A command-line interface (CLI) tool for interacting with models via Ollama.
clank is a lightweight CLI utility designed to simplify the process of working with AI models. It allows users to list available models, generate responses using specific models, and customize prompts with images, system instructions, and more. This tool is ideal for developers, researchers, and enthusiasts looking to leverage AI models efficiently.
clank [command]Use clank [command] --help to explore detailed usage and flags for each command.
- completion: Generate autocompletion scripts for supported shells (e.g., bash, zsh).
- help: Display help information for any command.
- list: List all models available for prompting.
- prompt: Prompt a model with user-defined instructions and parameters.
- version: Display the current version of the tool.
| Flag | Description |
|---|---|
| -h, --help | Display help information for the current command. |
| --debug | Show messages meant for debugging |
clank prompt [flags]| Flag | Description |
|---|---|
-i, --image |
Images to include in the user prompt (accepts multiple values). |
-m, --model |
Model to use for prompting. |
--prefix |
Required prefix for the model's response. |
-s, --system |
System prompt to guide the model's behavior. |
-t, --template |
Template for system and user prompts (custom formatting). |
--tool |
URL or command for MCP tool (e.g., http://... for streaming, sse+http://... for Server-Sent Events). |
--unload |
Unload the model immediately after generation. |
-u, --user |
User prompt to send to the model. |
clank listclank prompt "What is the capital of France?"clank prompt -m llama2 -s "You are a helpful assistant" -u "Explain quantum computing in simple terms."clank prompt -m llama2 -i image1.png "Describe the content of the image."Contributions are welcome! Please open an issue or submit a pull request on GitHub for any improvements, bug fixes, or feature requests.
This project is licensed under the MIT License. See the LICENSE file for details.