search results on default mode missing embedding

[esteban-serfe]

Using the default configuration when setting up the LocalAIG system with the default confirm from the example: https://github.com/mudler/LocalAGI/blob/main/docker-compose.yaml

• Entered to local recall interface
• Created a new collection
• Added a 4k txt file into a collection (SecurityAuditCheatSheet.txt)
• Search from the locall recall search interface on an npm vendor name that lives inside the txt file and have only one occurrence in the whole file.

All 5 search similarities have the same value and the embedded are empty.

Result #1
{
  "ID": "14",
  "Metadata": {
    "source": "SecurityAuditCheatSheet.txt",
    "type": "file"
  },
  "Embedding": null,
  "Content": ".......",
  "Similarity": 0.99999964
}
Result #2
{
  "ID": "16",
  "Metadata": {
    "source": "SecurityAuditCheatSheet.txt",
    "type": "file"
  },
  "Embedding": null,
  "Content": "........",
  "Similarity": 0.99999964
}
Result #3
{
  "ID": "15",
  "Metadata": {
    "source": "SecurityAuditCheatSheet.txt",
    "type": "file"
  },
  "Embedding": null,
  "Content": ".......",
  "Similarity": 0.99999964
}
Result #4
{
  "ID": "13",
  "Metadata": {
    "source": "SecurityAuditCheatSheet.txt",
    "type": "file"
  },
  "Embedding": null,
  "Content": "......",
  "Similarity": 0.99999964
}
Result #5
{
  "ID": "12",
  "Metadata": {
    "source": "SecurityAuditCheatSheet.txt",
    "type": "file"
  },
  "Embedding": null,
  "Content": "......",
  "Similarity": 0.99999964
}

Content returned does not belongs to the section of context where the word id located, nor have the reference for the package searched.

I see the request for the embedded been triggered on on localai docker logs, but is not stored?

[stancubed]

I'm seeing this same issue on my setup. The embeddings are being generated in the logs for LocalAI, but embeddings are showing as NULL in search results as well.

Here is my docker-compose:

services:
  local-recall:
    image: quay.io/mudler/localrecall:latest
    container_name: local-recall
    ports:
      - "8081:8080"  # LocalRecall API (different port to avoid conflict with LocalAI)
    volumes:
      - localrecall_storage:/db
      - localrecall_assets:/assets
    environment:
      - COLLECTION_DB_PATH=/db
      - EMBEDDING_MODEL=all-roberta-large-v1
      - FILE_ASSETS=/assets
      - OPENAI_API_KEY=sk-1234567890  # Dummy key for LocalAI compatibility
      - OPENAI_BASE_URL=http://local-ai:8080  # Points to LocalAI service
    restart: unless-stopped
    networks:
      - ai-net
    depends_on:
      - local-ai

  local-ai:
    container_name: local-ai
    image: 'localai/localai:latest-aio-gpu-nvidia-cuda-12'
    ports:
      - '8080:8080'
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
      interval: 1m
      timeout: 10m
      retries: 20
    environment:
      - CORS=true
      - CORS_ALLOW_ORIGINS=*
      - DEBUG=true
      - MODELS_PATH=/models
      - LOCALAI_EXTERNAL_BACKENDS="transformers-backend"
    volumes:
      - localai-models:/models
    tty: true
    stdin_open: true
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    networks:
      - ai-net

volumes:
  localai-models:
  localrecall_storage:
    driver: local
  localrecall_assets:
    driver: local

networks:
  ai-net:
    driver: bridge