Instructions to use keyvan-ai/german-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keyvan-ai/german-ocr with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="keyvan-ai/german-ocr")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("keyvan-ai/german-ocr")
model = AutoModelForMultimodalLM.from_pretrained("keyvan-ai/german-ocr")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keyvan-ai/german-ocr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keyvan-ai/german-ocr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keyvan-ai/german-ocr",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/keyvan-ai/german-ocr

SGLang

How to use keyvan-ai/german-ocr with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "keyvan-ai/german-ocr" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keyvan-ai/german-ocr",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "keyvan-ai/german-ocr" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "keyvan-ai/german-ocr",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use keyvan-ai/german-ocr with Docker Model Runner:
```
docker model run hf.co/keyvan-ai/german-ocr
```

german-ocr / schemas /generic_document.json

Keyven

Kopie von Keyven/german-ocr

fbe2fbc verified about 12 hours ago

Raw

History Blame Contribute Delete

3.23 kB

	{
	"$schema": "https://json-schema.org/draft/2020-12/schema",
	"$id": "german-ocr-3/schemas/generic_document.json",
	"title": "GermanOCR3 Generic Document",
	"description": "Allgemeines deutsches Dokument-Extraktionsschema. Felder dürfen null sein, wenn nicht eindeutig erkennbar.",
	"type": "object",
	"additionalProperties": false,
	"required": ["document_type", "language", "raw_text", "confidence"],
	"properties": {
	"document_type": {
	"description": "z.B. invoice, receipt, letter, form, contract, id_card, other, unknown",
	"type": ["string", "null"]
	},
	"language": {
	"description": "BCP-47 Sprachcode des Dokuments (typisch 'de').",
	"type": "string",
	"default": "de"
	},
	"sender": {
	"type": ["object", "null"],
	"additionalProperties": false,
	"properties": {
	"name": {"type": ["string", "null"]},
	"address": {"type": ["string", "null"]},
	"email": {"type": ["string", "null"]},
	"phone": {"type": ["string", "null"]},
	"tax_id": {"type": ["string", "null"]},
	"vat_id": {"type": ["string", "null"]}
	}
	},
	"recipient": {
	"type": ["object", "null"],
	"additionalProperties": false,
	"properties": {
	"name": {"type": ["string", "null"]},
	"address": {"type": ["string", "null"]},
	"customer_id": {"type": ["string", "null"]}
	}
	},
	"date": {
	"description": "Hauptdatum des Dokuments im Format YYYY-MM-DD, falls eindeutig erkennbar.",
	"type": ["string", "null"]
	},
	"reference_numbers": {
	"type": "array",
	"items": {
	"type": "object",
	"additionalProperties": false,
	"required": ["label", "value"],
	"properties": {
	"label": {"type": "string"},
	"value": {"type": "string"}
	}
	},
	"default": []
	},
	"amounts": {
	"type": "array",
	"items": {
	"type": "object",
	"additionalProperties": false,
	"required": ["label", "value"],
	"properties": {
	"label": {"type": "string"},
	"value": {"type": ["number", "string"]},
	"currency": {"type": ["string", "null"]}
	}
	},
	"default": []
	},
	"tables": {
	"type": "array",
	"default": [],
	"items": {
	"type": "object",
	"additionalProperties": false,
	"required": ["headers", "rows"],
	"properties": {
	"title": {"type": ["string", "null"]},
	"headers": {"type": "array", "items": {"type": "string"}},
	"rows": {
	"type": "array",
	"items": {
	"type": "array",
	"items": {"type": ["string", "number", "null"]}
	}
	}
	}
	}
	},
	"raw_text": {
	"description": "Roher OCR-Text, möglichst layouterhaltend, deutsche Originalschreibweise behalten.",
	"type": ["string", "null"]
	},
	"confidence": {
	"description": "Subjektive Selbsteinschätzung 0..1.",
	"type": ["number", "null"],
	"minimum": 0,
	"maximum": 1
	},
	"notes": {
	"type": "array",
	"items": {"type": "string"},
	"default": []
	}
	}
	}