TEI - Text Embeddings Inference

Lightweight embedding service for Clawdbot memory search.

Overview

Runs HuggingFace Text Embeddings Inference (TEI) on CPU to provide OpenAI-compatible embeddings for semantic memory search.

• Model: sentence-transformers/all-MiniLM-L6-v2 (~90MB, 384 dimensions)
• Endpoint: http://text-embeddings:8080/v1/embeddings
• No GPU required

Deploy

oc new-project tei
oc apply -f deployment.yaml

Clawdbot Config

Add to ~/.clawdbot/clawdbot.json:

{
  "agents": {
    "defaults": {
      "memorySearch": {
        "enabled": true,
        "provider": "openai",
        "model": "sentence-transformers/all-MiniLM-L6-v2",
        "remote": {
          "baseUrl": "http://text-embeddings.tei.svc.cluster.local:8080/v1/",
          "apiKey": "not-needed"
        }
      }
    }
  }
}

Resources

• Memory: 512Mi request, 1Gi limit
• CPU: 250m request, 1000m limit
• Storage: 1Gi PVC for model cache

Test

curl -X POST http://text-embeddings:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{"input": "Hello world", "model": "sentence-transformers/all-MiniLM-L6-v2"}'