### Install chunking_evaluation Package

Source: https://github.com/brandonstarxel/chunking_evaluation/blob/main/README.md

Installs the chunking_evaluation package directly from its GitHub repository using pip. This command fetches and installs the latest version of the package and its dependencies.

```bash
pip install git+https://github.com/brandonstarxel/chunking_evaluation.git
```

--------------------------------

### Configure Retrieval Strategies in Evaluation

Source: https://context7.com/brandonstarxel/chunking_evaluation/llms.txt

Shows how to toggle between adaptive retrieval (retrieving chunks based on content) and fixed-k retrieval. Also demonstrates optional caching of embeddings to disk.

```python
results_adaptive = evaluation.run(
    chunker=chunker,
    embedding_function=embedding_func,
    retrieve=-1
)
results_fixed = evaluation.run(
    chunker=chunker,
    embedding_function=embedding_func,
    retrieve=5,
    db_to_save_chunks="./chunk_cache"
)
```

--------------------------------

### Implement Custom Text Chunker in Python

Source: https://context7.com/brandonstarxel/chunking_evaluation/llms.txt

Defines an abstract base class `BaseChunker` for creating custom text chunking strategies. Users inherit from `BaseChunker` and implement the `split_text` method to define their chunking logic. This example demonstrates simple fixed-character chunking.

```python
from chunking_evaluation import BaseChunker
from typing import List

class CustomChunker(BaseChunker):
    def __init__(self, chunk_size: int = 1200):
        self.chunk_size = chunk_size

    def split_text(self, text: str) -> List[str]:
        # Simple fixed-character chunking
        chunks = []
        for i in range(0, len(text), self.chunk_size):
            chunks.append(text[i:i + self.chunk_size])
        return chunks

# Usage
chunker = CustomChunker(chunk_size=1000)
text = "Your long document text here..."
chunks = chunker.split_text(text)
print(f"Created {len(chunks)} chunks")
# Output: Created 5 chunks
```