docs: clarify memory search input type help · openclaw/openclaw@236ca49
steipete
·
2026-04-27
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -1001,7 +1001,7 @@ export const FIELD_HELP: Record<string, string> = {
|
1001 | 1001 | "agents.defaults.memorySearch.model": |
1002 | 1002 | "Embedding model override used by the selected memory provider when a non-default model is required. Set this only when you need explicit recall quality/cost tuning beyond provider defaults.", |
1003 | 1003 | "agents.defaults.memorySearch.inputType": |
1004 | | -"Optional provider-specific `input_type` value forwarded to compatible embedding requests when the same label should apply to both query and document embeddings. For asymmetric providers, prefer queryInputType and documentInputType.", |
| 1004 | +"Use this optional provider-specific `input_type` value when the same label should apply to both query and document embedding requests. For asymmetric providers, prefer queryInputType and documentInputType.", |
1005 | 1005 | "agents.defaults.memorySearch.queryInputType": |
1006 | 1006 | "Optional provider-specific `input_type` value for query-time memory embeddings. Use this with OpenAI-compatible asymmetric embedding endpoints that require a query label.", |
1007 | 1007 | "agents.defaults.memorySearch.documentInputType": |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
