rerank
role and used by @Codebase in order to select the most relevant code snippets after vector search.
Recommended reranking models
For a comparison of all reranking models including open and closed options, see our comprehensive model recommendations.
rerank-2
by Voyage AI, which is listed below along with the rest of the options for rerankers.
Voyage AI
Voyage AI offers the best reranking model for code with theirrerank-2
model. After obtaining an API key from here, you can configure a reranker as follows:
Cohere
See Cohere’s documentation for rerankers here.config.yaml
LLM
If you only have access to a single LLM, then you can use it as a reranker. This is discouraged unless truly necessary, because it will be much more expensive and still less accurate than any of the above models trained specifically for the task. Note that this will not work if you are using a local model, for example with Ollama, because too many parallel requests need to be made.config.yaml
"modelTitle"
field must match one of the models in your “models” array in config.json.
Text Embeddings Inference
Hugging Face Text Embeddings Inference enables you to host your own reranker endpoint. You can configure your reranker as follows:config.yaml