mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-25 06:19:57 +00:00
3ffed89793
based on https://github.com/lancedb/lancedb/pull/713 - The Reranker api can be plugged into vector only or fts only search but this PR doesn't do that (see example - https://txt.cohere.com/rerank/) ### Default reranker -- `LinearCombinationReranker(weight=0.7, fill=1.0)` ``` table.search("hello", query_type="hybrid").rerank(normalize="score").to_pandas() ``` ### Available rerankers LinearCombinationReranker ``` from lancedb.rerankers import LinearCombinationReranker # Same as default table.search("hello", query_type="hybrid").rerank( normalize="score", reranker=LinearCombinationReranker() ).to_pandas() # with custom params reranker = LinearCombinationReranker(weight=0.3, fill=1.0) table.search("hello", query_type="hybrid").rerank( normalize="score", reranker=reranker ).to_pandas() ``` Cohere Reranker ``` from lancedb.rerankers import CohereReranker # default model.. English and multi-lingual supported. See docstring for available custom params table.search("hello", query_type="hybrid").rerank( normalize="rank", # score or rank reranker=CohereReranker() ).to_pandas() ``` CrossEncoderReranker ``` from lancedb.rerankers import CrossEncoderReranker table.search("hello", query_type="hybrid").rerank( normalize="rank", reranker=CrossEncoderReranker() ).to_pandas() ``` ## Using custom Reranker ``` from lancedb.reranker import Reranker class CustomReranker(Reranker): def rerank_hybrid(self, vector_result, fts_result): combined_res = self.merge_results(vector_results, fts_results) # or use custom combination logic # Custom rerank logic here return combined_res ``` - [x] Expand testing - [x] Make sure usage makes sense - [x] Run simple benchmarks for correctness (Seeing weird result from cohere reranker in the toy example) - Support diverse rerankers by default: - [x] Cross encoding - [x] Cohere - [x] Reciprocal Rank Fusion --------- Co-authored-by: Chang She <759245+changhiskhan@users.noreply.github.com> Co-authored-by: Prashanth Rao <35005448+prrao87@users.noreply.github.com>
LanceDB
A Python library for LanceDB.
Installation
pip install lancedb
Usage
Basic Example
import lancedb
db = lancedb.connect('<PATH_TO_LANCEDB_DATASET>')
table = db.open_table('my_table')
results = table.search([0.1, 0.3]).limit(20).to_list()
print(results)
Development
Create a virtual environment and activate it:
python -m venv venv
. ./venv/bin/activate
Install the necessary packages:
python -m pip install .
To run the unit tests:
pytest
To run linter and automatically fix all errors:
ruff format python
ruff --fix python
If any packages are missing, install them with:
pip install <PACKAGE_NAME>
For Windows users, there may be errors when installing packages, so these commands may be helpful:
Activate the virtual environment:
. .\venv\Scripts\activate
You may need to run the installs separately:
pip install -e .[tests]
pip install -e .[dev]
tantivy requires rust to be installed, so install it with conda, as it doesn't support windows installation:
pip install wheel
pip install cargo
conda install rust
pip install tantivy
To run the unit tests:
pytest