Package org.apache.tika.inference

package org.apache.tika.inference
  • Class
    Description
    Chunk
    A content chunk with multimodal locators and an optional embedding vector.
    ChunkSerializer
    Serializes and deserializes a list of Chunk objects to/from JSON.
    ChunkTarget
    Where the chunks produced for a unit land and how they name where they came from.
    EmbeddingEngine
    An engine that turns images into vectors, many per request.
    EmbedTask
    The embed task.
    MarkdownChunker
    Splits markdown text into chunks that respect structural boundaries.
    MediaInput
    One audio or video item for an engine: the bytes, their type, and which channel they are.
    OpenAIEmbeddingEngine
    An OpenAI-compatible embeddings endpoint (POST /v1/embeddings), named in "engines".
    VectorSerializer
    Serializes and deserializes float vectors as base64-encoded big-endian float32 byte arrays.