Raglite

Fix

- add and enable OpenAI strict mode (55)
- support embedding with LiteLLM for Ragas (56)

Feat

- improve late chunking and optimize pgvector settings (51)

Feat

- support prompt caching and apply Anthropic's long-context prompt format (52)

Fix

- improve structured output extraction and query adapter updates (34)
- upgrade rerankers and remove flashrank patch (47)
- improve unpacking of keyword search results (46)
- add fallbacks for model info (44)

Feat

- add Chainlit frontend (33)

Fix

- fix optimal chunking edge cases (32)