telys 0.1.0a3

Telys — public, thin SDK for embedded on-device memory & retrieval (in-process, zero cloud roundtrips)

telys

Public, thin SDK for Telys — embedded, on-device memory & retrieval. In-process, zero cloud roundtrips at query time.

This package contains only the developer-facing surface: the Telys/Collection facades, query/filter types, the EmbeddingProvider interface, the Tuner/TuningPlan interfaces, a runtime loader, and the telys CLI. It contains no engine implementation — the engine is a separate, closed, signed, on-device runtime fetched by telys runtime install (see DECISIONS D-30).

pip install telys
telys runtime install          # fetch the signed on-device runtime for your platform

from telys import Telys
db = Telys("./memory")
col = db.create_collection("docs", dim=768, partition_by="tenant_id")
col.add(vectors, ids=ids, metadata=metadata)          # bring your own vectors (embedding-agnostic)
hits = col.search(qvec, where={"tenant_id": "acme"}, top_k=10, explain=True)

The runtime is required for execution; the embedder is optional — col.add(vectors, …) and col.add_texts(…) both need the runtime, but only *_texts needs an embedder (bring your own via telys.embedding.CallableEmbedder, or use the on-device bigram embedder).

For local development, install the runtime as a package instead of via the CLI:

pip install "telys[runtime]"   # or: pip install telys-runtime