# `Chunx.Chunk`
[🔗](https://github.com/preciz/chunx/blob/v0.2.0/lib/chunx/chunk.ex#L1)

Struct representing a text chunk with metadata.

## Fields
  * `:text` - The text content of the chunk
  * `:start_byte` - The starting byte offset of the chunk in the original text
  * `:end_byte` - The ending byte offset of the chunk in the original text
  * `:token_count` - The number of content tokens in the chunk, excluding
    tokenizer entries without a byte span
  * `:embedding` - The embedding vector for the chunk (optional)

# `t`

```elixir
@type t() :: %Chunx.Chunk{
  embedding: Nx.Tensor.t() | nil,
  end_byte: non_neg_integer(),
  start_byte: non_neg_integer(),
  text: String.t(),
  token_count: non_neg_integer()
}
```

# `new`

```elixir
@spec new(
  String.t(),
  non_neg_integer(),
  non_neg_integer(),
  pos_integer(),
  Nx.Tensor.t() | nil
) :: t()
```

Creates a chunk. Byte offsets use a half-open range.

---

*Consult [api-reference.md](api-reference.md) for complete listing*