You're looking at a specific version of this model. Jump to the model overview.
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| query_texts |
string
|
A JSON formatted array of strings you wish to generate *retreival* embeddings for. (note, that you should keep this list short to avoid Replicate response size limitations). Use this to embed short text queries intended for comparison against document text. A vector will be returned corresponding to each line of text in the input array (in order of input). This endpoint will automatically format your query strings for retrieval, you do not need to preprocess them.
|
|
| file_excerpts |
string
|
A JSON object formatted string, where each key of the object corresponds to a collection of text excerpts, and each value is an array of strings composing that collection. Embeddings will be generated for each excerpt. A JSON formatted string will be returned, where each key corresponds to the input collection and each value is a url through which the embeddings for that collection may be downloaded (the output embeddings will be in the order of the input text excerpts to which they correspond).
|
|
| normalize |
boolean
|
True
|
normalizes returned embedding vectors to a magnitude of 1. (default: true, as this model presumes cosine similarity comparisons downstream)
|
| batchtoken_max |
integer
|
80000
Min: 512 |
maximumum number of tokens to try to stuff into a batch (to avoid out of memory errors but maximize throughput). If the total number of tokens across the flattened list of requested embeddings exceed this value, the list will be split internally and run across multiple forward passes. This will not affect the shape of your output, just the time it takes to run.
|
| precision |
string
(enum)
|
full
Options: full, half |
either full or half. defaults to a paranoid value of full. You should prefer to use the same precision for querying as you do for archiving
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'document_embeddings': {'items': {'format': 'uri',
'type': 'string'},
'title': 'Document Embeddings',
'type': 'array'},
'metrics': {'title': 'Metrics', 'type': 'string'},
'query_embeddings': {'items': {'items': {'type': 'number'},
'type': 'array'},
'title': 'Query Embeddings',
'type': 'array'}},
'required': ['query_embeddings', 'document_embeddings', 'metrics'],
'title': 'Output',
'type': 'object'}