diff --git a/docs/mkdocs.yml b/docs/mkdocs.yml index a5fd070e..0eb4f4e0 100644 --- a/docs/mkdocs.yml +++ b/docs/mkdocs.yml @@ -91,8 +91,8 @@ nav: - Vector Search: search.md - Full-text search: fts.md - Hybrid search: - - hybrid_search/hybrid_search.md - - AirBNB financial data example: notebooks/hybrid_search.ipynb + - Overview: hybrid_search/hybrid_search.md + - Airbnb financial data example: notebooks/hybrid_search.ipynb - Filtering: sql.md - Versioning & Reproducibility: notebooks/reproducibility.ipynb - Configuring Storage: guides/storage.md @@ -154,8 +154,8 @@ nav: - Vector Search: search.md - Full-text search: fts.md - Hybrid search: - - hybrid_search/hybrid_search.md - - AirBNB financial data example: notebooks/hybrid_search.ipynb + - Overview: hybrid_search/hybrid_search.md + - Airbnb financial data example: notebooks/hybrid_search.ipynb - Filtering: sql.md - Versioning & Reproducibility: notebooks/reproducibility.ipynb - Configuring Storage: guides/storage.md diff --git a/docs/src/hybrid_search/hybrid_search.md b/docs/src/hybrid_search/hybrid_search.md index 4a0440a7..244e8740 100644 --- a/docs/src/hybrid_search/hybrid_search.md +++ b/docs/src/hybrid_search/hybrid_search.md @@ -1,6 +1,6 @@ # Hybrid Search -LanceDB supports both semantic and keyword-based search. In real world applications, it is often useful to combine these two approaches to get the best best results. For example, you may want to search for a document that is semantically similar to a query document, but also contains a specific keyword. This is an example of *hybrid search*, a search algorithm that combines multiple search techniques. +LanceDB supports both semantic and keyword-based search (also termed full-text search, or FTS). In real world applications, it is often useful to combine these two approaches to get the best best results. For example, you may want to search for a document that is semantically similar to a query document, but also contains a specific keyword. This is an example of *hybrid search*, a search algorithm that combines multiple search techniques. ## Hybrid search in LanceDB You can perform hybrid search in LanceDB by combining the results of semantic and full-text search via a reranking algorithm of your choice. LanceDB provides multiple rerankers out of the box. However, you can always write a custom reranker if your use case need more sophisticated logic . diff --git a/docs/src/notebooks/hybrid_search.ipynb b/docs/src/notebooks/hybrid_search.ipynb index 1f62a0f7..6a3cc32b 100644 --- a/docs/src/notebooks/hybrid_search.ipynb +++ b/docs/src/notebooks/hybrid_search.ipynb @@ -5,13 +5,13 @@ "id": "0daef1cd-9130-46b8-8eb8-1b721860e239", "metadata": {}, "source": [ - "# [Example] AirBNB fincial data search\n", + "# Example - Airbnb financial data search\n", "\n", "\"Open \n", "\n", - "LanceDB supports both semantic and keyword-based search. In real world applications, it is often useful to combine these two approaches to get the best best results. For example, you may want to search for a document that is semantically similar to a query document, but also contains a specific keyword. This is an example of hybrid search, a search algorithm that combines multiple search techniques.\n", + "The code below is an example of hybrid search, a search algorithm that combines FTS and vector search in LanceDB.\n", "\n", - "Let's get stared with an Example. In this notebook we'll use AirBNB financial data document to search for \"the specific reasons for higher operating costs\" in that particular year" + "Let's get stared with an example. In this notebook we'll use Airbnb financial data documents to search for \"the specific reasons for higher operating costs\" in a particular year." ] }, {