Query & retrieval runtime
How one query runtime fuses graph traversal, vector ANN, and full-text search — the .gq surface, the search functions, RRF fusion, embeddings, and the executor underneath.
Providers
provider |
Wire shape | Use it for |
|---|---|---|
openai-compatible (default) |
POST {base}/embeddings, bearer auth, {model, input, dimensions} |
OpenRouter (the default gateway — one key for many models), OpenAI direct, or a self-hosted endpoint (vLLM / Ollama / LM Studio) |
gemini |
POST {base}/models/{model}:embedContent, x-goog-api-key, with RETRIEVAL_QUERY / RETRIEVAL_DOCUMENT task types |
Reaching Google's generativelanguage API directly |
mock |
none — deterministic offline vectors | Tests and local dev without a key |
Vectors are stored L2-normalized as FixedSizeList(Float32, dim); the requested output dimension is driven by
the target column width and sent as Gemini outputDimensionality / OpenAI dimensions.