Llm Enrich
Enrich documents with LLM-generated fields using natural language prompts
Configuration
LLM provider: 'openai', 'google', or 'anthropic'. Auto-inferred from model_name.
Specific LLM model. Examples: gemini-3.1-flash-lite, gpt-4o-mini, claude-3-5-haiku-20241022.
REQUIRED. Prompt template. Supports {{DOC.field}} and {{INPUT.field}} variables.
REQUIRED. Dot-path where generated content is stored.
Documents per LLM request batch.
JSON schema for structured LLM output.
Sampling temperature (0-1).
OPTIONAL. Conditional filter for selective enrichment (CRITICAL FOR COST SAVINGS).
Output
No output yet
Configure the stage parameters and click "Run Stage" to see the simulated output.
Related to llm_enrich
Pages on the same stages, extractors and patterns.
Json Transform
Transform documents using Jinja2 templates that render to JSON
Rag Prepare
Prepare documents for LLM context windows with token management
External Web Search
Enrich documents with web search results using Exa AI
Api Call
Enrich documents with external API calls
Sql Lookup
Enrich documents with SQL query results from external databases
Taxonomy Enrich
Classify documents against taxonomy nodes via vector similarity