WeKnora/internal/agent
wizardchen 4c66be1be0 feat: enhance knowledge search by resolving embedding model keys
- Introduced a new method to resolve embedding model IDs to their actual identity keys (name + endpoint), enabling optimal grouping of knowledge bases across different tenants.
- Updated the concurrent search functionality to utilize the resolved model keys, improving the efficiency of query embedding computations.
- Refactored search target grouping to reduce redundant API calls and enhance performance during hybrid searches.

These changes significantly improve the knowledge search process by ensuring that embeddings are computed efficiently and reused across multiple knowledge bases sharing the same underlying model.
2026-03-13 20:54:25 +08:00
..
skills feat: adapt preloaded skills to smart-reasoning agent 2026-02-04 20:08:49 +08:00
tools feat: enhance knowledge search by resolving embedding model keys 2026-03-13 20:54:25 +08:00
const.go refactor: Remove agent_test command-line tool and associated files to streamline project structure and eliminate unused components 2025-12-01 17:24:57 +08:00
engine.go feat: implement image upload and multimodal support 2026-03-12 10:32:26 +08:00
prompts.go feat: implement image upload and multimodal support 2026-03-12 10:32:26 +08:00