Parser¶
Parser turns JSON-like text into structured data, including output from a language model that contains code fences or escaping errors. Place it before nodes that need fields rather than a raw text response.
- Category: Processing
- Purpose: Safely parses stringified or malformed JSON, including markdown code blocks and escape sequences. Useful for cleaning up LLM output
- Inputs:
input- Data to parse - Outputs:
output- Parsed result - Configuration:
- Output Format:
json(returns a parsed object usable by later nodes) oryaml(returns readable text). Defaultjson - Input: Leave empty to process the connected node's output directly, or use
${{node_name}}to select a source. Multiple sources can be combined with surrounding text - Usage: This node reformats — it does not select fields. Extracting a single field requires a Code Node.