feat(transformers): add embeddings with Automodel (#1308)

* Update huggingface.py

Switch SentenceTransformer for AutoModel in order to set trust_remote_code needed to use the encode method with embeddings models like jinai-v2

Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu>

* feat(transformers): split in separate backend

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Lucas Hänke de Cansino <lhc@next-boss.eu>
This commit is contained in:
Ettore Di Giacinto 2023-11-20 21:21:17 +01:00 committed by GitHub
parent ff9afdb0fe
commit 92cbc4d516
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
23 changed files with 783 additions and 34 deletions

View file

@ -78,7 +78,7 @@ jobs:
sudo apt-get install -y libopencv-dev && sudo ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
sudo rm -rfv /usr/bin/conda || true
PATH=$PATH:/opt/conda/bin make -C backend/python/huggingface
PATH=$PATH:/opt/conda/bin make -C backend/python/sentencetransformers
# Pre-build piper before we start tests in order to have shared libraries in place
make sources/go-piper && \