You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* <p>Custom classifier - a custom model that you have created and trained.
50
-
* For input, you can provide plain text, a single-page document (PDF, Word, or image), or Textract API output.
51
-
* For more information, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html">Custom classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>
50
+
* For input, you can provide plain text, a single-page document (PDF, Word, or image), or
51
+
* Amazon Textract API output. For more information, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html">Custom classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>
52
52
* </li>
53
53
* <li>
54
-
* <p>Prompt classifier - Amazon Comprehend provides a model for classifying prompts.
54
+
* <p>Prompt safety classifier - Amazon Comprehend provides a pre-trained model for classifying
55
+
* input prompts for generative AI applications.
55
56
* For input, you provide English plain text input.
56
-
* For prompt classification, the response includes only the <code>Classes</code> field.
57
-
* For more information about prompt classifiers, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/prompt-classification.html">Prompt classifiers</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>
57
+
* For prompt safety classification, the response includes only the <code>Classes</code> field.
58
+
* For more information about prompt safety classifiers, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/trust-safety.html#prompt-classification">Prompt safety classification</a> in the <i>Amazon Comprehend Developer Guide</i>.</p>
58
59
* </li>
59
60
* </ul>
60
61
* <p>If the system detects errors while processing a page in the input document,
61
-
* the API response includes an entry in <code>Errors</code> that describes the errors.</p>
62
+
* the API response includes an <code>Errors</code> field that describes the errors.</p>
62
63
* <p>If the system detects a document-level error in your input document, the API returns an
* <p>Performs toxicity analysis on the list of text strings that you provide as input.
45
-
* The analysis uses the order of strings in the list to determine context when predicting toxicity.
46
45
* The API response contains a results list that matches the size of the input list.
47
-
* For more information about toxicity detection, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/toxicity-detection.html">Toxicity detection</a> in the <i>Amazon Comprehend Developer Guide</i>
48
-
* </p>
46
+
* For more information about toxicity detection, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/toxicity-detection.html">Toxicity detection</a> in the <i>Amazon Comprehend Developer Guide</i>.
47
+
* </p>
49
48
* @example
50
49
* Use a bare-bones client and the command you need to make an API call.
0 commit comments