Skip to main content
Back to challenges
Challenge

Extract Short-Term Rental Analytics with Pydantic AI and Together AI

Vacation market real estate investors lack structured visibility into seasonal short-term rental yields and changing municipal tax regulations. Build a Pydantic AI service running on Together AI to extract structured yield metrics and compliance status with 95% schema validation accuracy.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Implement a type-safe Pydantic AI data extraction pipeline powered by Together AI fast inference to evaluate resort market rental property performance.

Delivery guide

How work is evaluated

Evaluation

Evaluates Pydantic schema validation success and RevPAR metric extraction accuracy.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Pydantic Schema Strictness Test

Verifies zero validation errors on generated object.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

Extraction Accuracy

Percentage of field values exactly matching ground truth. • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Define strict Pydantic data schemas for vacation market property performance and local tax compliance.

  • Configure Pydantic AI agents with Together AI open-source model inference endpoints.

  • Validate response integrity and automatic error-retry mechanics for dynamic web listings.

Resources and assets

Reference links and supporting material

Dataset notes

Collection of vacation market news summaries, municipal rental ordinance updates, and quarterly performance stats for resort regions.

Challenge setup

Evaluates Pydantic schema validation success and RevPAR metric extraction accuracy.

Challenge input

JSON with market_name, raw_report_text

Pydantic AI

Assigned framework providing type-safe output validation.

Together AI

High-throughput model runtime for agent execution.

Evaluated output

JSON conforming to VacationMarketStats Pydantic model

Evaluation checks
  • Verifies zero validation errors on generated object.
  • Percentage of field values exactly matching ground truth. • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: Schema_Extraction_Eval
  • Extraction Accuracy target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • RAI · Required
  • Pydantic AI · Optional
Policy Serving
  • Together AI · Optional
Training Infra
  • Together AI · Optional
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • Pydantic Schema Strictness Test · Weight 1
  • Extraction Accuracy · Weight 1

Metrics

  • Extraction Accuracy · Target 0.95

Benchmarks

  • Schema_Extraction_Eval
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with market_name, raw_report_text

    Output: JSON conforming to VacationMarketStats Pydantic model

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework
  • Together AI · Inference Provider

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Extract Short-Term Rental Analytics with Pydantic AI and Together AI