vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 19:31:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(ollama): harden native provider routing

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-27 01:01:51 +01:00
parent be56f172ab
commit a3e0674261
18 changed files with 909 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/providers/ollama.md
View File

@@ -318,6 +318,10 @@ Once configured, all your Ollama models are available:
}
```
Custom Ollama provider ids are also supported. When a model ref uses the active
provider prefix, such as `ollama-spark/qwen3:32b`, OpenClaw strips only that
prefix before calling Ollama so the server receives `qwen3:32b`.
## Ollama Web Search
OpenClaw supports **Ollama Web Search** as a bundled `web_search` provider.
@@ -437,7 +441,8 @@ For the full setup and behavior details, see [Ollama Web Search](/tools/ollama-s
<Accordion title="Memory embeddings">
The bundled Ollama plugin registers a memory embedding provider for
[memory search](/concepts/memory). It uses the configured Ollama base URL
and API key.
and API key, calls Ollama's current `/api/embed` endpoint, and batches
multiple memory chunks into one `input` request when possible.
| Property | Value |
| ------------- | ------------------- |