A newer version of the Gradio SDK is available:
5.6.0
Machine Learning with Embeddings
You can use embeddings to
- Evaluate text similarity, see test_sentence_similarity.py
- Build your own classifier, see test_classification.py
- Search relative texts, see test_semantic_search.py
To these tests, you need to download the data here. You also need an OpenAI API key for comparison.
Run with:
cd playground/test_embedding
python3 test_classification.py
The script will train classifiers based on vicuna-7b
, text-similarity-ada-001
and text-embedding-ada-002
and report the accuracy of each classifier.