Releases: mindflowai/mindflow
Releases · mindflowai/mindflow
Fix break in login and improve comments in chat command.
Fix conversation history bug.
The most recent message in the conversation was not being used as context.
Streaming responses from OpenAI. Lazy importing.
Asynchronous runtime, performance and quality improvements.
Implemented asynchronous runtime to improve performance, and also made other performance improvements to the mf diff functionality which also improves performance and quality on the commit and pr commands. This release also comes with a big refactoring of the code base, and is starting to separate out the client-side logic (CLI) from the core library - i.e. the stuff for document segmentation, chat history management, indexing, and managing API requests to GPT.
Improve code quality and performance.
- Small refactors
- Improved ConfiguredModel and MindFlowModel abstractions for clarity, extensibility, and performance.
Patching last release.
Merge pull request #123 from mindflowai/patch Patch broken release
General code quality and performance improvements. Refactored codebase.
v0.5.0 Update version to 0.5.0 and fix save method in json store_traits: Co-…
Refactor, Include Pinecone Support, Update Indexing Performance and Accuracy. Ability to use Anthropic models.
Big Release! This one deserves 0.4.0.
- Improved indexing and query performance.
- Use Pinecone to store vectors for speed and scale.
- Refactor the codebase to be more clean and generic.
- Add support for Anthropic's Claude and Claude Instance models.
Fix Store issues and add commit co-author
v0.3.19 Updated version to 0.3.19 and made minor formatting changes to commit…
GPT 4, Config, Slight indexing performance boost
- Added GPT 4 and configuration for the model used to generate MindFlow responses.
- Improved performance and generalization of the object model.