2.0.1

Minor visual updates

2.0.0

🔥 Biggest update ever!

Moved configuration to AI Providers — this allows to use only one plugin to setup any AI providers for all plugins at once (someday).
All existing providers must be semi-automatically migrated after AI Providers installation. If it's not — try to restart Obsidian and create an issue.

1.14.7

Fixed mime types for images, removed context optimizations for Ollama provider when it's an image in the selected text.

1.14.6

Fixed issue with parsing OpenRouter's requests.

1.14.5

Increased threshold when in next call context size can be deoptimized in order to reduce VRAM consumption. Closes #54

1.14.4

Changed default URL for OpenAI like providers to v1/
Added necessary headers to embeddings request

1.14.3

Fixed delay between first load and showing settings tab. Closes #40

1.14.2

Changed heuristic for setting the context length of the requests introduced in 1.12.0. Previously it could cause problems with requests larger than 2048 tokens.

1.14.1

Fixed PDF caching. It didn't work in 1.14.0 if you updated from 1.13+
Increased Context cap from 7000 to 10000 characters for very long requests.

1.14.0

Added nice ✨Enhancing loader for embedding process

Added PDF caching. No more waiting of parsing PDFs.

Limited Context to 7000 characters. It should be enough for anyone. This will provide more precise responses for Enhanced Actions.