Repository navigation
fix(embeddings): 语义层在慢速 CPU 模型上也能补齐向量 - #12
Merged
Merged
Conversation
线上 seed-SER9 上 bge-m3 跑在繁忙服务器的 CPU 上，每条约 3.5 秒：一批 16 条要 60 秒，超过 15 秒超时，后台补齐每次都失败， 向量一直是 0。 - 后台补齐改为每批 4 条，超时按条数放宽（每条 30 秒），新技能优先 - 查询向量单独用较短的超时（ASH_EMBED_QUERY_TIMEOUT_MS，默认 8 秒），超时就只用文本比对，ash suggest 不会被慢模型拖住 - 回归测试：慢速假向量服务 + 很短的超时，旧代码下补不上向量 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
问题
#11 部署后，线上日志出现
embeddings: The operation was aborted due to timeout，56 个技能的向量一直是 0。实测 seed-SER9 上 bge-m3 跑在 CPU 上（服务器负载约 12）：1 条约 5.5 秒，4 条约 14 秒，16 条约 60 秒。后台补齐每批 16 条、超时 15 秒，所以每次都失败。本地 Mac 用 GPU 很快，沙盒验证时没有暴露这个问题。
修复
ash suggest）单独用较短的超时ASH_EMBED_QUERY_TIMEOUT_MS（默认 8 秒），超时就只用文本比对。验证
🤖 Generated with Claude Code