Add ability to use Jina CLIP V2 for semantic search (#16826)

* add wheels

* move extra index url to bottom

* config model option

* add postprocess

* fix config

* jina v2 embedding class

* use jina v2 in embeddings

* fix ov inference

* frontend

* update reference config

* revert device

* fix truncation

* return np tensors

* use correct embeddings from inference

* manual preprocess

* clean up

* docs

* lower batch size for v2 only

* docs clarity

* wording
This commit is contained in:
Josh Hawkins
2025-02-26 07:58:25 -07:00
committed by GitHub
parent 447f26e1b9
commit d0e9bcbfdc
10 changed files with 380 additions and 49 deletions
+2
View File
@@ -536,6 +536,8 @@ semantic_search:
enabled: False
# Optional: Re-index embeddings database from historical tracked objects (default: shown below)
reindex: False
# Optional: Set the model used for embeddings. (default: shown below)
model: "jinav1"
# Optional: Set the model size used for embeddings. (default: shown below)
# NOTE: small model runs on CPU and large model runs on GPU
model_size: "small"