The Langchain importer leverages the Langchain library's extensive collection of document loaders to import content from diverse sources including websites, databases, social media platforms, cloud storage, and research repositories. This service provides programmatic access to external data sources that require API authentication or specialized protocols.
| Property | Value |
|---|---|
| Service Name | Langchain importer |
| Status | Enabled |
| Compatible Nodes | Import Content |
| Parameter | Type | Default | Description |
|---|---|---|---|
| Import Method | choice | - | Select the Langchain loader to use |
| Parameter | Type | Default | Description |
|---|---|---|---|
| Tags | text | (empty) | Comma-separated tags for organizing imported content |
| Notes | text | (empty) | Additional notes or metadata about the import |
Basic single-page web content loader.
| Parameter | Type | Default | Description |
|---|---|---|---|
| Url to load | text | - | The webpage URL to import |
Best for: Simple single-page imports without crawling needs.
Recursively crawls and imports web content following links.
| Parameter | Type | Default | Description |
|---|---|---|---|
| Url | text | - | Starting URL for recursive crawl |
| Max depth | number | 2 | Maximum link depth to follow |
Best for: Importing documentation sites or multi-page content with predictable link structures.
Imports all pages listed in a website's sitemap.xml.