💡 What's new in txtai 4.0

• txtai

  163 3,645 8.5 Python

  💡 Build AI-powered semantic search applications

  

  txtai executes machine-learning workflows to transform data and build AI-powered semantic search applications.

• transformers

  62 87,023 10.0 Python

  🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

  

  txtai supports generating vectors with Hugging Face Transformers, PyTorch, ONNX and Word Vector models.

• Sonar

  www.sonarsource.com

  sponsored

  Write Clean Python Code. Always.. Sonar helps you commit clean code every time. With over 225 unique rules to find Python bugs, code smells & vulnerabilities, Sonar finds the issues while you focus on the work.

  

• Pytorch

  117 64,431 10.0 C++

  Tensors and Dynamic neural networks in Python with strong GPU acceleration

  

  txtai supports generating vectors with Hugging Face Transformers, PyTorch, ONNX and Word Vector models.

• onnxruntime

  16 8,662 9.9 C++

  ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

  

  txtai supports generating vectors with Hugging Face Transformers, PyTorch, ONNX and Word Vector models.

• magnitude

  0 11 10.0 Python

  Magnitude fork that only supports Word2Vec, GloVe and fastText embeddings (by neuml)

  

  txtai supports generating vectors with Hugging Face Transformers, PyTorch, ONNX and Word Vector models.

• spaCy

  31 25,592 9.8 Python

  💫 Industrial-strength Natural Language Processing (NLP) in Python

  

  The next example uses spaCy to build vectors and then loads them into txtai. The vectors with this model are much faster to generate at the expense of accuracy.

Suggest a related project