Skip to main content
Find technical documentation for understanding, configuring, and deploying VectorAI DB. Each section provides reference material and task-based guides.

Fundamentals

Understand the core concepts and data structures in VectorAI DB.

Data structures

Collections, points, vectors, and payloads that organize your data.

Search and filtering

Vector similarity search with metadata filtering using must, should, and must-not conditions.

Indexing

HNSW algorithm configuration for efficient approximate nearest neighbor search.

Distance metrics

Cosine similarity, Euclidean distance, and dot product for measuring similarity.

Guides

Configure, secure, and operate VectorAI DB in production environments.

Configuration

Server settings, performance tuning, and environment configuration.

Security

Authentication, authorization, and secure deployment practices.

Monitoring and logging

Observability, metrics collection, and log management.

Troubleshooting

Diagnose and resolve common issues.

Installation and deployment

Set up VectorAI DB in your environment.

Docker

Run VectorAI DB in containers for development and production.

Integrations

Connect VectorAI DB with embedding providers and AI frameworks.

OpenAI

Generate embeddings using OpenAI models.

LangChain

Build RAG pipelines with the LangChain framework.

LlamaIndex

Build RAG applications with the LlamaIndex framework.

Quick reference

SectionContentUse case
FundamentalsCore concepts and data structuresUnderstanding VectorAI DB architecture
GuidesConfiguration and operationsProduction deployment and maintenance
InstallationSetup proceduresGetting VectorAI DB running
Cloud platformsAWS, Azure, GCP deploymentCloud infrastructure setup
IntegrationsThird-party connectionsConnecting embedding providers and frameworks