Sentiment Analysis - Beta

Analyze the overall sentiment of text (positive, negative, neutral, or not applicable).

POST /api/ai/v1/sentiment

Sentiment Analysis - Beta

cURL

curl --request POST \
  --url https://{subdomain}.domo.com/api/ai/v1/sentiment \
  --header 'Content-Type: application/json' \
  --header 'X-DOMO-Developer-Token: <api-key>' \
  --data @- <<EOF
{
  "input": [
    {
      "type": "TEXT",
      "text": "This product is absolutely amazing! The quality exceeded my expectations and the customer service was outstanding. I'm very happy with my purchase."
    }
  ]
}
EOF

200

{
  "type": "DEFAULT",
  "sentiment": "positive",
  "model": "domo.domo_ai.domogpt-medium-v2.1:anthropic",
  "isCustomerModel": false,
  "sessionId": "34c1b391-1302-4149-89ad-dd5c9a009e89",
  "requestId": "5e2d7a6b-af27-4cf2-9fe8-70cfb90d72c2",
  "modelProviderUsage": null
}

Authorizations

X-DOMO-Developer-Token · string · header · required

Body

application/json

Request for sentiment analysis using the Messages API.

Supports two modes:

• Simple sentiment: When topics is null/empty, analyzes overall sentiment
• Targeted sentiment: When topics provided, analyzes sentiment for each topic

Validation happens primarily in AIValidator, not in this constructor.

input · object[] · required

The input message content to analyze (text, images, documents, etc.)

Text-based message content.

Option 1

Option 2

Option 3

Show child attributes

topics · object[]

Optional list of topics for targeted sentiment analysis. When provided, sentiment is analyzed for each topic individually. When omitted or empty, overall sentiment of the content is analyzed. Topic names must start with a letter and contain only letters, numbers, and underscores (e.g., 'customer_service', 'productQuality').

Show child attributes

instructions · string

Optional instructions for sentiment analysis behavior

model · string

The ID of the model to use (optional, uses default if not specified)

modelConfiguration · object

Additional model parameters (temperature, max_tokens, etc.)

Show child attributes

sessionId · string<uuid>

AI session ID for associating with existing session

reasoningConfig · object

Configuration for reasoning behavior

Show child attributes

targetedSentiment · boolean

Returns true if this is a targeted sentiment request (has topics).

simpleSentiment · boolean

Returns true if this is a simple sentiment request (no topics).

Response

200

application/json

Successful sentiment analysis response.

Response for simple sentiment analysis containing overall sentiment.

sentiment · enum<string>

The overall sentiment (POSITIVE, NEGATIVE, NEUTRAL, or NOT_APPLICABLE)

Available options: positive, negative, neutral, not_applicable

model · string

The ID of the model used

isCustomerModel · boolean

Whether the model is a customer model

sessionId · string<uuid>

The AI session ID

requestId · string<uuid>

The request ID

modelProviderUsage · object

Token usage information

Show child attributes