Added experimental Retrieval Augmented Generation (RAG) through a local Weaviate server
- Ability to query user inputs through a Weaviate vector database using hybrid search
- Search results are provided to the LLM as contextual information along with the users input
- See the README for more information
Removed Full manual prompting option: the original reason for this is no longer a thing, its not been documented, and looks to have broken in a prior update anyway
Full Changelog: 1.1.3...1.2.0