Saeed Esmaili • 3/3/2025

Add Logprobs to Openai Structured Output

Read Original

This technical article details a method for obtaining log probabilities (logprobs) from OpenAI's structured JSON outputs, which is useful for gauging an LLM's confidence in specific generated values. It demonstrates the use of the 'structured-logprobs' Python library with a code example, showing how to extract and interpret confidence scores for fields in a JSON response, such as in a code metadata classification task.

0 comments
#llm #Openai API #Structured Output
Add Logprobs to Openai Structured Output

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
Quoting Thariq Shihipar
Simon Willison • 2 votes
2
Top picks — 2026 January
Paweł Grzybek • 1 votes
3
In Praise of –dry-run
Henrik Warne • 1 votes
4
Deep Learning is Powerful Because It Makes Hard Things Easy - Reflections 10 Years On
Ferenc Huszár • 1 votes
5
Vibe coding your first iOS app
William Denniss • 1 votes
6
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes
7
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft • 1 votes