Embedflow

EmbedFlow lets a new embedding model serve over candidates from an existing vector index while target document vectors are materialized progressively. It supports migration analysis, persistent caching, background work, and serving through FAISS, Qdrant, pgvector, a CLI, and FastAPI.

Qdrant and model-runtime extras are documented in docs/installation.md . For model-backed analysis, install embedflow[faiss,models,dashboard] .

The deterministic demo needs no paid service or model download: install the FAISS/dashboard variant above to use its browser UI.

Open http://127.0.0.1:8000/ . The first search can be COLD or PARTIAL ; repeated traffic becomes WARM as the background materializer fills the persistent cache.

Search responses expose COLD , PARTIAL , or WARM , cache hits and misses, synchronous work, queued work, and stage timings. Once the candidate vectors are warm, target scoring over that candidate set is deterministic.

EmbedFlow ships a versioned core registry of measured results from the research study. Matching model contracts can provide useful starting depths and show what was observed on earlier corpora; a new corpus still receives its own analysis.