docs: add multi-vector reranking, answerdotai and studies section (#1579)

docs/mkdocs.yml

@@ -108,6 +108,7 @@ nav:
               - ColBERT Reranker: reranking/colbert.md
               - Jina Reranker: reranking/jina.md
               - OpenAI Reranker: reranking/openai.md
+              - AnswerDotAi Rerankers: reranking/answerdotai.md
               - Building Custom Rerankers: reranking/custom_reranker.md
               - Example: notebooks/lancedb_reranking.ipynb
           - Filtering: sql.md
@@ -179,6 +180,8 @@ nav:
               - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
           - 🦀 Rust:
               - Overview: examples/examples_rust.md
+      - Studies:
+          - ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
       - 💭 FAQs: faq.md
       - ⚙️ API reference:
           - 🐍 Python: python/python.md
@@ -219,6 +222,7 @@ nav:
           - ColBERT Reranker: reranking/colbert.md
           - Jina Reranker: reranking/jina.md
           - OpenAI Reranker: reranking/openai.md
+          - AnswerDotAi Rerankers: reranking/answerdotai.md
           - Building Custom Rerankers: reranking/custom_reranker.md
           - Example: notebooks/lancedb_reranking.ipynb
       - Filtering: sql.md
@@ -286,6 +290,9 @@ nav:
           - TransformersJS Embedding Search: examples/transformerjs_embedding_search_nodejs.md
       - 🦀 Rust:
           - Overview: examples/examples_rust.md
+  - Studies:
+    - studies/overview.md
+    - ↗Improve retrievers with hybrid search and reranking: https://blog.lancedb.com/hybrid-search-and-reranking-report/
   - API reference:
       - Overview: api_reference.md
       - Python: python/python.md

docs/src/reranking/index.md

@@ -45,6 +45,23 @@ tbl.create_fts_index("text")
 result = tbl.query("hello", query_type="hybrid").rerank(reranker).to_list()
 ```
 
+### Multi-vector reranking
+Most rerankers support reranking based on multiple vectors. To rerank based on multiple vectors, you can pass a list of vectors to the `rerank` method. Here's an example of how to rerank based on multiple vector columns using the `CrossEncoderReranker`:
+
+```python
+from lancedb.rerankers import CrossEncoderReranker
+
+reranker = CrossEncoderReranker()
+
+query = "hello"
+
+res1 = table.search(query, vector_column_name="vector").limit(3)
+res2 = table.search(query, vector_column_name="text_vector").limit(3)
+res3 = table.search(query, vector_column_name="meta_vector").limit(3)
+
+reranked = reranker.rerank_multivector([res1, res2, res3],  deduplicate=True)
+```
+    
 ## Available Rerankers
 LanceDB comes with some built-in rerankers. Here are some of the rerankers that are available in LanceDB:
 

docs/src/studies/overview.md

@@ -0,0 +1,4 @@
+This is a list of benchmarks and reports we've worked on at LanceDB. Some of these are continuously updated, while others are one-off reports.
+
+- [Improve retrievers with hybrid search and reranking](https://blog.lancedb.com/hybrid-search-and-reranking-report/)
+