github.com/vdparikhrh/moderator
Package provides easy integration with AWS Comprehend APIs Amazon Comprehend is a platform within Amazon Web Services (AWS) that uses machine learning to find insights in unstructured text. You can either use pre-trained text analysis models or customize your own to extract specific pieces of information, identify sentiment, and find topics in a collection of documents.
Readme
Package to provide easy integration with AWS Comprehend APIs.
Amazon Comprehend is a platform within Amazon Web Services (AWS) that uses machine learning to find insights in unstructured text. You can either use pre-trained text analysis models or customize your own to extract specific pieces of information, identify sentiment, and find topics in a collection of documents.
package main
import (
"encoding/json"
"fmt"
"log"
"net/http"
moderator "github.com/vdparikhrh/moderator"
)
type Server struct {
client moderator.Moderator
}
type Request struct {
Text string `json:"text"`
}
func main() {
var s Server
s.client = moderator.New("en")
http.HandleFunc("/", s.AnalyzeText)
fmt.Printf("Starting server for text analysis...\n")
if err := http.ListenAndServe(":8080", nil); err != nil {
log.Fatal(err)
}
}
func (s *Server) AnalyzeText(w http.ResponseWriter, r *http.Request) {
var request Request
err := json.NewDecoder(r.Body).Decode(&request)
if err != nil {
http.Error(w, "Invalid Body", http.StatusInternalServerError)
return
}
// Takes text as input parameters
// Second parameter is translate if the text is not in EN
msg := s.client.Analyze(request.Text, true)
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(msg)
}
curl --location --request POST 'localhost:8080' \
--header 'Content-Type: application/json' \
--data-raw '{
"text": "Hello Vishal Parikh, I am John. Your AnyCompany Financial Services, LLC credit card account 1111-0000-1111-0008 has a minimum payment of $24.53"
}'
{
"MessageID": "459ad748-789b-4f3b-909d-716878948bff",
"text": "Hello Vishal Parikh, I am John. Your AnyCompany Financial Services, LLC credit card account 1111-0000-1111-0008 has a minimum payment of $24.53",
"pii": {
"Entities": [
{
"BeginOffset": 6,
"EndOffset": 19,
"Score": 0.9999790787696838,
"Type": "NAME"
},
{
"BeginOffset": 26,
"EndOffset": 30,
"Score": 0.9999895095825195,
"Type": "NAME"
},
{
"BeginOffset": 92,
"EndOffset": 111,
"Score": 0.9990487694740295,
"Type": "BANK_ACCOUNT_NUMBER"
}
]
},
"languages": {
"Languages": [
{
"LanguageCode": "en",
"Score": 0.9806605577468872
}
]
},
"sentiment": {
"Sentiment": "NEUTRAL",
"SentimentScore": {
"Mixed": 0.0000050544572332000826,
"Negative": 0.0004280143475625664,
"Neutral": 0.9985914826393127,
"Positive": 0.0009754511411301792
}
},
"entities": {
"Entities": [
{
"BeginOffset": 6,
"EndOffset": 19,
"Score": 0.9996585845947266,
"Text": "Vishal Parikh",
"Type": "PERSON"
},
{
"BeginOffset": 26,
"EndOffset": 30,
"Score": 0.9987456798553467,
"Text": "John",
"Type": "PERSON"
},
{
"BeginOffset": 37,
"EndOffset": 71,
"Score": 0.9970827698707581,
"Text": "AnyCompany Financial Services, LLC",
"Type": "ORGANIZATION"
},
{
"BeginOffset": 92,
"EndOffset": 111,
"Score": 0.9832412004470825,
"Text": "1111-0000-1111-0008",
"Type": "OTHER"
},
{
"BeginOffset": 137,
"EndOffset": 143,
"Score": 0.9973769783973694,
"Text": "$24.53",
"Type": "QUANTITY"
}
]
},
"key_phrases": {
"KeyPhrases": [
{
"BeginOffset": 6,
"EndOffset": 19,
"Score": 0.9719115495681763,
"Text": "Vishal Parikh"
},
{
"BeginOffset": 26,
"EndOffset": 30,
"Score": 0.9995399713516235,
"Text": "John"
},
{
"BeginOffset": 32,
"EndOffset": 66,
"Score": 0.9826791286468506,
"Text": "Your AnyCompany Financial Services"
},
{
"BeginOffset": 68,
"EndOffset": 111,
"Score": 0.8073769211769104,
"Text": "LLC credit card account 1111-0000-1111-0008"
},
{
"BeginOffset": 116,
"EndOffset": 133,
"Score": 0.9997748732566833,
"Text": "a minimum payment"
}
]
},
"syntax": {
"SyntaxTokens": [
{
"BeginOffset": 0,
"EndOffset": 5,
"PartOfSpeech": {
"Score": 0.9827689528465271,
"Tag": "INTJ"
},
"Text": "Hello",
"TokenId": 1
},
{
"BeginOffset": 6,
"EndOffset": 12,
"PartOfSpeech": {
"Score": 0.9977828860282898,
"Tag": "PROPN"
},
"Text": "Vishal",
"TokenId": 2
},
{
"BeginOffset": 13,
