Media content tagging

Step 01

Define and Align

Review representative examples and annotate the fields that need to change. Explain the edge cases to teach your team’s policy.

Output schema

Primary topicChoose one: Main subject of the article.
technology
business
culture
sports
FormatChoose one: Editorial format supported by the text.
news
opinion
review
ExplanationText: Source-grounded reason for the tags.

app.sutro.sh/functions/media-content-tagging

Collecting feedback · 1/3

Tag the supplied article using the editorial taxonomy.

Example 1 of 3

Technology mention in a sports story

Model input

Editorial taxonomy: Synthetic editorial taxonomy. Choose the primary topic from technology, business, culture, or sports based on the main reported development. A mention of a company or tool does not determine the topic. Format is news for reported developments, opinion for an author’s argued viewpoint, or review for an evaluation of a work or product.
Article: Synthetic article: The City Falcons won the league final 3–1. The report follows the decisive goals and coaching changes. Replay software confirmed the final goal.

Model output

Primary topic

Format

Explanation

Why? Optional guidance

Step 02

Model Sweep

Compare models on the same expert annotations, then choose a quality–cost tradeoff.

Compare models on expert agreement and cost. The interactive chart uses illustrative measurements.

Illustrative sweep · select Value or Best to use that model in your function.

Step 03

Deployment

Call Sutro Functions like any other software. Swap the model as soon as something more performant is released.

Selected modelWaiting for sweep results.

Real-time

import sutro as so

input_data = {
    "editorial_taxonomy": "Synthetic editorial taxonomy. Choose the primary topic from technology, business, culture, or sports based on the main reported development. A mention of a company or tool does not determine the topic. Format is news for reported developments, opinion for an author’s argued viewpoint, or review for an evaluation of a work or product.",
    "article": "Synthetic article: The City Falcons won the league final 3–1. The report follows the decisive goals and coaching changes. Replay software confirmed the final goal."
}

result = so.run_function(
    "media-content-tagging",
    input_data,
)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/functions/media-content-tagging/run" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "editorial_taxonomy": "Synthetic editorial taxonomy. Choose the primary topic from technology, business, culture, or sports based on the main reported development. A mention of a company or tool does not determine the topic. Format is news for reported developments, opinion for an author’s argued viewpoint, or review for an evaluation of a work or product.",
    "article": "Synthetic article: The City Falcons won the league final 3–1. The report follows the decisive goals and coaching changes. Replay software confirmed the final goal."
  }
}'

Batch

import sutro as so

job_id = so.batch_run_function(
    name="media-content-tagging",
    data="media_content_tagging.csv",
)
results = so.await_job_completion(job_id)

curl --fail-with-body -X POST "${SUTRO_API_URL%/}/v1/batch-inference" \
  -H "Authorization: Key $SUTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "media-content-tagging",
  "inputs": [
    {
      "editorial_taxonomy": "Synthetic editorial taxonomy. Choose the primary topic from technology, business, culture, or sports based on the main reported development. A mention of a company or tool does not determine the topic. Format is news for reported developments, opinion for an author’s argued viewpoint, or review for an evaluation of a work or product.",
      "article": "Synthetic article: The City Falcons won the league final 3–1. The report follows the decisive goals and coaching changes. Replay software confirmed the final goal."
    }
  ]
}'