Metadata-Version: 2.4
Name: telys
Version: 0.1.0a3
Summary: Telys — public, thin SDK for embedded on-device memory & retrieval (in-process, zero cloud roundtrips)
Project-URL: Homepage, https://telys.ai
Project-URL: Documentation, https://telys.ai
Project-URL: Repository, https://github.com/thyn-ai/telys
Project-URL: Issues, https://github.com/thyn-ai/telys/issues
Project-URL: Company, https://thyn.ai
Author-email: Thyn <eng@thyn.ai>
Maintainer-email: Thyn <eng@thyn.ai>
License: Apache-2.0
Keywords: embeddings,memory,on-device,rag,retrieval,sdk,telys,vector-search
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Requires-Dist: cryptography>=42
Requires-Dist: numpy>=1.24
Provides-Extra: runtime
Requires-Dist: telys-runtime; extra == 'runtime'
Description-Content-Type: text/markdown

# 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](../../docs/DECISIONS.md)).

```bash
pip install telys
telys runtime install          # fetch the signed on-device runtime for your platform
```
```python
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:

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