Commitf9c5ff2

committed

Clarify examples and add some more information about cross-encoders

1 parent46dfe4a commitf9c5ff2Copy full SHA for f9c5ff2

File tree

-2

lines changed

-2

lines changed

Lines changed: 8 additions & 2 deletions

Original file line number	Diff line number	Diff line change
`@@ -19,16 +19,22 @@ pgml.rank(`
`19`	`19`
`20`	`20`	`##Example`
`21`	`21`
	`22`	`+Ranking documents is as simple as calling the the function with the documents you want to rank, and text you want to rank against:`
	`23`	`+`
`22`	`24`	```postgresql
`23`	`25`	`SELECT pgml.rank('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2']);`
`24`	`26`	```
`25`	`27`
	`28`	+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.
	`29`	`+`
`26`	`30`	```postgresql
`27`		`-SELECT pgml.chunk('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2'], '{"return_documents": false, "top_k": 10}'::JSONB);`
	`31`	`+SELECT pgml.rank('mixedbread-ai/mxbai-rerank-base-v1', 'test', ARRAY['doc1', 'doc2'], '{"return_documents": false, "top_k": 10}'::JSONB);`
`28`	`32`	```
`29`	`33`
`30`	`34`	`##Supported ranking models`
`31`	`35`
`32`		`-We support the following ranking models:`
	`36`	`+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.`
	`37`	`+`
	`38`	`+By default we provide the following ranking models:`
`33`	`39`
`34`	`40`	*`mixedbread-ai/mxbai-rerank-base-v1`

Comments

(0)