AgentDB Advanced Features FAQs

Question 1

How does hybrid search work with this skill?

Accepted Answer

Hybrid search allows you to combine semantic vector similarity scores with specific metadata filters (like price, date, or category) to find the most relevant and accurate data points.

Question 2

Which distance metric is best for text search?

Accepted Answer

Cosine similarity is generally the default and best choice for text embeddings and semantic search, as it measures the orientation of vectors regardless of their magnitude.

Question 3

What is QUIC synchronization in AgentDB?

Accepted Answer

QUIC synchronization enables sub-millisecond latency data syncing between different AgentDB nodes, providing encrypted, multiplexed communication for distributed AI systems.

Question 4

Can AgentDB handle multiple database shards?

Accepted Answer

Yes, this skill provides implementation patterns for sharding databases by domain or task, allowing your AI memory system to scale horizontally across multiple files or nodes.

Question 5

When should I use Maximal Marginal Relevance (MMR)?

Accepted Answer

Use MMR when you need to avoid redundant search results. It balances relevance with diversity to ensure the retrieved context covers a broad range of information rather than similar duplicates.

AgentDB Advanced Features

Key Features

Use Cases

AgentDB Advanced Features

Key Features

Use Cases