Shopify
Stripe
Slack
Notion
Google Workspace
Confluence
Vector Database
定義
A vector database is a database built to store and search embeddings — high-dimensional vectors — by similarity, so you can quickly find the content whose meaning is closest to a query.
How it works
Your content is converted into embeddings and stored as vectors. When a query arrives, it's embedded too, and the database finds the nearest vectors using approximate nearest-neighbor (ANN) algorithms that stay fast even across millions of items.
Unlike a traditional database that matches exact values, a vector database ranks results by semantic closeness. Popular examples include Pinecone, Weaviate, Milvus, and pgvector for Postgres.
Why it matters for support
The vector database is the retrieval engine behind RAG-powered support agents. It's what makes it possible to search your entire knowledge base by meaning in milliseconds and hand the most relevant passages to the model — so answers stay grounded in your real content.
よくある質問
Do I need a vector database for AI support?
If you want retrieval-augmented answers grounded in your own docs, some form of vector search is involved — but many platforms manage it for you behind the scenes, so you connect a knowledge source without running a database yourself.
How is a vector database different from a normal database?
A normal database finds exact or structured matches; a vector database finds the items whose meaning is most similar to a query, ranked by distance between embeddings.
関連用語
Embeddings
Embeddings are numeric vector representations of text (or images, code, etc.) that capture meaning, so that pieces of content with similar meaning sit close together in a high-dimensional space..
Semantic Search
Semantic search is a search technique that matches content by meaning rather than by exact keywords, using embeddings to find results that are conceptually related to the query even when they share no words with it..
Retrieval-Augmented Generation (RAG)
Retrieval-augmented generation (RAG) is a technique where an AI model retrieves relevant information from your own knowledge sources at query time and uses it to ground its answer, instead of relying only on what it memorized during training..
Knowledge Base
A knowledge base is a structured, searchable library of articles — how-tos, FAQs, troubleshooting guides, and policies — that lets customers or agents find answers without contacting support directly..
Data Sources
Data sources (also called knowledge sources) are the knowledge an agent reads from — uploaded documents, indexed websites, and live content from connected apps like Google Docs, Notion, and Confluence.
アイデアを実装に
Macha は既に運用中のヘルプデスク (Zendesk、Freshdesk、Front、Intercom、Gorgias) の上に載る AI エージェント層です。
トライアルを開始