Model downloads can take several minutes (~5GB for MiniCPM-V).
### Out of memory
- **GPU:** Use the CPU variant or upgrade VRAM
- **CPU:** Increase container memory: `--memory=16g`
### API not responding
1. Check container health: `docker ps`
2. Review logs: `docker logs <container>`
3. Verify port: `curl localhost:11434/api/tags` or `curl localhost:8000/health`
### Enable NVIDIA GPU support on host
```bash
# Install NVIDIA Container Toolkit
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker
```
---
## License and Legal Information
This repository contains open-source code licensed under the MIT License. A copy of the license can be found in the [LICENSE](./LICENSE) file.
**Please note:** The MIT License does not grant permission to use the trade names, trademarks, service marks, or product names of the project, except as required for reasonable and customary use in describing the origin of the work and reproducing the content of the NOTICE file.
### Trademarks
This project is owned and maintained by Task Venture Capital GmbH. The names and logos associated with Task Venture Capital GmbH and any related products or services are trademarks of Task Venture Capital GmbH or third parties, and are not included within the scope of the MIT license granted herein.
Use of these trademarks must comply with Task Venture Capital GmbH's Trademark Guidelines or the guidelines of the respective third-party owners, and any usage must be approved in writing. Third-party trademarks used herein are the property of their respective owners and used only in a descriptive manner, e.g. for an implementation of an API or similar.
### Company Information
Task Venture Capital GmbH
Registered at District Court Bremen HRB 35230 HB, Germany
For any legal inquiries or further information, please contact us via email at hello@task.vc.
By using this repository, you acknowledge that you have read this section, agree to comply with its terms, and understand that the licensing of the code does not imply endorsement by Task Venture Capital GmbH of any derivative works.