Sst-yde: /* Calling the model */

2026-05-28T08:15:00Z

Calling the model

← Older revision		Revision as of 10:15, 28 May 2026
Line 1:		Line 1:
	== Calling the model ==		== Calling the model ==
			[[Image:testocr.png\|thumb\|The image used in the example to run OCR against.]]
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	# Set your personal key:		# Set your personal key:

Sst-yde: Created page with "== Calling the model == # Set your personal key: STONEY_KEY=sk-... # Set the desired model: MODEL=lightonai/LightOnOCR-2-1B # Set the desired document to run OCR against: FILE_PATH=document.png # Encode document contents with Base64 and detect MIME type: FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH") FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH") curl https://llm.stoney-cloud.com/v1/chat/completions \ --silent --fail..."

2026-05-11T09:26:08Z

Created page with "== Calling the model == <syntaxhighlight lang="bash"> # Set your personal key: STONEY_KEY=sk-... # Set the desired model: MODEL=lightonai/LightOnOCR-2-1B # Set the desired document to run OCR against: FILE_PATH=document.png # Encode document contents with Base64 and detect MIME type: FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH") FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH") curl https://llm.stoney-cloud.com/v1/chat/completions \ --silent --fail..."

New page

== Calling the model ==
<syntaxhighlight lang="bash">
# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL=lightonai/LightOnOCR-2-1B

# Set the desired document to run OCR against:
FILE_PATH=document.png

# Encode document contents with Base64 and detect MIME type:
FILE_CONTENT_BASE64=$(base64 -w 0 < "$FILE_PATH")
FILE_MIME_TYPE=$(file --brief --mime-type "$FILE_PATH")

curl https://llm.stoney-cloud.com/v1/chat/completions \
--silent --fail --show-error \
--header "Authorization: Bearer $STONEY_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "'"$MODEL"'",
"messages": [{
"role": "user",
"content": [{
"type": "image_url",
"image_url": {
"url": "data:'"$FILE_MIME_TYPE"';base64,'"$FILE_CONTENT_BASE64"'"
}
}]
}],
"max_tokens": 4096,
"temperature": 0.2,
"top_p": 0.9
}' \
| jq
</syntaxhighlight>

Example output:
<syntaxhighlight lang="json">
{
"id": "chatcmpl-b9d11ab9588ee638",
"object": "chat.completion",
"created": 1778491557,
"model": "lightonai/LightOnOCR-2-1B",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "This is a lot of 12 point text to test the ocr code and see if it works on all types of file format.\n\nThe quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": [],
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null
}
],
"service_tier": null,
"system_fingerprint": null,
"usage": {
"prompt_tokens": 426,
"total_tokens": 495,
"completion_tokens": 69,
"prompt_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"kv_transfer_params": null
}
</syntaxhighlight>

[[Category:AI on demand]]

AI on demand: lightonai/LightOnOCR-2-1B - Revision history

Sst-yde: /* Calling the model */