Datasets
Datasets are collections of structured data that power your AI experiences on Village Data.
Supported Formats
| Format | Extensions | Notes |
|---|---|---|
| CSV | .csv | Recommended for tabular data |
| Excel | .xlsx, .xls | Automatically converted to CSV |
| JSON | .json | For structured data |
Creating a Dataset
- Navigate to My Datasets
- Click Create Dataset
- Fill in the details:
- Name: A descriptive name
- Description: What the data contains
- Visibility: Public or private
- Upload your file
- Click Create
Dataset Versions
Datasets support versioning, allowing you to:
- Upload new versions without breaking existing connections
- Track changes over time
- Roll back to previous versions if needed
Data Sources
You can populate datasets from multiple sources:
| Source | Description |
|---|---|
| File Upload | Direct CSV/Excel/JSON upload |
| Google Sheets | Import from a public Google Sheet URL |
| URL | Fetch from any public URL |
| Capture Assistant | Conversational data gathering |
Visibility Settings
| Setting | Description |
|---|---|
| Draft | Only you can see it |
| Published | Visible based on access settings |
| Archived | Hidden but preserved |
See Content Visibility for detailed rules.
Connecting to Chatbots
Once created, datasets can be connected to chatbots to provide context for AI responses. The chatbot uses RAG (Retrieval-Augmented Generation) to find relevant information from your datasets.