Cloudglue makes it easy to turn video into LLM ready data. Official Python SDK for the Cloudglue API.
By using this SDK, you agree to the Cloudglue Terms of Service and acknowledge our Privacy Policy.
You can install the Cloudglue Python SDK using pip:
pip install cloudgluefrom cloudglue import CloudGlue
# Initialize the client
client = CloudGlue(api_key="your_api_key") # Or use CLOUDGLUE_API_KEY env variable
# Define your messages
messages = [
{"role": "user", "content": "What are aligned video captions?"}
]
# Make an API request
response = client.chat.completions.create(
messages=messages,
model="nimbus-001",
collections=["abc123"], # Assumes collection already exists, otherwise create one first then reference here by collection id
)
# Get the generated text
generated_text = response.choices[0].message.content
print(generated_text)- Python 3.10+
- Make (for build tasks)
- Git
Clone the repository and set up the development environment:
git clone https://github.com/aviaryhq/cloudglue-python.git
cd cloudglue-python
brew install openapi-generator
make setup # This will set up the virtual environment
# Initialize the API spec Git submodule
make submodule-initThe OpenAPI specification is maintained in a separate repository and included as a Git submodule:
# Update the API spec to the latest version
make submodule-update
# After updating the spec, regenerate the SDK
make generatemake generate # Generate SDK from OpenAPI spec
make build # Build the packageProject directory structure described below:
cloudglue/
├── __init__.py # Main package initialization
├── client/ # Custom client wrapper code
│ └── main.py # CloudGlue class implementation
└── sdk/ # Auto-generated API code
dist/ # Pre-built package dist
spec/ # Git submodule with OpenAPI specification
└── spec/ # Nested spec directory
└── openapi.json # OpenAPI spec file