telys 0.1.0a5

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).

Install

As a CLI (recommended — isolated env, on your PATH, not pinned to one Python):

pipx install telys
# …or the one-liner (installs via pipx):
curl -fsSL https://telys.ai/install.sh | sh

telys login          # sign in → free device license + signed runtime; fully offline thereafter

As a library (to import telys in your own project):

python -m venv .venv && . .venv/bin/activate
pip install telys

Plain pip install --user telys works too, but pip may warn that its user-scripts dir isn't on your PATH (a macOS --user quirk) — pipx avoids that entirely. Runtime platforms: macOS arm64, Linux x86_64/arm64 (Windows: run under WSL2).

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