vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 15:10:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(memory): resolve custom embedding provider ids

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-28 03:10:57 +01:00
parent 632b0fd580
commit a0a0ab4d9e
9 changed files with 231 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/concepts/memory-search.md
View File

@@ -29,6 +29,10 @@ explicitly:
}
```
For multi-endpoint setups, `provider` can also be a custom
`models.providers.<id>` entry, such as `ollama-5080`, when that provider sets
`api: "ollama"` or another embedding adapter owner.
For local embeddings with no API key, install the optional `node-llama-cpp`
runtime package next to OpenClaw and use `provider: "local"`.

2
docs/providers/ollama.md
View File

@@ -25,7 +25,7 @@ Ollama provider config uses `baseUrl` as the canonical key. OpenClaw also accept
Remote public hosts and Ollama Cloud (`https://ollama.com`) require a real credential through `OLLAMA_API_KEY`, an auth profile, or the provider's `apiKey`.
</Accordion>
<Accordion title="Custom provider ids">
Custom provider ids that set `api: "ollama"` follow the same rules. For example, an `ollama-remote` provider that points at a private LAN Ollama host can use `apiKey: "ollama-local"` and sub-agents will resolve that marker through the Ollama provider hook instead of treating it as a missing credential.
Custom provider ids that set `api: "ollama"` follow the same rules. For example, an `ollama-remote` provider that points at a private LAN Ollama host can use `apiKey: "ollama-local"` and sub-agents will resolve that marker through the Ollama provider hook instead of treating it as a missing credential. Memory search can also set `agents.defaults.memorySearch.provider` to that custom provider id so embeddings use the matching Ollama endpoint.
</Accordion>
<Accordion title="Memory embedding scope">
When Ollama is used for memory embeddings, bearer auth is scoped to the host where it was declared:

39
docs/reference/memory-config.md
View File

@@ -46,12 +46,12 @@ See [Active Memory](/concepts/active-memory) for the activation model, plugin-ow
## Provider selection
| Key | Type | Default | Description |
| ---------- | --------- | ---------------- | -------------------------------------------------------------------------------------------------------------------------- |
| `provider` | `string` | auto-detected | Embedding adapter ID: `bedrock`, `deepinfra`, `gemini`, `github-copilot`, `local`, `mistral`, `ollama`, `openai`, `voyage` |
| `model` | `string` | provider default | Embedding model name |
| `fallback` | `string` | `"none"` | Fallback adapter ID when the primary fails |
| `enabled` | `boolean` | `true` | Enable or disable memory search |
| Key | Type | Default | Description |
| ---------- | --------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `provider` | `string` | auto-detected | Embedding adapter ID such as `bedrock`, `deepinfra`, `gemini`, `github-copilot`, `local`, `mistral`, `ollama`, `openai`, or `voyage`; may also be a configured `models.providers.<id>` whose `api` points at one of those adapters |
| `model` | `string` | provider default | Embedding model name |
| `fallback` | `string` | `"none"` | Fallback adapter ID when the primary fails |
| `enabled` | `boolean` | `true` | Enable or disable memory search |
### Auto-detection order
@@ -86,6 +86,33 @@ When `provider` is not set, OpenClaw selects the first available:
`ollama` is supported but not auto-detected (set it explicitly).
### Custom provider ids
`memorySearch.provider` can point at a custom `models.providers.<id>` entry. 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:
```json5
{
models: {
providers: {
"ollama-5080": {
api: "ollama",
baseUrl: "http://gpu-box.local:11435",
apiKey: "ollama-local",
models: [{ id: "qwen3-embedding:0.6b" }],
},
},
},
agents: {
defaults: {
memorySearch: {
provider: "ollama-5080",
model: "qwen3-embedding:0.6b",
},
},
},
}
```
### API key resolution
Remote embeddings require an API key. Bedrock uses the AWS SDK default credential chain instead (instance roles, SSO, access keys).