NEWVectors or files. Pick a path.Start →
    Apply

    Rag Prepare

    Prepare documents for LLM context windows with token management

    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

    integer

    Maximum tokens for combined context output.

    string

    Tokenizer for token counting.

    string

    How to handle overflow: 'priority_truncate', 'proportional', 'drop_last'.

    string

    Output format: 'single_context' (combined) or 'formatted_list' (individual).

    string

    Template for formatting each document. Supports {{DOC.*}}, {{CONTEXT.INDEX}}, {{CONTEXT.CITATION}}.

    object

    Citation configuration for source tracking.

    Output

    No output yet

    Configure the stage parameters and click "Run Stage" to see the simulated output.