github/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-04-18 16:37:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(memory): default batch embeddings to off

Browse Source 
Disables async batch embeddings by default for memory indexing; batch remains opt-in via agents.defaults.memorySearch.remote.batch.enabled.

(#13069) Thanks @mcinteerj.

Co-authored-by: Jake McInteer <mcinteerj@gmail.com>
This commit is contained in:
Jake
2026-02-10 17:31:58 +13:00
committed by GitHub
parent 5c62e4d51b
commit 757522fb48
5 changed files with 8 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/concepts/memory.md
View File

@@ -302,9 +302,9 @@ Fallbacks:
- `memorySearch.fallback` can be `openai`, `gemini`, `local`, or `none`.
- The fallback provider is only used when the primary embedding provider fails.
Batch indexing (OpenAI + Gemini):
Batch indexing (OpenAI + Gemini + Voyage):
- Enabled by default for OpenAI and Gemini embeddings. Set `agents.defaults.memorySearch.remote.batch.enabled = false` to disable.
- Disabled by default. Set `agents.defaults.memorySearch.remote.batch.enabled = true` to enable for large-corpus indexing (OpenAI, Gemini, and Voyage).
- Default behavior waits for batch completion; tune `remote.batch.wait`, `remote.batch.pollIntervalMs`, and `remote.batch.timeoutMinutes` if needed.
- Set `remote.batch.concurrency` to control how many batch jobs we submit in parallel (default: 2).
- Batch mode applies when `memorySearch.provider = "openai"` or `"gemini"` and uses the corresponding API key.