Embeddings & Rerank
**Endpoint:** `POST /v1/embeddings`
Embeddings
Endpoint: POST /v1/embeddings
curl https://api.starrise.ai/v1/embeddings \
-H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-3-small",
"input": "The food was delicious and the service was excellent."
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.starrise.ai/v1",
api_key="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
)
response = client.embeddings.create(
model="text-embedding-3-small",
input=["Document one", "Document two"],
)
print(len(response.data[0].embedding))Use cases: semantic search, RAG, clustering, recommendation.
Rerank
Endpoint: POST /v1/rerank
Jina-compatible reranking for improving retrieval quality:
curl https://api.starrise.ai/v1/rerank \
-H "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "jina-reranker-v2-base-multilingual",
"query": "What is the capital of France?",
"documents": ["Paris is the capital.", "Berlin is in Germany."]
}'Available embedding and rerank models are listed on the console Pricing page and in GET /v1/models.