LlamaParse is an advanced PDF parsing service that transforms complex PDF documents into clean, structured text or Markdown format. It excels at preserving document layout, extracting tables, and handling multi-column text with high accuracy.
| Property | Value |
|---|---|
| Service Name | LlamaParse |
| Status | Enabled |
| Compatible Nodes | Transform Content |
LlamaParse is ideal for:
| Parameter | Type | Default | Description |
|---|---|---|---|
| Auto Mode (Simplified Setup) | Boolean | False | Enable automatic configuration for quick setup. When enabled, LlamaParse uses optimal settings automatically |
Available when Auto Mode is disabled
| Parameter | Type | Default | Options | Description |
|---|---|---|---|---|
| Parsed Output Format | Choice | markdown | text, markdown | Format of the parsed output |
| OCR Language (Affects Image Text) | Choice | English | English, 한국어 | Language for OCR processing of embedded images |
Available when Auto Mode is disabled
| Parameter | Type | Default | Description |
|---|---|---|---|
| Ignore Diagonal Text | Boolean | True | Skip diagonal or rotated text that may cause parsing errors |
| Disable Column Unrolling (Keep Columns Separate) | Boolean | False | Prevents merging text from columns into a single reading sequence |