tessl/npm-pulumi--aws
A Pulumi package for creating and managing Amazon Web Services (AWS) cloud resources with infrastructure-as-code.
—
Quality
Pending
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
comprehend.mddocs/services/
Amazon Comprehend
Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find insights and relationships in text.
Package
import * as aws from "@pulumi/aws";Overview
Amazon Comprehend provides pre-trained and custom ML models for text analysis.
Key Features
Sentiment Analysis
Determine positive, negative, neutral, or mixed sentiment.
const sentimentRole = new aws.iam.Role("comprehend-role", {
assumeRolePolicy: JSON.stringify({
Version: "2012-10-17",
Statement: [{
Action: "sts:AssumeRole",
Effect: "Allow",
Principal: {
Service: "comprehend.amazonaws.com",
},
}],
}),
});
const sentimentPolicy = new aws.iam.Policy("comprehend-s3", {
policy: JSON.stringify({
Version: "2012-10-17",
Statement: [{
Effect: "Allow",
Action: [
"s3:GetObject",
"s3:ListBucket",
"s3:PutObject",
],
Resource: [
bucket.arn,
pulumi.interpolate`${bucket.arn}/*`,
],
}],
}),
});
new aws.iam.RolePolicyAttachment("attach", {
role: sentimentRole.name,
policyArn: sentimentPolicy.arn,
});Entity Recognition
Identify people, places, organizations, dates, and more.
Key Phrase Extraction
Extract key phrases and topics from text.
Language Detection
Detect the dominant language in text.
Custom Classification
Train custom models for document classification.
const documentClassifierRole = new aws.iam.Role("classifier-role", {
assumeRolePolicy: JSON.stringify({
Version: "2012-10-17",
Statement: [{
Action: "sts:AssumeRole",
Effect: "Allow",
Principal: {
Service: "comprehend.amazonaws.com",
},
}],
}),
});Custom Entity Recognition
Train models to recognize custom entities specific to your domain.
Common Patterns
Lambda Integration
const comprehendLambda = new aws.lambda.Function("text-analysis", {
runtime: "python3.11",
handler: "index.handler",
role: lambdaRole.arn,
code: new pulumi.asset.AssetArchive({
"index.py": new pulumi.asset.StringAsset(`
import boto3
import json
comprehend = boto3.client('comprehend')
def handler(event, context):
text = event['text']
# Detect sentiment
sentiment = comprehend.detect_sentiment(
Text=text,
LanguageCode='en'
)
# Extract entities
entities = comprehend.detect_entities(
Text=text,
LanguageCode='en'
)
return {
'sentiment': sentiment,
'entities': entities
}
`),
}),
});Batch Analysis
Process large volumes of documents.
const batchRole = new aws.iam.Role("batch-role", {
assumeRolePolicy: JSON.stringify({
Version: "2012-10-17",
Statement: [{
Action: "sts:AssumeRole",
Effect: "Allow",
Principal: {
Service: "comprehend.amazonaws.com",
},
}],
}),
});Use Cases
- Customer Feedback Analysis: Analyze reviews and feedback
- Social Media Monitoring: Track brand sentiment
- Document Classification: Categorize support tickets
- Content Moderation: Detect inappropriate content
- Medical Text Analysis: Extract medical entities (Comprehend Medical)
Related Services
Install with Tessl CLI
npx tessl i tessl/npm-pulumi--aws