Updates
- Updated MemGPT and Agent Configs: This release makes changes to how MemGPT and agent configurations are stored. These changes will help MemGPT keep track of what settings and with what version an agent was saved with, to help improve cross-version compatibility for agents.
- If you've been using a prior version of MemGPT, you may need to re-run
memgpt configureto update your configuration settings to be compatible with this version.
- If you've been using a prior version of MemGPT, you may need to re-run
- Configurable Presets: Presets have been refactored to allow developers to customize the set of functions and system prompts MemGPT uses.
What's Changed
- Configurable presets to support easy extension of MemGPT's function set by @cpacker in #420
- WebSocket interface and basic
server.pyprocess by @cpacker in #399 - patch
getargspecerror by @cpacker in #440 - always cast
config.context_windowtointbefore use by @cpacker in #444 - Refactor config + determine LLM via
config.model_endpoint_typeby @sarahwooders in #422 - Update config to include
memgpt_versionand re-run configuration for old versions onmemgpt runby @sarahwooders in #450 - Add load and load_and_attach functions to memgpt autogen agent. by @wrmedford in #430
- Update documentation [local LLMs, presets] by @cpacker in #453
- When default_mode_endpoint has a value, it needs to become model_endp… by @kfsone in #452
- Upgrade workflows to Python 3.11 by @sarahwooders in #441
New Contributors
Full Changelog: 0.2.2...0.2.3