FAE
1.0.0
A method to fine-tune the black-box OpenAI embedding to improve the retrieval performance ?.
See our blog post How to Improve Your OpenAI Embeddings? for a detailed introduction to the FAE method.
Other training details and dataset construction can be found in LlamaIndex's Blog.
pip install -r requirements.txtcd ./finetune
python train.pycd ./finetune
python fae_train.pyThe comparison of the evaluation results can be found in the jupyter notebook .
Get early access to our RAG platform and embedding model fine-tuning service.
Vectify AI ?
