Embeddings
embeddings
endpoint generates embeddings from the input text and returns a vector.Embeddings are used by data scientists to capture semantic information about language.
How to Call the Endpoint
Python SDK
First, make sure you are using the latest version of the SDK; the endpoint will not work on versions prior to 2.2.0. You can use this command to upgrade:
pip install scienceio --upgrade
After initializing the ScienceIO client, use scio.embeddings()
to submit the request:
from scienceio import ScienceIO
scio = ScienceIO()
query_text = "The patient presents with a complaint of allergies to ragweed."
# Call the embeddings endpoint
response = scio.embeddings(query_text)
# Print and format the response
import json
print(json.dumps(response, indent=2))
HTTP
~/.bashrc
or ~/.zshrc
(depending on your shell). For additional help, see Configure Environment Variables.Update the endpoint in your POST request to embeddings
as shown in the URL below:
curl https://api.aws.science.io/v2/embeddings \
--request POST \
--header "Content-type: application/json" \
--header "x-api-id: $SCIENCEIO_KEY_ID" \
--header "x-api-secret: $SCIENCEIO_KEY_SECRET" \
--data '{ "input_text": "The patient presents with a complaint of allergies to ragweed."}'
You will receive a response containing a request_id
and the inference_status
. Use the request_id
in your GET request as shown below to retrieve your results:
curl https://api.aws.science.io/v2/embeddings/<REQUEST_ID> \
--request GET \
--header "x-api-id: $SCIENCEIO_KEY_ID" \
--header "x-api-secret: $SCIENCEIO_KEY_SECRET"
JSON Response
A response from the embeddings
endpoint contains a vector with 1024 numbers.
Note: The JSON response below has been purposely truncated due to length; the actual response does contain 1024 numbers.
{
"input_text": "The patient presents with a complaint of allergies to ragweed.",
"embeddings": [
1.8246774673461914,
-0.844181478023529,
-1.5076367855072021,
-1.3067437410354614,
-1.7539191246032715,
-2.1734962463378906,
-1.7270381450653076,
-0.021796129643917084,
1.8656187057495117,
1.1780860424041748,
2.352179527282715,
4.2799072265625,
1.001699686050415,
4.147101402282715,
1.4132367372512817,
-0.5631498694419861,
1.8193037509918213,
1.82432222366333,
0.13829514384269714,
0.24757304787635803,
-0.232064887881279,
0.49826741218566895,
1.6542580127716064,
0.8582350015640259,
-4.373599052429199,
...
]
}
Feedback
Was this page helpful?
Great! If you ever have questions or want to provide feedback, send us an email.
Bummer. We hate when we miss the mark. If you have suggestions for improvements or other general comments, send us an email.