Skip to content

In-process local vision model so AI works with no cloud key #5

Description

@exekyute

Auto-tagging and semantic search are heuristic and lexical without a Groq or Cohere key (see keepstack/ai.py). A small in-process model would make them genuinely learned with no cloud dependency.

What to do: add an optional local model path (for example a small CLIP) for tagging and embeddings, behind the same pluggable interface. Keep the current deterministic fallbacks as the zero-dependency default.

Acceptance: with the local model enabled, semantic search ranks by visual and semantic similarity rather than lexical overlap, and no external API is called.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions