Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

ollama-memory-embeddings

bởi vidarbrekke

Coding Agents & IDEs
1.2kLượt tải do clawskills.sh công bố
3Sao
2Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Configure OpenClaw memory search to use Ollama as the embeddings server (OpenAI-compatible /v1/embeddings) instead.

Mô tả

Kỹ năng này làm gì

Configures OpenClaw memory search to use Ollama as the embeddings server via its OpenAI-compatible /v1/embeddings endpoint, replacing the built-in node-llama-cpp local GGUF loader. Supports multiple embedding models, optional import of existing local GGUFs into Ollama, config drift enforcement, and a launchd watchdog for auto-healing.

Offloading embedding generation to Ollama avoids in-process GGUF loading overhead while keeping all data local, and the drift watchdog ensures config stays consistent across gateway restarts.

Khi nào nên dùng

  • Switching OpenClaw memory search from local GGUF loading to Ollama embeddings
  • Selecting a different embedding model without manually editing config
  • Importing an existing local embedding GGUF into Ollama for reuse
  • Running scheduled config drift checks to keep embedding settings consistent
  • Rebuilding the memory index after changing embedding providers

Quy trình ví dụ

ĐẦU VÀO

User runs install.sh to switch OpenClaw memory search from built-in GGUF to Ollama

AGENT
  1. 1

    Verifies Ollama is installed and reachable at 127.0.0.1:11434

  2. 2

    Prompts user to select an embedding model such as nomic-embed-text or embeddinggemma

  3. 3

    Updates agents.defaults.memorySearch in OpenClaw config with provider, model, baseUrl, and apiKey fields

  4. 4

    Optionally triggers a memory reindex if the embedding fingerprint changed

  5. 5

    Calls the Ollama embeddings endpoint and validates the response to confirm setup

ĐẦU RA

OpenClaw memory search uses Ollama for embedding vector generation, with config backed up and verified

Yêu cầu

  • Ollama installed and running locally

Cài đặt

clawhub install vidarbrekke/ollama-memory-embeddings

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết