Skip to content
Draft
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,9 @@ public Uni<BatchedRerankingResponse> rerank(
"In order to rerank, please provide the reranking API key.");
}
var accessToken = HttpConstants.BEARER_PREFIX_FOR_API_KEY + rerankingCredentials.apiKey();

// Extract tenant ID from reranking credentials to forward to GPU API Gateway
String tenantId = rerankingCredentials.tenant().toString();

var nvidiaRequest =
new NvidiaRerankingRequest(
Expand All @@ -107,7 +110,7 @@ public Uni<BatchedRerankingResponse> rerank(
TRUNCATE_PASSAGE);

final long callStartNano = System.nanoTime();
return retryHTTPCall(nvidiaClient.rerank(accessToken, nvidiaRequest))
return retryHTTPCall(nvidiaClient.rerank(accessToken, tenantId, nvidiaRequest))
.onItem()
.transform(
jakartaResponse -> {
Expand Down Expand Up @@ -145,7 +148,9 @@ public interface NvidiaRerankingClient {
@POST
@ClientHeaderParam(name = HttpHeaders.CONTENT_TYPE, value = MediaType.APPLICATION_JSON)
Uni<Response> rerank(
@HeaderParam("Authorization") String accessToken, NvidiaRerankingRequest request);
@HeaderParam("Authorization") String accessToken,
@HeaderParam("TENANT_ID") String tenantId,
NvidiaRerankingRequest request);
}

/**
Expand Down
Loading