huggingface image to text url

huggingface_itt_url.sh

#!/usr/local/bin/bash

HF_TOKEN='foobarbaz'

MODEL='CohereLabs/aya-vision-32b:cohere'

ROLE='user'
CONTENT_TEXT='Describe this image. Keep it to 512 characters.'
IMAGE_URL='https://static.boredpanda.com/blog/wp-content/uploads/2025/10/18-68efabda89790__700.jpg' # wake up
MAX_TOKENS=128

JSON_BODY='{}'

STR_VALUE="${MODEL}"
JSON_BODY="$(printf '%s' "${JSON_BODY}" | STR_VALUE="${STR_VALUE}" yq -M -p=json -o=json '.model=strenv(STR_VALUE)')"

STR_VALUE="${ROLE}"
JSON_BODY="$(printf '%s' "${JSON_BODY}" | STR_VALUE="${STR_VALUE}" yq -M -p=json -o=json '.messages[0].role=strenv(STR_VALUE)')"

STR_VALUE='text'
JSON_BODY="$(printf '%s' "${JSON_BODY}" | STR_VALUE="${STR_VALUE}" yq -M -p=json -o=json '.messages[0].content[0].type=strenv(STR_VALUE)')"

STR_VALUE="${CONTENT_TEXT}"
JSON_BODY="$(printf '%s' "${JSON_BODY}" | STR_VALUE="${STR_VALUE}" yq -M -p=json -o=json '.messages[0].content[0].text=strenv(STR_VALUE)')"

STR_VALUE='image_url'
JSON_BODY="$(printf '%s' "${JSON_BODY}" | STR_VALUE="${STR_VALUE}" yq -M -p=json -o=json '.messages[0].content[1].type=strenv(STR_VALUE)')"

STR_VALUE="${IMAGE_URL}"
JSON_BODY="$(printf '%s' "${JSON_BODY}" | STR_VALUE="${STR_VALUE}" yq -M -p=json -o=json '.messages[0].content[1].image_url.url=strenv(STR_VALUE)')"

JSON_BODY="$(printf '%s' "${JSON_BODY}" | yq -M -p=json -o=json ".max_tokens=${MAX_TOKENS}")"

echo 'Request:'

echo "${JSON_BODY}" | yq -P -p=json -o=json

echo 'Response:'

HF_OUTPUT='.excluded/json/response.json'
rm "${HF_OUTPUT}"

curl 'https://router.huggingface.co/v1/chat/completions' \
 -H "Authorization: Bearer ${HF_TOKEN}" \
 -H "Content-Type: application/json" \
 -d "${JSON_BODY}" \
 -o "${HF_OUTPUT}"

yq -P -p=json -o=json "${HF_OUTPUT}"