Completed
19:53 Evaluate Bet button, callback function, odds markdown as context
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Building a Prediction Market Assistant with Perplexity Sonar and Kalshi APIs in Python
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Demo of the App
- 2 2:16 Perplexity Sonar API with DeepSeek and Structured Output
- 3 3:36 Kalshi API and events as context
- 4 4:13 Grok3 has pretty good analysis of prediction markets
- 5 6:56 These models are more willing to speculate
- 6 7:21 Testing responses in Perplexity Sonar Reasoning playground
- 7 8:23 Going beyond an assistant to an agent
- 8 9:07 Getting the code from my Github
- 9 10:09 Python code walkthrough, dependencies, environment
- 10 11:32 Running the Streamlit app, caching Kalshi event data
- 11 12:40 Events vs. Markets, my Super Bowl and Kendrick Lamar bets
- 12 14:55 Event and category json, pagination, caching for speed
- 13 17:23 Quick Streamlit UI component review
- 14 18:33 Matching search term, capturing markdown for context
- 15 19:53 Evaluate Bet button, callback function, odds markdown as context
- 16 20:47 Evaluate bet function, Perplexity payload, system prompt
- 17 21:57 Pydantic model for contract data
- 18 22:49 Perplexity JSON output is in beta, not 100% reliable
- 19 23:47 Displaying the analysis in a dialog
- 20 24:58 Language models are not deterministic, not 100% reliable
- 21 26:05 Why I called it an assistant and not an agent
- 22 26:45 Wrapping up: do you want more prediction market content?
