# Workflow templates

Templates provide connected processing steps. Choose one for your task, load it onto the canvas, and configure your sources, models, and output location.

## Select and use a template

![Template picker in the Chinese interface, with search by name or purpose](../images/template-picker.png)

1. On the workflow creation page, choose the option to start from a template.
2. Search by name or purpose, such as knowledge base or information extraction.
3. Select a template to load its steps onto the canvas.
4. Review node settings and fill in source and target resources in the run form.
5. Save the parameters, start a manual run, and inspect node outputs and saved results.

For your first file-processing run, use a small sample. Memory Governance is session-triggered; see [Memory Governance](memory-governance.md).

## Choose by task

| Template | Purpose |
| --- | --- |
| [Prepare Document Knowledge Base](document-knowledge-base.md) | Write document text to a knowledge base |
| [Prepare Document Knowledge Base with Image Index](document-image-index.md) | Build both text and image indexes |
| [Document Information Extraction](document-extraction.md) | Parse documents and save extracted fields |
| [Extract Information to Table](extraction-to-table.md) | Extract fields into a table |
| [Drawing Parsing](drawing-parsing.md) | Parse drawings and build text and image indexes |
| [Multimodal Information Extraction](multimodal-extraction.md) | Extract fields directly from PDF pages |
| [Dataset Generation](dataset-generation.md) | Generate training or evaluation samples from rules |
| [Speech Transcription Q&A](audio-knowledge-base.md) | Transcribe audio and build a knowledge base index |
| [Video Transcription Q&A](video-knowledge-base.md) | Transcribe video speech and build a knowledge base index |
| [Memory Governance](memory-governance.md) | Filter sessions, extract information, and save memories |

Memory Governance requires the corresponding feature to be enabled. Follow its page after the creation entry becomes available.

## Choose between similar templates

| Task | Choice and difference |
| --- | --- |
| Retrieve document text | Document knowledge base preparation builds a text index and saves parsed files |
| Retrieve text and images | The image-index variant adds visual manifests and image vectors with matching model settings |
| Analyze drawing regions and parts | Drawing Parsing analyzes structure before building text and image indexes |
| Extract fields to files | Document extraction parses first; multimodal extraction reads PDF pages directly and saves JSON |
| Write fields to a database | Table extraction adds a writing step and requires compatible columns |
| Retrieve spoken content | Speech and video templates index transcripts; video does not analyze individual frames |
| Generate training or evaluation material | Dataset Generation needs rules and a schema, followed by sample review |
| Retain session memories | Memory Governance uses synchronized sessions, filtering, extraction, deduplication, and writing |

## Check resources before starting

File templates need sources and an output location. Knowledge base templates also need matching indexes and embedding models; table templates need a database and compatible fields. Follow the selected template's preparation steps and start with a small sample.

Extraction templates combine inputs by default. Do not assume every file produces one row. When changing modes, also check downstream saving bindings. Each template page explains data flow, defaults, and result checks.

## Scenarios

- [Prepare text and images for RAG](multimodal-rag.md)
- [Extract resume information](resume-extraction.md)
- [Generate legal fine-tuning data](legal-sft.md)

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

Prepare Document Knowledge Base <document-knowledge-base>
Prepare Document Knowledge Base with Image Index <document-image-index>
Document Information Extraction <document-extraction>
Extract Information to Table <extraction-to-table>
Drawing Parsing <drawing-parsing>
Multimodal Information Extraction <multimodal-extraction>
Dataset Generation <dataset-generation>
Speech Transcription Q&A <audio-knowledge-base>
Video Transcription Q&A <video-knowledge-base>
Memory Governance <memory-governance>
Prepare text and images for RAG <multimodal-rag>
Extract resume information <resume-extraction>
Generate legal fine-tuning data <legal-sft>
```