Vector database
Vector similarity search (GraphQL nearVector).
6 fields
Semantic search by text (GraphQL nearText — requires the class to have a text2vec vectorizer module).
Hybrid BM25 + vector search (GraphQL hybrid).
8 fields
Generative search (RAG): retrieve objects then generate text with an LLM (GraphQL generate). The collection must have a generative module configured in its schema (e.g. generative-openai, generative-anthropic, generative-cohere). Pass the corresponding API key in the credential. Provide single_prompt, group_task, or both.
10 fields
Aggregate statistics over a collection (GraphQL Aggregate — count, mean, topOccurrences, etc.).
5 fields
Insert an object (REST).
4 fields
Get an object by ID (REST).
2 fields
Partial update (PATCH /v1/objects/{class}/{id}) — merges provided fields.
Delete an object by ID (REST).
Batch-delete objects matching a where filter (up to 10,000 per call).
3 fields
Upload a document file, chunk + embed it, and batch-insert objects.
List collections (schema classes).
Create a collection (schema class).
Drop a collection and ALL of its objects — permanent.
1 field
Start building workflows in minutes with our visual builder. No code required.