> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lancedb.com/llms.txt
> Use this file to discover all available pages before exploring further.

# ColBERT Reranker

> Enhance search results with ColBERT's contextual reranking in LanceDB. Features efficient model deployment, device optimization, and flexible scoring options for vector, FTS, and hybrid search.

# ColBERT Reranker

This reranker uses ColBERT model to rerank the search results. You can use this reranker by passing `ColbertReranker()` to the `rerank()` method.

> **Note:** Supported query types: Hybrid, Vector, and FTS.

```python Python icon="python" theme={"theme":{"light":"vitesse-light","dark":"catppuccin-mocha"}}
import tempfile
from pathlib import Path

import lancedb
from lancedb.embeddings import get_registry
from lancedb.pydantic import LanceModel, Vector
from lancedb.rerankers import ColbertReranker

embedder = get_registry().get("sentence-transformers").create()
db = lancedb.connect(str(Path(tempfile.mkdtemp()) / "colbert-rerank"))

class Schema(LanceModel):
    text: str = embedder.SourceField()
    vector: Vector(embedder.ndims()) = embedder.VectorField()

data = [
    {"text": "hello world"},
    {"text": "goodbye world"},
]
tbl = db.create_table("test", schema=Schema)
tbl.add(data)
reranker = ColbertReranker()

# Run vector search with a reranker
result = tbl.search("hello").rerank(reranker=reranker).to_list()

# Build the full-text index before either FTS or hybrid search.
tbl.create_fts_index("text", replace=True)

# Run FTS search with a reranker
result = tbl.search("hello", query_type="fts").rerank(reranker=reranker).to_list()

# Run hybrid search with a reranker
result = (
    tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
)
```

## Accepted Arguments

| Argument | Type | Default | Description |
| - | - | - | - |
| `model_name` | `str` | `"colbert-ir/colbertv2.0"` | The name of the reranker model to use. |
| `column` | `str` | `"text"` | The name of the column to use as input to the cross encoder model. |
| `device` | `str` | `None` | The device to use for the cross encoder model. If None, will use "cuda" if available, otherwise "cpu". |
| `return_score` | `str` | `"relevance"` | Options are "relevance" or "all". The type of score to return. If "relevance", will return only the `_relevance_score` column. If "all" is supported, will return relevance score along with the vector and/or fts scores depending on query type. |

## Supported Scores for each query type

You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:

### Hybrid Search

| `return_score` | Status | Description |
| - | - | - |
| `relevance` | ✅ Supported | Results only have the `_relevance_score` column. |
| `all` | ❌ Not Supported | Results have vector(`_distance`) and FTS(`score`) along with Hybrid Search score(`_relevance_score`). |

### Vector Search

| `return_score` | Status | Description |
| - | - | - |
| `relevance` | ✅ Supported | Results only have the `_relevance_score` column. |
| `all` | ✅ Supported | Results have vector(`_distance`) along with Hybrid Search score(`_relevance_score`). |

### FTS Search

| `return_score` | Status | Description |
| - | - | - |
| `relevance` | ✅ Supported | Results only have the `_relevance_score` column. |
| `all` | ✅ Supported | Results have FTS(`score`) along with Hybrid Search score(`_relevance_score`). |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.