Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
n8n community node for SiliconFlow AI models - chat completions, vision language models, embeddings, and reranking
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
Hybrid search toolkit for Postgres (pgvector + BM25 + rerank)
Reusable retrieval primitives for Taura-style “type → recall” apps.