"EndOffset": 19,
"PartOfSpeech": {
"Score": 0.9993051290512085,
"Tag": "PROPN"
},
"Text": "Parikh",
"TokenId": 3
},
{
"BeginOffset": 19,
"EndOffset": 20,
"PartOfSpeech": {
"Score": 0.9999982118606567,
"Tag": "PUNCT"
},
"Text": ",",
"TokenId": 4
},
{
"BeginOffset": 21,
"EndOffset": 22,
"PartOfSpeech": {
"Score": 0.9997889399528503,
"Tag": "PRON"
},
"Text": "I",
"TokenId": 5
},
{
"BeginOffset": 23,
"EndOffset": 25,
"PartOfSpeech": {
"Score": 0.9863438606262207,
"Tag": "VERB"
},
"Text": "am",
"TokenId": 6
},
{
"BeginOffset": 26,
"EndOffset": 30,
"PartOfSpeech": {
"Score": 0.9998950958251953,
"Tag": "PROPN"
},
"Text": "John",
"TokenId": 7
},
{
"BeginOffset": 30,
"EndOffset": 31,
"PartOfSpeech": {
"Score": 0.9999862909317017,
"Tag": "PUNCT"
},
"Text": ".",
"TokenId": 8
},
{
"BeginOffset": 32,
"EndOffset": 36,
"PartOfSpeech": {
"Score": 0.9985802173614502,
"Tag": "PRON"
},
"Text": "Your",
"TokenId": 9
},
{
"BeginOffset": 37,
"EndOffset": 47,
"PartOfSpeech": {
"Score": 0.9924488067626953,
"Tag": "PROPN"
},
"Text": "AnyCompany",
"TokenId": 10
},
{
"BeginOffset": 48,
"EndOffset": 57,
"PartOfSpeech": {
"Score": 0.9987910389900208,
"Tag": "PROPN"
},
"Text": "Financial",
"TokenId": 11
},
{
"BeginOffset": 58,
"EndOffset": 66,
"PartOfSpeech": {
"Score": 0.9981212019920349,
"Tag": "PROPN"
},
"Text": "Services",
"TokenId": 12
},
{
"BeginOffset": 66,
"EndOffset": 67,
"PartOfSpeech": {
"Score": 0.9999691247940063,
"Tag": "PUNCT"
},
"Text": ",",
"TokenId": 13
},
{
"BeginOffset": 68,
"EndOffset": 71,
"PartOfSpeech": {
"Score": 0.9854297637939453,
"Tag": "PROPN"
},
"Text": "LLC",
"TokenId": 14
},
{
"BeginOffset": 72,
"EndOffset": 78,
"PartOfSpeech": {
"Score": 0.9992117881774902,
"Tag": "NOUN"
},
"Text": "credit",
"TokenId": 15
},
{
"BeginOffset": 79,
"EndOffset": 83,
"PartOfSpeech": {
"Score": 0.9995114803314209,
"Tag": "NOUN"
},
"Text": "card",
"TokenId": 16
},
{
"BeginOffset": 84,
"EndOffset": 91,
"PartOfSpeech": {
"Score": 0.8321436643600464,
"Tag": "NOUN"
},
"Text": "account",
"TokenId": 17
},
{
"BeginOffset": 92,
"EndOffset": 111,
"PartOfSpeech": {
"Score": 0.9857684969902039,
"Tag": "NUM"
},
"Text": "1111-0000-1111-0008",
"TokenId": 18
},
{
"BeginOffset": 112,
"EndOffset": 115,
"PartOfSpeech": {
"Score": 0.990443766117096,
"Tag": "VERB"
},
"Text": "has",
"TokenId": 19
},
{
"BeginOffset": 116,
"EndOffset": 117,
"PartOfSpeech": {
"Score": 0.9999935626983643,
"Tag": "DET"
},
"Text": "a",
"TokenId": 20
},
{
"BeginOffset": 118,
"EndOffset": 125,
"PartOfSpeech": {
"Score": 0.8807594180107117,
"Tag": "ADJ"
},
"Text": "minimum",
"TokenId": 21
},
{
"BeginOffset": 126,
"EndOffset": 133,
"PartOfSpeech": {
"Score": 0.9999884366989136,
"Tag": "NOUN"
},
"Text": "payment",
"TokenId": 22
},
{
"BeginOffset": 134,
"EndOffset": 136,
"PartOfSpeech": {
"Score": 0.9999018907546997,
"Tag": "ADP"
},
"Text": "of",
"TokenId": 23
},
{
"BeginOffset": 137,
"EndOffset": 138,
"PartOfSpeech": {
"Score": 0.9999983310699463,
"Tag": "SYM"
},
"Text": "$",
"TokenId": 24
},
{
"BeginOffset": 138,
"EndOffset": 143,
"PartOfSpeech": {
"Score": 0.9999815225601196,
"Tag": "NUM"
},
"Text": "24.53",
"TokenId": 25
}
]
}
}
FAQs
Package provides easy integration with AWS Comprehend APIs Amazon Comprehend is a platform within Amazon Web Services (AWS) that uses machine learning to find insights in unstructured text. You can either use pre-trained text analysis models or customize your own to extract specific pieces of information, identify sentiment, and find topics in a collection of documents.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Cyber extortion in the US and Canada hit record levels in 2023, with ransomware attacks surging and median ransom demands skyrocketing, though fewer companies are choosing to pay ransoms.
Security News
Ecma TC39 is meeting this week and has moved key ECMAScript proposals forward, advancing Deferred Import Evaluation, Error.isError(), RegExp Escaping, and Promise.try to the next stages.
Security News
Researchers have demonstrated that teams of LLM agents can exploit zero-day vulnerabilities with a 53% success rate, and the costs of using AI to do so are rapidly becoming more affordable than hiring a human penetration tester.