# AI processing

Choose a node to view its purpose and configuration.

| Node | Purpose |
| --- | --- |
| [General Document Parsing](document-parse.md) | Parse files into text and document records for chunking, extraction, and retrieval. |
| [Parse Image](image-parse.md) | Recognize text in images or generate captions. |
| [Parse Audio](audio-parse.md) | Transcribe speech from audio. |
| [Parse Video](video-parse.md) | Transcribe speech from video. |
| [Text Embedding](text-embedding.md) | Generate text vectors for documents. |
| [Clean](clean.md) | Clean whitespace, tags, and selected noise. |
| [Segment](chunk.md) | Split text by target length while retaining sources. |
| [Information Extraction](information-extraction.md) | Extract structured information using field definitions. |
| [AI Inference](ai-inference.md) | Generate summaries, rewrites, or other text from a prompt. |
| [Image Embedding](image-embedding.md) | Generate vectors for page and document images and write an image index. |
| [Embed and Add to Knowledge Base](knowledge-index.md) | Generate text vectors and write them to a knowledge base for retrieval. |

```{toctree}
:hidden:
:maxdepth: 1

General Document Parsing <document-parse>
Parse Image <image-parse>
Parse Audio <audio-parse>
Parse Video <video-parse>
Text Embedding <text-embedding>
Clean <clean>
Segment <chunk>
Information Extraction <information-extraction>
AI Inference <ai-inference>
Image Embedding <image-embedding>
Embed and Add to Knowledge Base <knowledge-index>
```