- Add new "vision" chat mode to the application
- Implement the `visionChatMode` function to handle vision-based chat interactions
- Update the UI to include a new button to toggle the vision chat mode
- Add new translations for the "vision" chat mode tooltip
- Disable certain UI elements when the vision chat mode is active
This commit includes the following improvements:
- Update the `memoryEmbedding` function to use the `PAMemoryVectorStore` instead of the generic `MemoryVectorStore`. This ensures that the vector store is specifically designed for the Page Assist application.
- Modify the `useMessage` hook to use the `PAMemoryVectorStore` type for the `keepTrackOfEmbedding` state.
- Update the `rerankDocs` function to use the `EmbeddingsInterface` type instead of the deprecated `Embeddings` type.
- Add a new `PageAssistVectorStore` class that extends the `VectorStore` interface and provides a custom implementation for the Page Assist application.
These changes improve the handling of memory embeddings and vector stores, ensuring better compatibility and performance within the Page Assist application.
Firefox does not allow extensions to run content scripts on PDF pages, so we have to work around this limitation. This commit adds a workaround that retrieves the PDF URL and type directly from the tab. This ensures that the extension can handle PDFs in Firefox while waiting for the bug in Firefox to be fixed.
Refactor embedding models and their handling to improve performance and simplify the process.
Add a new model selection mechanism, and enhance the UI for model selection, offering clearer and more user-friendly options for embedding models.
Refactor embeddings to use a common model for page assist and RAG, further improving performance and streamlining the workflow.
Adds support for LMStudio models, allowing users to access and use them within the application. This involves:
- Adding new functions to `db/models.ts` to handle LMStudio model IDs and fetch their information from the OpenAI API.
- Modifying the `ollamaFormatAllCustomModels` function to include LMStudio models in the list of available models.
- Introducing a timeout mechanism in `libs/openai.ts` to prevent API requests from hanging.
This change enhances the model selection experience, providing users with a wider range of models to choose from.
This commit introduces a new UI for managing models within the OpenAI integration. This UI allows users to view, add, and delete OpenAI models associated with their OpenAI providers. It includes functionality to fetch and refresh model lists, as well as to search for specific models. These changes enhance the user experience by offering greater control over their OpenAI model interactions.
This commit also includes improvements to the existing OpenAI configuration UI, enabling users to seamlessly manage multiple OpenAI providers and associated models.
