- Introduce save / load functionality for
Conversation
.
- General improvements.
- Remove default max-tokens for OpenAI provider.
- Update default model for Amazon provider.
- Improved logging to handle streaming functions.
- Add streaming support (set
stream=True
togenerate_text
). conv.prepend_system_message
now uses system role by default.- Add
provider.supports_streaming
property. - Add
provider.supports_structured_response
property. - General improvements.
- Add
cached_property
to Amazon provider.
- Add Amazon Bedrock provider.
- Make all provider optional dependencies. Use
$ pip install 'simplemind[full]'
to install all providers. - General improvements.
- Add
logger
decorator. - Add
sm.enable_logfire()
function. - General improvements.
- Add
sm.Plugin
syntax sugar. - Improvements to Anthropic provider, related to max tokens.
- General improvements.
- Add tests for structured response.
- Add
llm_model
tostructured_response
.
- Add Gemini provider.
- Add structured response to Gemini provider.
- Support for Python 3.10.
- Introduce
Session
class to manage repeatability. - General improvements.
- Make Conversation a context manager.
- Add more robust conversation plugin hooks — replace
send_hook
withpre_send_hook
andpost_send_hook
. - Change plugin hooks to try/except NotImplementedError.
- Implement 'did you mean' with provider names. Can do this eventually with model names, as well.
- Add ollama provider.
- Fix Groq provider.
- Initial release.