mirror of https://github.com/openclaw/openclaw.git synced 2026-07-14 02:36:03 +00:00

Files

liuhao1024 94e6255666 feat(memory): apply outputDimensionality truncation to local GGUF embeddings (fixes #58765 ) (#93758 )

* feat(memory): apply outputDimensionality truncation to local GGUF embeddings

The outputDimensionality config field was passed through to the local
embedding provider but never applied. Local GGUF models (e.g.
Qwen3-Embedding-0.6B) always returned their full dimension vector.

Apply slice(0, N) after normalization so MRL-capable models can benefit
from dimension truncation — matching the behavior already supported by
Gemini embedding-2 and OpenAI providers.

Fixes #58765

* fix(memory): preserve local embedding dimensions through worker

---------

Co-authored-by: Vincent Koc <25068+vincentkoc@users.noreply.github.com>

2026-06-17 05:05:49 +08:00

src

feat(memory): apply outputDimensionality truncation to local GGUF embeddings (fixes #58765 ) (#93758 )

2026-06-17 05:05:49 +08:00

index.test.ts

feat(memory): apply outputDimensionality truncation to local GGUF embeddings (fixes #58765 ) (#93758 )

2026-06-17 05:05:49 +08:00

index.ts

…

npm-shrinkwrap.json

chore: set version 2026.6.9

2026-06-16 19:54:07 +01:00

openclaw.plugin.json

…

package.json

chore: set version 2026.6.9

2026-06-16 19:54:07 +01:00

README.md

fix(release): harden plugin package preflight

2026-06-15 14:23:57 +08:00

README.md

@openclaw/llama-cpp-provider

Official llama.cpp embedding provider for OpenClaw.

This plugin runs local GGUF embedding models through node-llama-cpp.

Install

openclaw plugins install @openclaw/llama-cpp-provider

Restart the Gateway after installing or updating the plugin. Use Node 24 for native installs and updates.

Configure

Set agents.defaults.memorySearch.provider to local. By default, the plugin downloads and uses the EmbeddingGemma GGUF model. Configure agents.defaults.memorySearch.local.modelPath to use another local path, Hugging Face model URI, or HTTPS model URL.

Package

Plugin id: llama-cpp
Package: @openclaw/llama-cpp-provider
Minimum OpenClaw host: 2026.6.2