4 Services from vektor.halowerk.com

Embeds a natural language request and a provided list of tools locally, then returns deterministic cosine similarity ranks and selects the best-matching tool.

Embeds up to 32 texts into vector representations using a local Ollama runtime with nomic or bge_m3 models, returning the model name and embedding dimensions.

Calculates item co-occurrence and similarity from submitted interaction events to return recommendations, without storing any user profiles.

Embeds a query and up to 64 candidate strings locally, then returns cosine similarity scores and stable descending ranks for each candidate.