WeKnora/internal/models
wizardchen 9f4fb39e10 feat(chat): introduce provider-specific request customizers and specs
- Added a new `ProviderSpec` struct to define provider-specific behaviors for chat completions.
- Implemented request and endpoint customizers for various providers including Qwen3, LKEAP, DeepSeek, and Generic.
- Refactored the `NewRemoteChat` function to utilize the new provider specs for customizing requests based on the provider and model name.
- Removed legacy chat implementations for LKEAP, NVIDIA, DeepSeek, and Qwen, consolidating their logic into the new structure.
2026-03-25 22:08:29 +08:00
..
chat feat(chat): introduce provider-specific request customizers and specs 2026-03-25 22:08:29 +08:00
embedding fix: enforce 7500 char limit in chunker to prevent embedding API errors 2026-03-15 23:59:34 +08:00
provider feat(provider): add Novita AI as LLM provider 2026-03-24 22:10:42 +08:00
rerank feat: enhance multimodal support and image handling 2026-03-16 02:26:47 +08:00
utils refactor: Update function signatures across multiple files to improve readability by adding context parameters and enhancing code structure 2025-11-28 16:17:52 +08:00
vlm feat: implement image upload and multimodal support 2026-03-16 02:26:47 +08:00