0.5.0

• Add support for forcing the model to reply with a valid JSON object

0.4.3

• Fix the type of stop option. This allows using it through the llm Python API; however, it's not clear how to pass it through the CLI.

0.4.2

• Ignore KeyError when iterating through response messages in streaming mode

0.4.1

• Prevent inability to communicate with Ollama server from failing the entire llm CLI

0.4.0

• Add missing pydantic dependency

0.3.0

• Add support for specifying Ollama modelfile parameters as LLM model options

0.2.0

• Switch to using official Ollama Python library instead of raw HTTP API
• Automatically create aliases for identical models with different names

0.1.0

Initial release.