# Jina Chunking

Blocks for splitting text into semantic chunks using Jina AI.

## Jina Chunking

### What it is

Chunks texts using Jina AI's segmentation service

### How it works

This block uses Jina AI's segmentation service to split texts into semantically meaningful chunks. Unlike simple splitting by character count, Jina's chunking preserves semantic coherence, making it ideal for RAG applications.

Configure maximum chunk length and optionally return token information for each chunk.

### Inputs

| Input              | Description                         | Type       | Required |
| ------------------ | ----------------------------------- | ---------- | -------- |
| texts              | List of texts to chunk              | List\[Any] | Yes      |
| max\_chunk\_length | Maximum length of each chunk        | int        | No       |
| return\_tokens     | Whether to return token information | bool       | No       |

### Outputs

| Output | Description                              | Type       |
| ------ | ---------------------------------------- | ---------- |
| error  | Error message if the operation failed    | str        |
| chunks | List of chunked texts                    | List\[Any] |
| tokens | List of token information for each chunk | List\[Any] |

### Possible use case

**RAG Preprocessing**: Chunk documents for retrieval-augmented generation systems.

**Embedding Preparation**: Split long texts into optimal chunks for embedding generation.

**Document Processing**: Break down large documents for analysis or storage in vector databases.

***


---

# 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://agpt.co/docs/integrations/block-integrations/chunking.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.