Create a vector store

Create an empty vector store, a searchable index of your files.

POST/vector_stores

Create an empty vector store, a searchable index of your files.

Add files with POST /vector_stores/{vector_store_id}/files, then search it with POST /vector_stores/{vector_store_id}/search or let Olive search it by giving a file_search tool to POST /responses. Use a vector store when a document is too long to send whole.

You can create 50 stores per day, with a burst of 10. Reuse a store for a whole project instead of creating one per question. A store belongs to your account, and another account's id answers as not found.

Authorization

BearerAuth
AuthorizationBearer <token>

Your Avey API key, sent as Authorization: Bearer <key>. This is the header the OpenAI SDKs already send, so pass the key as the client's ordinary api_key and no further configuration is needed.

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

The body of a request that creates a vector store.

Response Body

application/json

application/json

application/json

application/json

application/json

application/json

application/json

curl https://api.avey.ai/llm/vector_stores \  -H "Authorization: Bearer $AVEY_API_KEY" \  -H "Content-Type: application/json" \  -d '{ "name": "ward-protocols" }'
{  "id": "vs_6f1c2a9d8e7b4c35a0d1e2f3b4c5d6e7",  "object": "vector_store",  "created_at": 1769904000,  "name": "ward-protocols",  "status": "completed",  "usage_bytes": 0,  "file_counts": {    "in_progress": 0,    "completed": 0,    "failed": 0,    "cancelled": 0,    "total": 0  },  "metadata": {}}