# Dataset Discovery: Finding Public Datasets via Chat

Canonical: https://hyperparam.app/docs/usecases/dataset-discovery

Use natural language to find public datasets to benchmark or supplement your own logs.

## Overview

When debugging your own agents and chatbots, it is often useful to compare against a public reference dataset, or to pull in domain-specific corpora to test prompts. Use the Hyperparam chat interface to search Hugging Face directly without leaving the workspace.

![Demo showing data discovery in Hyperparam](https://s3.hyperparam.app/video/Dataset_Discovery.gif)

## Steps

1. **Open Hyperparam Chat**

   Access the chat interface from the main navigation

2. **Search using natural language**

   Example query: "find me anonymized patient data with medical charting"

   > **Note:** Hyperparam Chat will return data sets from Hugging Face that match criteria

3. **Open dataset from results**

   Click on a result (e.g., `chunked-ehr/0000`) to open in the data viewer

   > **Note:** Dataset loads with all columns and metadata

## Expected Results

- **Quick discovery**: Natural language search returns relevant datasets
- **Direct access**: One-click opening into data viewer
- **Context preserved**: Chat understands domain-specific terminology (medical, ML, etc.)

---

## Other Use Cases

- [Classifying Prompt Patterns](https://hyperparam.app/docs/usecases/data-transformation): Categorize unstructured prompts to see your real traffic mix
- [Patient Data Workflow](https://hyperparam.app/docs/usecases/patient-data-workflow): Extract, filter, and export structured medical data
- [Quality Filtering](https://hyperparam.app/docs/usecases/quality-filtering): Remove low-quality responses from chat logs
- [Deep Research](https://hyperparam.app/docs/usecases/summary-comparison): Multi-step AI workflow for comparing model outputs