BLIP (Bootstrapping Language Image Pre-training) is a technique to improve the way AI models understand and process the relationship between images and textual descriptions.

This is a BentoML example project, demonstrating how to build an image captioning inference API server, using the BLIP model. See here for a full list of BentoML example projects.

git clone https://github.com/bentoml/BentoBlip.git
cd BentoBlip

# Recommend Python 3.11
pip install -r requirements.txt

We have defined a BentoML Service in service.py. Run bentoml serve in your project directory to start the Service.

$ bentoml serve .

2024-01-02T08:32:34+0000 [INFO] [cli] Prometheus metrics for HTTP BentoServer from "service:BlipImageCaptioning" can be accessed at http://localhost:3000/metrics.
2024-01-02T08:32:35+0000 [INFO] [cli] Starting production HTTP BentoServer from "service:BlipImageCaptioning" listening on http://localhost:3000 (Press CTRL+C to quit)
Model blip loaded device: cuda

The Service is accessible at http://localhost:3000. You can interact with it using the Swagger UI or in other different ways:

CURL

curl -s -X POST \
    -F txt='unicorn at sunset' \
    -F '[email protected]' \
    http://localhost:3000/generate

Python client

import bentoml
from pathlib import Path

with bentoml.SyncHTTPClient("http://localhost:3000") as client:
    result = client.generate(
        img=Path("demo.jpg"),
        txt="unicorn at sunset",
    )

Expected output:

unicorn at sunset by a pond with a beautiful landscape in the background, with a reflection of the sun in the water

For detailed explanations of the Service code, see BLIP: Image captioning.

After the Service is ready, you can deploy the application to BentoCloud for better management and scalability. Sign up if you haven't got a BentoCloud account.

Make sure you have logged in to BentoCloud, then run the following command to deploy it.

bentoml deploy .

Once the application is up and running on BentoCloud, you can access it via the exposed URL.

Note: For custom deployment in your own infrastructure, use BentoML to generate an OCI-compliant image.