VectorAI
One API to store your documents and search them by meaning.
VectorAI handles the retrieval part of RAG: send it text, it chunks it, removes personal data and stores the embeddings; then search by meaning from your app, agent or bot.
Free to start One AcadmyAI account opens all 11 apps.
What VectorAI does
Ingest
Send text and documents; VectorAI splits them into chunks and creates embeddings. Large uploads run as batch jobs.
Search by meaning
Query in plain language with filters and get the closest passages back.
Privacy built in
Personal data is removed before storage, and prompts are checked for injection.
Bring your own
Use your own vector database and embedding model if you prefer.
SDKs
pip install vectorai-sdk for Python and npm i @vectorai-sdk/sdk for TypeScript.
Audit log
Every ingest and search is logged for your account.
Who it's for
- Developers building RAG chatbots and assistants
- Teams giving AI agents long-term memory
- Products that need semantic search without running a vector database
How to start
- Create an API key in the VectorAI console.
- Ingest your documents with the SDK or the REST API.
- Call search from your app and pass the results to your model.
VectorAI in each package
One package covers every AcadmyAI app. These are VectorAI's limits in each one.
Questions
How fast can I call it?
1 request a minute on Free, then 10, 25, 50 and 100 a minute on Explorer, Starter, Growth and Professional.
Do I need my own vector database?
No. You can bring one, but VectorAI works without it.
More from AcadmyAI
The same account opens these too.