# Going multimodal

- [Introduction](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/introduction.md): Percolate is a multimodal database that manages relational, key-value, graph and vector data for building AI applications. We can combine indexes when querying Percolate.
- [Querying](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/querying.md): Examples of queries and query generation in each modality
- [Graph](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/querying/graph.md)
- [Vector](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/querying/vector.md)
- [Key-value](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/querying/key-value.md)
- [Relational](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/querying/relational.md)
- [Indexing](https://percolation-labs.gitbook.io/percolation-labs/going-multimodal/indexing.md): Indexing means combining the benefits of each modality when ingesting and querying data. Learn how this is achieved in Percolate


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://percolation-labs.gitbook.io/percolation-labs/going-multimodal.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.