Add specific section about GPU in semantic search (#14685)

This commit is contained in:
Nicolas Mowen 2024-10-30 06:23:10 -06:00 committed by GitHub
parent ab26aee8b2
commit d10fea6012
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -43,12 +43,6 @@ The text model is used to embed tracked object descriptions and perform searches
Differently weighted CLIP models are available and can be selected by setting the `model_size` config option:
:::tip
The CLIP models are downloaded in ONNX format, which means they will be accelerated using GPU hardware when available. This depends on the Docker build that is used. See [the object detector docs](../configuration/object_detectors.md) for more information.
:::
```yaml
semantic_search:
enabled: True
@ -58,6 +52,18 @@ semantic_search:
- Configuring the `large` model employs the full Jina model and will automatically run on the GPU if applicable.
- Configuring the `small` model employs a quantized version of the model that uses much less RAM and runs faster on CPU with a very negligible difference in embedding quality.
### GPU Acceleration
The CLIP models are downloaded in ONNX format, and the `large` model can be accelerated using GPU hardware, when available. This depends on the Docker build that is used, see [the object detector docs](../configuration/object_detectors.md) for more information.
If the correct build is used for your GPU and the `large` model is configured, then the GPU will be automatically detected and used automatically.
```yaml
semantic_search:
enabled: True
model_size: small
```
## Usage and Best Practices
1. Semantic search is used in conjunction with the other filters available on the Search page. Use a combination of traditional filtering and semantic search for the best results.