English language model text encoder

import requests

url = "https://application_id.applications.lucidworks.com/ai/prediction/embedding/text-encoder"

payload = {
    "batch": [{ "text": "<string>" }],
    "useCaseConfig": { "dataType": "query or passage" }
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

English language model text encoder

The English language encoder is an embedding use that takes in plain English text and returns a 768-dimensional vector encoding of that text. This model powers this semantic search.

The API truncates incoming text to approximately 256 words before the model encodes it and returns a vector. An example usage pattern is to encode all the texts and descriptions in a website and then use this encoder on query text, supporting natural language queries such as “1990s children’s fiction”.

Each API request includes one batch containing up to 32 text strings.

POST

prediction

embedding

text-encoder

English language model text encoder

import requests

url = "https://application_id.applications.lucidworks.com/ai/prediction/embedding/text-encoder"

payload = {
    "batch": [{ "text": "<string>" }],
    "useCaseConfig": { "dataType": "query or passage" }
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

Headers

Authorization: Bearer ACCESS_TOKEN

string

The authentication and authorization access token.

Content-Type

string

application/json

Example:

"application/json"

Body

application/json

batch

object[]

The batch of key:value pairs used as inputs in the prediction. Up to 32 inputs per request are allowed.

Maximum array length: 32

Show child attributes

batch.text

string

The content the model analyzes.

useCaseConfig

UseCaseConfigKeywordEmbedding · object

Show child attributes

useCaseConfig.dataType

string

default:query

This optional parameter enables model-specific handling in the Prediction API to help improve model accuracy. Use the most applicable fields based on available dataTypes and the dataType value that best aligns with the text sent to the Prediction API.

The two string values to use for embedding models are:

"dataType": "query" for the query. For query-to-query pairing, best practice is to use dataType=query on both API calls.
"dataType": "passage" for fields searched at query time.

For example, if questions and answers from a FAQ are indexed, the value for questions is "dataType": "query" and the value for the answers is "dataType": "passage".

Example:

"query or passage"

Response

200 - application/json

predictions

object[]

Show child attributes

predictions.vector

any[]

The list of model predictions for the input batch.

Example:

[
  -0.0011799398344010115,
  0.07051781564950943,
  -0.06832550466060638,
  0.020428132265806198,
  0.11977626383304596
]

Model predictions by use case Multilingual language model text encoder

⌘I

Models

Authentication

Use Case

Predict

Async Chunking

Async Predict

Prompt Preview

Signals

Tokenization

English language model text encoder

Headers

Body

Response