skamenan7 6634b21a76 Merge upstream/main and resolve conflicts ... Resolved merge conflicts in: - Documentation files: updated vector IO provider docs to include both kvstore fields and embedding model configuration - Config files: merged kvstore requirements from upstream with embedding model fields - Dependencies: updated to latest client versions while preserving llama-models dependency - Regenerated lockfiles to ensure consistency All embedding model configuration features preserved while incorporating upstream changes.		2025-07-16 19:57:02 -04:00
..
__init__.py	chore: enable pyupgrade fixes (#1806)	2025-05-01 14:23:50 -07:00
embedding_mixin.py	feat: New OpenAI compat embeddings API (#2314)	2025-05-31 22:11:47 -07:00
inference_store.py	feat: support auth attributes in inference/responses stores (#2389)	2025-06-20 10:24:45 -07:00
litellm_openai_mixin.py	feat: create dynamic model registration for OpenAI and Llama compat remote inference providers (#2745)	2025-07-16 12:49:38 -04:00
model_registry.py	feat: add infrastructure to allow inference model discovery (#2710)	2025-07-14 11:38:53 -07:00
openai_compat.py	fix: Resolve Llama4 tool calling 500 errors (Issue #2584)	2025-07-15 11:47:05 -04:00
prompt_adapter.py	fix: address reviewer feedback - improve conditional imports and remove provider alias logic\n\n- Improve conditional import approach with better documentation\n- Remove provider-specific alias logic from sku_list.py\n- Conditional imports are necessary because llama4 requires torch\n- Addresses @ashwinb and @raghotham feedback while maintaining compatibility	2025-07-15 13:21:33 -04:00
stream_utils.py	feat: drop python 3.10 support (#2469)	2025-06-19 12:07:14 +05:30