Llm-sentence-transformers

Latest version: v0.2

Safety actively analyzes 681881 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

0.2

- New `llm sentence-transformers register --trust-remote-code` option for installing models that require `trust_remote_code=True`. [14](https://github.com/simonw/llm-sentence-transformers/issues/14)

Here's how to install [nomic-embed-text-v1](https://huggingface.co/nomic-ai/nomic-embed-text-v1) using this option (which also requires an additional dependency, [einops](https://pypi.org/project/einops/)):

bash
llm install einops
llm sentence-transformers register nomic-ai/nomic-embed-text-v1 --trust-remote-code

Then use it to create embeddings for text like this:
bash
llm embed -m sentence-transformers/nomic-ai/nomic-embed-text-v1 -c 'hello'

0.1.2

- Fixed a bug where an error was thrown if the LLM user directory (usually `io.datasette.llm`) did not exist yet. [9](https://github.com/simonw/llm-sentence-transformers/issues/9)

0.1.1

- Improved documentation, with related reading and a warning about truncation by different models.

0.1

- Initial release, providing LLM [embeddings](https://llm.datasette.io/en/stable/embeddings/index.html) access to models from [sentence-transformers](https://www.sbert.net/). [#1](https://github.com/simonw/llm-sentence-transformers/issues/1)

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.