Filter
Llm Filter
Filter documents using LLM-based semantic evaluation
Note: This playground provides simulated output to showcase functionality. No data is processed on our servers. Use this demo to explore the stage's configuration options before integrating it into your retriever pipeline.
Configuration
string
Required
REQUIRED. Prompt template for LLM evaluation. Should instruct the LLM to return true/false.
string
LLM model to use for evaluation.
number
Confidence threshold for keeping documents.
integer
Number of documents to evaluate per LLM call.
Output
No output yet
Configure the stage parameters and click "Run Stage" to see the simulated output.
Related to llm_filter
Pages on the same stages, extractors and patterns.
Retriever
Feature Search
Search and filter documents by vector similarity using feature embeddings
Learn more
Retriever
Attribute Filter
Filter documents by metadata attribute values using boolean logic
Learn more
Retriever
Agent Search
LLM-driven multi-step retrieval with iterative reasoning and tool orchestration
Learn more
Retriever
Query Expand
Generate query variations with LLM and fuse search results via RRF
Learn more
Retriever
Score Threshold
Drop results below an absolute score and return no results when nothing qualifies
Learn more