Chukwuma Nwaugha

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

response = client.chat.completions.create(
    model="paddlepaddle/paddleocr-vl",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.receipt/playground/2.jpg"
                    },
                },
            ],
        }
    ],
    extra_body={"method": "table"},
)

print(response.choices[0].message.content)

curl https://gateway.vlm.run/v1/openai/chat/completions \
  -X POST \
  -H "Authorization: Bearer <VLMRUN_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paddlepaddle/paddleocr-vl",
    "method": "table",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "image_url",
            "image_url": {
              "url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/document.receipt/playground/2.jpg"
            }
          }
        ]
      }
    ]
  }'

pip install vlmrun

vlmrun gw models
vlmrun config set --api-key 'vlmrun' # anon-user, rate-limited
vlmrun gw chat <doc>.pdf -m paddleocr/pp-ocrv6

vlmrun gw chat <doc>.pdf -m zai-org/glm-ocr
vlmrun gw chat <doc>.pdf -m zai-org/glm-ocr --json-mode
vlmrun gw chat <doc>.pdf -m deepseek-ai/deepseek-ocr-2
vlmrun gw chat <doc>.pdf -m rednote-hilab/dots.mocr