Working with Reranker

What is a Reranker / CrossEncoder?

A Reranker model provides a powerful semantic boost to the search quality of any keyword or vector search system without requiring overhauls or intensive replacing.

Using Rerankers with Trieve Vector Inference

Update embedding_models.yaml

To use a reranker model with Trieve Vector Inference, you will need to update your embedding_models.yaml file

embedding_models.yaml

...
models:
  ...
  my-reranker-model:
    replicas: 1
    revision: main
    modelName: BAAI/bge-reranker-large
...

Upgrade your TVI cluster

Update TVI to include your models

helm upgrade -i vector-inference \
  oci://709825985650.dkr.ecr.us-east-1.amazonaws.com/trieve/trieve-embeddings \
    -f embedding_models.yaml

Get embeddings endpoint

kubectl get ing

NAME                                              CLASS   HOSTS   ADDRESS                                                                 PORTS   AGE
vector-inference-embedding-bge-reranker-ingress   alb     *       k8s-default-vectorin-b09efe8cf6-890425945.us-west-1.elb.amazonaws.com   80      77m

The output looks like this

Upgrading your Instance Working with SPLADE v2

Get Started

Self Hosting

Guides

API Reference

Working with Reranker

What is a Reranker / CrossEncoder?

Using Rerankers with Trieve Vector Inference

​What is a Reranker / CrossEncoder?

​Using Rerankers with Trieve Vector Inference

What is a Reranker / CrossEncoder?

Using Rerankers with Trieve Vector Inference