> ## Documentation Index
> Fetch the complete documentation index at: https://docs.topk.io/llms.txt
> Use this file to discover all available pages before exploring further.

# TopK Documentation

> TopK is a hybrid retrieval engine built on object storage for 10x lower cost and massive scale. Semantic, keyword, dense, sparse, and multi-vector search with filtering and custom ranking, in one API.

> **Set up with a coding agent**
>
> Paste this into Claude Code, Cursor, Codex, or any agent with terminal access. It sets everything up from the CLI.
>
> ```text theme={null}
> Set up TopK: docs.topk.io/start
> ```

## Get started

> **[Python SDK](/sdk/topk-py/overview)**
>
> Search from Python. TopK embeds your text for you.
>
> ```python theme={null}
> # pip install topk-sdk
> client.collection("books").query(
>   select(
>     score=fn.semantic_similarity(
>       "content", "meaning of life"
>     ),
>   )
>   .sort(field("score"), asc=False)
>   .limit(10)
> )
> ```

> **[JavaScript SDK](/sdk/topk-js/overview)**
>
> Search from TypeScript or JavaScript. Same API.
>
> ```typescript theme={null}
> // npm install topk-js
> await client.collection("books").query(
>   select({
>     score: fn.semanticSimilarity(
>       "content", "meaning of life"
>     ),
>   })
>   .sort(field("score"), false)
>   .limit(10)
> );
> ```

> **[CLI](/cli)**
>
> Import data and run SQL from your terminal.
>
> ```bash theme={null}
> brew tap topk-io/topk
> brew install topk
> topk login
> topk project select
> topk import ./books.parquet \
>   --region aws-us-east-1-elastica
> ```

> **[SQL](/sdk/topk-sql/overview)**
>
> Search with any PostgreSQL client.
>
> ```sql theme={null}
> SELECT title,
>   semantic_similarity(content,
>     'meaning of life') AS score
> FROM books
> ORDER BY score DESC LIMIT 10;
> ```

## Search types

> **[Semantic search](/guides/semantic-search)**
>
> Search by meaning. No embedding pipeline, vector store, or reranker to run.

> **[True hybrid search](/guides/true-hybrid-search)**
>
> Blend meaning, keywords, and filters in one query.

> **[Keyword search](/guides/keyword-search)**
>
> Full-text search ranked with BM25.

> **[Dense vector search](/guides/vector-search)**
>
> ANN search with >95% recall and p99 under 50 ms.

> **[Sparse vector search](/guides/sparse-vector-search)**
>
> Exact retrieval over learned sparse models like SPLADE.

> **[Multi-vector search](/guides/multi-vector-search)**
>
> Late interaction with MaxSim for long documents.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.