enquire-mcp API reference - v3.9.0-rc.4
    Preparing search index...

    Interface EmbedHit

    One chunk-level hit from embeddingsSearch.

    Unlike SemanticHit, embedding hits are chunk-scoped (not note- scoped) — chunk_index / line_start / line_end let the agent jump to the exact paragraph that matched.

    interface EmbedHit {
        chunk_index: number;
        kind: "md" | "pdf";
        line_end: number;
        line_start: number;
        path: string;
        score: number;
        snippet: string;
        title: string;
    }
    Index

    Properties

    chunk_index: number

    0-based chunk number within the source file.

    kind: "md" | "pdf"

    v2.8.0 — content-source kind ("md" | "pdf").

    line_end: number

    1-based end line of the chunk (inclusive).

    line_start: number

    1-based start line of the chunk in the source file.

    path: string

    Vault-relative path of the source file (markdown or PDF).

    score: number

    Cosine score in [-1, 1], rounded to 4 decimals. Sort key.

    snippet: string

    ~240-char excerpt from the matching chunk.

    title: string

    .md/.pdf-stripped basename for display.