You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/reference/memory-config.md
+5Lines changed: 5 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -58,6 +58,11 @@ explicitly to use Gemini, Voyage, Mistral, DeepInfra, Bedrock, GitHub Copilot,
58
58
Ollama, a local GGUF model, or an OpenAI-compatible `/v1/embeddings` endpoint.
59
59
Legacy configs that still say `provider: "auto"` resolve to `openai`.
60
60
61
+
If OpenAI embeddings are unreachable from your network, memory recall fails open
62
+
instead of blocking the turn. Set the existing `memorySearch.provider` field to a
63
+
reachable local, Ollama, regional, or OpenAI-compatible provider to restore
64
+
semantic ranking.
65
+
61
66
### Custom provider ids
62
67
63
68
`memorySearch.provider` can point at a custom `models.providers.<id>` entry for memory-specific provider adapters such as `ollama`, or for OpenAI-compatible model APIs such as `openai-responses` / `openai-completions`. OpenClaw resolves that provider's `api` owner for the embedding adapter while preserving the custom provider id for endpoint, auth, and model-prefix handling. This lets multi-GPU or multi-host setups dedicate memory embeddings to a specific local endpoint:
0 commit comments