# `Chunx.Chunker.Semantic`
[🔗](https://github.com/preciz/chunx/blob/main/lib/chunx/chunker/semantic.ex#L1)

Implements semantic chunking using sentence embeddings.

Splits text into semantically coherent chunks using embeddings
while respecting token limits.

# `chunk_opts`

```elixir
@type chunk_opts() :: [
  chunk_size: pos_integer(),
  threshold: float() | :auto,
  min_sentences: pos_integer(),
  min_chunk_size: pos_integer(),
  threshold_step: float()
]
```

# `chunk`

```elixir
@spec chunk(
  binary(),
  Tokenizers.Tokenizer.t(),
  ([String.t()] -> [Nx.Tensor.t()]),
  chunk_opts()
) :: {:ok, [Chunx.SentenceChunk.t()]} | {:error, term()}
```

Splits text into semantically coherent chunks using embeddings.

## Options
  * `:chunk_size` - Maximum number of tokens per chunk (default: 512)
  * `:threshold` - Threshold for semantic similarity (0-1) or :auto (default: :auto)
  * `:min_sentences` - Minimum number of sentences per chunk (default: 1)
  * `:min_chunk_size` - Minimum number of tokens per chunk (default: 2)
  * `:threshold_step` - Step size for threshold calculation (default: 0.01)

---

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