sinapsis-huggingface-embeddings 0.1.4

Templates to generate and/or extract text and image embeddings using HuggingFace

Sinapsis Hugging Face Embeddings

Templates for seamless integration with Hugging Face embedding models

🐍 Installation • 📦 Features • 📦 Example usage • 📙 Documentation • 🔍 License

🐍 Installation

Install using your package manager of choice. We encourage the use of uv

Example with uv:

  uv pip install sinapsis-huggingface-embeddings --extra-index-url https://pypi.sinapsis.tech

or with raw pip:

  pip install sinapsis-huggingface-embeddings --extra-index-url https://pypi.sinapsis.tech

Change the name of the package for the one you want to install.

[!IMPORTANT] Templates in each package may require extra dependencies. For development, we recommend installing the package with all the optional dependencies:

with uv:

  uv pip install sinapsis-huggingface-embeddings[all] --extra-index-url https://pypi.sinapsis.tech

or with raw pip:

  pip install sinapsis-huggingface-embeddings[all] --extra-index-url https://pypi.sinapsis.tech

📦 Features

The templates in this package include multiple templates tailored for different embedding-based tasks:

• SpeakerEmbeddingFromAudio: Extracts speaker embeddings from audio data and attaches them to text or audio packets.
• SpeakerEmbeddingFromDataset: Retrieves speaker embeddings from Hugging Face datasets and integrates them into a DataContainer.
• HuggingFaceEmbeddingNodeGenerator: Generates text embeddings, splits documents into chunks, and processes them with metadata.

▶️ Example Usage

Below is an example YAML configuration for extracting speaker embeddings from an audio file and attaching them to text packets.

Config

agent:
  name: embeddings_agent

templates:
  - template_name: InputTemplate
    class_name: InputTemplate
    attributes: {}

  - template_name: TextInput
    class_name: TextInput
    template_input: InputTemplate
    attributes:
      text: This is a test to check how the model works with a normal voice like mine.

  - template_name: AudioReaderSoundfile
    class_name: AudioReaderSoundfile
    template_input: TextInput
    attributes:
      audio_file_path: test.mp3

  - template_name: SpeakerEmbeddingFromAudio
    class_name: SpeakerEmbeddingFromAudio
    template_input: AudioReaderSoundfile
    attributes:
      target_packet: texts

[!IMPORTANT] The TextInput and AudioReaderSoundfile templates correspond to the sinapsis-data-readers package. If you want to use the example, please make sure you install this package.

To run the config, use the CLI:

sinapsis run name_of_config.yml

📙 Documentation

Documentation is available on the sinapsis website

Tutorials for different projects within sinapsis are available at sinapsis tutorials page

🔍 License

This project is licensed under the AGPLv3 license, which encourages open collaboration and sharing. For more details, please refer to the LICENSE file.

For commercial use, please refer to our official Sinapsis website for information on obtaining a commercial license.