github/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-30 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

memory: wire Gemini embedding dimensions through config

Browse Source
This commit is contained in:
Gustavo Madeira Santana
2026-03-10 20:29:46 -04:00
parent 2bf605cd4e
commit bc70d85474
15 changed files with 230 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/concepts/memory.md
View File

@@ -310,7 +310,7 @@ Notes:
- `remote.baseUrl` is optional (defaults to the Gemini API base URL).
- `remote.headers` lets you add extra headers if needed.
- Default model: `gemini-embedding-001`.
- `gemini-embedding-2-preview` is also supported: multimodal inputs, 8192 token limit, configurable dimensions (768 / 1536 / 3072, default 3072).
- `gemini-embedding-2-preview` is also supported: 8192 token limit and configurable dimensions (768 / 1536 / 3072, default 3072).
#### Gemini Embedding 2 (preview)
@@ -330,8 +330,9 @@ agents: {
```
> **⚠️ Re-index required:** Switching from `gemini-embedding-001` (768 dimensions)
> to `gemini-embedding-2-preview` (3072 dimensions) changes the vector size.
> OpenClaw will automatically reindex when it detects the model change.
> to `gemini-embedding-2-preview` (3072 dimensions) changes the vector size. The same is true if you
> change `outputDimensionality` between 768, 1536, and 3072.
> OpenClaw will automatically reindex when it detects a model or dimension change.
If you want to use a **custom OpenAI-compatible endpoint** (OpenRouter, vLLM, or a proxy),
you can use the `remote` configuration with the OpenAI provider: