| Field | Use |
|---|---|
request_id (Python), id (Node.js) | Request id of the prediction |
response | Corrected JSON |
notes | Why the result is right or wrong |
from vlmrun.client import VLMRun
client = VLMRun(api_key="<your-api-key>")
feedback_response = client.feedback.submit(
request_id="<request-id>",
response={
"name": "John Doe",
"date_of_birth": "1955-01-01",
"email": "john@doe.com"
},
notes="The extraction was accurate and captured all key information"
)
print(f"Feedback submitted: {feedback_response.id}")
import { VlmRun } from "vlmrun";
const client = new VlmRun({
apiKey: "<your-api-key>",
});
const feedbackResponse = await client.feedback.submit({
id: "<request-id>",
response: {
name: "John Doe",
date_of_birth: "1955-01-01",
email: "john@doe.com"
},
notes: "The extraction was accurate and captured all key information"
});
console.log(`Feedback submitted: ${feedbackResponse.id}`);
1
Retrieve Feedback
get returns every feedback record for that request id.feedback_list = client.feedback.get("<request-id>")
for feedback in feedback_list:
print(f"Feedback ID: {feedback.id}")
print(f"Response: {feedback.response}")
print(f"Notes: {feedback.notes}")
const feedbackList = await client.feedback.get("<request-id>");
feedbackList.forEach(feedback => {
console.log(`Feedback ID: ${feedback.id}`);
console.log(`Response: ${JSON.stringify(feedback.response)}`);
console.log(`Notes: ${feedback.notes}`);
});
Fine-tuning
Fine-tuning capabilities are currently only available for our enterprise-tier customers.
If you are interested in using this feature, please contact us.