# searches.do

> Deploy powerful search with vector embeddings, full-text matching, and hybrid ranking. <50ms query latency with automatic relevance tuning and typo tolerance.

Build Google-Quality Search in Minutes. Combine vector similarity, full-text search, and custom ranking with automatic query understanding and typo correction. Index millions of documents, search across multiple fields, and return results in <50ms P95 with intelligent caching, fuzzy matching, and semantic understanding at 300+ edge locations.

searches.do is one of the primitives of Platform.do, in the Data layer (records, vocabulary and search). Every .do shares one grammar, Business-as-Code, and one SDK.

## Page

- [searches.do](https://searches.do/): Searches.do - Build Semantic Search Engines | Vector, Full-Text, Hybrid Search ([Markdown](https://searches.do/index.md))

## Business-as-Code

- [What is Business-as-Code?](https://platform.do/business-as-code): the grammar every .do shares ([Markdown](https://platform.do/business-as-code.md))
- [Platform.do](https://platform.do/): infrastructure for autonomous business ([llms.txt](https://platform.do/llms.txt))

## Docs

- [Documentation](https://docs.platform.do): guides and reference for the whole platform
- [SDK](https://docs.platform.do/sdk): TypeScript SDK, `import { on, send, db, $ } from 'sdk.do'`
- [CLI](https://docs.platform.do/cli): the `do` command
- [MCP](https://docs.platform.do/mcp): one MCP tool, `do`, that runs a script
- [API](https://docs.platform.do/api): REST API

## Other Data primitives

- [databases.do](https://databases.do)
- [datasets.do](https://datasets.do)
- [nouns.do](https://nouns.do)
- [verbs.do](https://verbs.do)
- [lists.do](https://lists.do)
- [mdx.do](https://mdx.do)
- [resources.do](https://resources.do)
- [directory.do](https://directory.do)

## Optional

- [Full text](https://searches.do/llms-full.txt): this index plus the page in full