# v0.9.32, build 207 (2025-03-xx xx:xx UTC)
- Added the "Community & Code" section to the about page. It includes links to the GitHub repositories and the project website.
- Improved data security by preventing the use of cloud LLMs after confidential data has been retrieved previously.
- Improved the ERI client to expect JSON responses and send JSON requests using camel case.
- Improved the ERI client to raise an error when the server responds with additional JSON data that is not expected.
- Improved the error handling in the ERI data source info dialog in cases where servers respond with an invalid message.
- Improved the error handling for the entire RAG process.
- Improved chat thread persistence after modifications through the RAG process.
- Improved the augmentation and generation part of RAG by passing the augmented data into the system prompt.
- Fixed the chat thread we use for the data retrieval by removing the last block, which is meant to be for the final AI answer.
- Fixed the data source name for ERI data sources when performing data retrieval.
- Fixed the default data source selection when replacing the current chat with a new one.
- Fixed the state of the re-generate button in the chat thread, when no provider is selected or the data security is preventing the use of cloud LLMs.
- Upgraded code dependencies.