Metadata-Version: 2.4
Name: agentforge-voyage
Version: 0.2.4
Summary: Voyage AI embedding provider for AgentForge — voyage-3 / voyage-large / voyage-code
Project-URL: Homepage, https://github.com/Scaffoldic/agentforge-py
Project-URL: Repository, https://github.com/Scaffoldic/agentforge-py
Project-URL: Documentation, https://github.com/Scaffoldic/agentforge-py
Project-URL: Changelog, https://github.com/Scaffoldic/agentforge-py/blob/main/CHANGELOG.md
Project-URL: Issues, https://github.com/Scaffoldic/agentforge-py/issues
Author: The AgentForge Authors
License-Expression: Apache-2.0
License-File: LICENSE
Keywords: agent,ai,embeddings,rag,voyage
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Typing :: Typed
Requires-Python: >=3.13
Requires-Dist: agentforge-core~=0.2.4
Provides-Extra: voyage
Requires-Dist: voyageai>=0.3; extra == 'voyage'
Description-Content-Type: text/markdown

# agentforge-voyage

Voyage AI embedding provider for
[AgentForge](https://github.com/Scaffoldic/agentforge-py).

Implements `EmbeddingClient` over Voyage's `embeddings.create()`
API. Embedding-only — Voyage doesn't ship a chat model. Use it
when you want Voyage's RAG-optimised embeddings paired with any
chat provider (Anthropic, OpenAI, Bedrock).

## Install

```bash
pip install "agentforge-voyage[voyage]"
```

## Use

```python
from agentforge_voyage import VoyageEmbeddingClient

emb = VoyageEmbeddingClient.from_config(
    model="voyage-3-large",
    api_key="pa-...",  # or omit and use VOYAGE_API_KEY
)
resp = await emb.embed(["hello", "world"])
print(resp.vectors[0])
```

## Capabilities

`{"multimodal"}` for `voyage-multimodal-3`; empty set otherwise.

## License

Apache-2.0. See [LICENSE](./LICENSE).
