Charmed Ollama Documentation
Get up and running with large language models.
Ollama in a nutshell
Ollama is an inference engine for large language models.
Ollama is a package manager for large language models.
Ollama is an OpenAI-style HTTP server for large language models.
This charm is suitable for developers and organizations looking to harness the power of large language models in their applications without the complexity of manual setup and configuration.
Ollama exposes an HTTP API with the same format as OpenAI, enabling rapid migration of your application from closed-source models like OpenAI’s to open-source models like Llama and Mistral.
In this documentation
| Tutorial Get started - a hands-on introduction to Charmed Ollama for new users |
How-to guides Step-by-step guides covering key operations and common tasks |
|
| Explanation Discussion and clarification of key topics |
Reference Technical information - specifications, APIs, architecture |
|