Jun 12, 2024 · Jun 7, 2024 · Jun 7, 2024 · Jun 7, 2024 · Jun 7, 2024 · Jun 7, 2024
diff --git a/pgml-cms/docs/api/sql-extension/pgml.rank.md b/pgml-cms/docs/api/sql-extension/pgml.rank.md

 ## Example

 Ranking documents is as simple as calling the the function with the documents you want to rank, and text you want to rank against:

 ```postgresql
 SELECT pgml.rank('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2']);
 ```

 By default the `pgml.rank()` function will return and rank all of the documents. The function can be configured to only return the relevance score and index of the top k documents by setting `return_documents` to `false` and `top_k` to the number of documents you want returned.

 ```postgresql
 SELECT pgml.chunk('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2'], '{"return_documents": false, "top_k": 10}'::JSONB);
 SELECT pgml.rank('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2'], '{"return_documents": false, "top_k": 10}'::JSONB);
 ```

 ## Supported ranking models

 We support the following ranking models:
 We currently support cross-encoders for re-ranking. Check out [Sentence Transformer's documentation](https://sbert.net/examples/applications/cross-encoder/README.html) for more information on how cross-encoders work.

 By default we provide the following ranking models:

 * `mixedbread-ai/mxbai-rerank-base-v1`
Original file line number	Diff line number	Diff line change
Expand Up		@@ -19,16 +19,22 @@ pgml.rank(

		## Example

Copy link Contributor levkkJun 7, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. Let's document the difference between these calls. Take a look at examples: https://postgresml.org/docs/api/sql-extension/pgml.transform/#examples https://postgresml.org/docs/api/sql-extension/pgml.embed#generate-embeddings-inside-a-table Copy link ContributorAuthor SilasMarvinJun 7, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. How does this look:`f9c5ff2`
		Ranking documents is as simple as calling the the function with the documents you want to rank, and text you want to rank against:

		```postgresql
		SELECT pgml.rank('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2']);
		```

		By default the `pgml.rank()` function will return and rank all of the documents. The function can be configured to only return the relevance score and index of the top k documents by setting `return_documents` to `false` and `top_k` to the number of documents you want returned.

		```postgresql
		SELECT pgml.chunk('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2'], '{"return_documents": false, "top_k": 10}'::JSONB);
		SELECT pgml.rank('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2'], '{"return_documents": false, "top_k": 10}'::JSONB);
		```

		## Supported ranking models

		We support the following ranking models:
		We currently support cross-encoders for re-ranking. Check out [Sentence Transformer's documentation](https://sbert.net/examples/applications/cross-encoder/README.html) for more information on how cross-encoders work.

SilasMarvin marked this conversation as resolved. Show resolvedHide resolved
		By default we provide the following ranking models:

		* `mixedbread-ai/mxbai-rerank-base-v1`
Copy link katopzJun 8, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. Can I use other models from hugging face? There's no mention here. Copy link ContributorAuthor SilasMarvinJun 8, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. Yes you can. If you are using a serverless hosted database you can request for that model specifically. Is there a model you are interested in using that is not here? katopz reacted with thumbs up emoji Copy link katopzJun 8, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. Just to make sure that I can use any because embedding and reranking models will get update regularly. I currently pick: for embedding (multilingual) 👉https://huggingface.co/BAAI/bge-m3 for reranking 👉https://huggingface.co/BAAI/bge-reranker-large SilasMarvin reacted with thumbs up emoji Copy link ContributorAuthor SilasMarvinJun 10, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. Those should work. If you are using serverless and want to use them, you will need to request access to them. Let me know if you have any problems and I'm happy to take a look! katopz reacted with thumbs up emoji