Rerank (v1 API)

This endpoint takes in a query and a list of texts and produces an ordered array with each text assigned a relevance score.

Headers

X-Client-NamestringOptional

The name of the project that is making the request.

Request

This endpoint expects an object.

querystringRequired

The search query

documentslist of strings or maps from strings to stringsRequired

A list of document objects or strings to rerank. If a document is provided the text fields is required and all other fields will be preserved in the response.

The total max chunks (length of documents * max_chunks_per_doc) must be less than 10000.

We recommend a maximum of 1,000 documents for optimal endpoint performance.

modelstringOptional

The identifier of the model to use, one of : rerank-english-v3.0, rerank-multilingual-v3.0, rerank-english-v2.0, rerank-multilingual-v2.0

top_nintegerOptional

The number of most relevant documents or indices to return, defaults to the length of the documents

rank_fieldslist of stringsOptional

If a JSON object is provided, you can specify which keys you would like to have considered for reranking. The model will rerank based on order of the fields passed in (i.e. rank_fields=[‘title’,‘author’,‘text’] will rerank using the values in title, author, text sequentially. If the length of title, author, and text exceeds the context length of the model, the chunking will not re-consider earlier fields). If not provided, the model will use the default text field for ranking.

return_documentsbooleanOptional

If false, returns results without the doc text - the api will return a list of {index, relevance score} where index is inferred from the list passed into the request.
If true, returns results with the doc text passed in - the api will return an ordered list of {index, text, relevance score} where index + text refers to the list passed into the request.

max_chunks_per_docintegerOptional

The maximum number of chunks to produce internally from a document

Response

This endpoint returns an object.

resultslist of objects

An ordered list of ranked documents

idstringOptional

metaobjectOptional

1	import cohere
2
3	co = cohere.Client()
4
5	docs = [
6	"Carson City is the capital city of the American state of Nevada.",
7	"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
8	"Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
9	"Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
10	"Capital punishment (the death penalty) has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states.",
11	]
12
13	response = co.rerank(
14	model="rerank-english-v3.0",
15	query="What is the capital of the United States?",
16	documents=docs,
17	top_n=3,
18	)
19	print(response)

1	{
2	"results": [
3	{
4	"index": 3,
5	"relevance_score": 0.999071
6	},
7	{
8	"index": 4,
9	"relevance_score": 0.7867867
10	},
11	{
12	"index": 0,
13	"relevance_score": 0.32713068
14	}
15	],
16	"id": "8bc745a3-7871-4597-822e-18c95d5df48c",
17	"meta": {
18	"api_version": {
19	"version": "1"
20	},
21	"billed_units": {
22	"search_units": 1
23	}
24	}
25	}