Skip to content
Hanzo AI
Try Hanzo
Language: English (United States)

Hanzo Search

Hybrid Search + RAG

Keyword and meaning in the same query

Read the docsGitHub

Four ways to ask, one index

The same documents answer all four. Choose per query, not per deployment.

  1. Full text

    01 / 04

    Typo tolerance, facets and filters. A user who types Kubernets still finds the page, and a user who wants only last quarter's docs can say so.

  2. Vector

    02 / 04

    Bring your own embedding model — ours or anyone's — and search by meaning. Useful exactly when the user does not know the word your document uses.

  3. Hybrid

    03 / 04

    Reciprocal Rank Fusion merges the two lists by rank rather than by score, so a keyword hit and a semantic hit compete fairly without a threshold you have to tune.

  4. RAG chat

    04 / 04

    The retrieved passages go to a model and come back as an answer with links to what it read. Streamed, so the first sentence arrives before the last one is written.

How it works

Content in, ranked results out, and a model over the top if you want one.

  1. Index your content

    Step 01

    Push documents at build time or over the REST API. Text fields become searchable as they land; embeddings go to the vector store beside them. Adding a vector field later does not force a text reindex.

  2. Query it from anywhere

    Step 02

    A React hook for search-as-you-type, the REST API for everything else, and an MCP tool so an agent can search the same index a user searches. One index, three callers.

  3. Let people ask instead

    Step 03

    Turn on RAG chat and a question gets an answer built from the passages that were retrieved, each one linked. If the index has nothing, the answer says so rather than inventing one.

Pricing

Pay for hosted search, vector, and AI. Self-host Meilisearch free forever.

Which plan fits

fits Build

  1. Build

    $99mo

    • 5 projects
    • 10k docs per project
    • 2,500 AI chat sessions
    • Unlimited searches
    • React hook + REST API
    Read the docs

  2. Scale

    $1,450mo

    • 25 projects
    • 100k docs per project
    • 50,000 AI chat sessions
    • Unlimited searches
    • Priority support
    Read the docs

  3. Enterprise

    Custom

    • Unlimited projects
    • Unlimited docs
    • Unlimited AI chat sessions
    • Dedicated support + SLA
    Contact Sales

Meilisearch is open source. Self-host free forever. Pay only for our hosted API, vector search, and AI features.

Works with any docs framework

Native support for Hanzo Docs, Fumadocs, Nextra, and Docusaurus. REST API for everything else.

Hanzo Docsnative/v1/search
Search — Hanzo
  • gatewayReady
  • payments-apiReady
  • checkout-webBuilding
  • docs-siteReady

Every request enters here, so the limiter does too.

api.hanzo.ai/v1/searchOpen in the console ↗

Example project. Every name in it is one you would give your own.

Paste and ship

Paste this into any agent. It reads the skill manifest and calls Search from there.

Agent promptapi /v1/search
Read https://hanzo.ai/skill.md and use Hanzo Search in my project. Start with: hanzo search create

Make your content searchable and conversational

Index once, search everywhere.

Full-text, vector, hybrid, and RAG -- all from one API.

Read the docsView on GitHub

Get Search

AI-powered search

License: Apache-2.0hanzoaiDeploy to Cloud