Populate your dataset with information from various supported formats:
Python
Copy
# Add a PDF document as data sourceclient.dataset.add_source("author/dataset_name", file_path="document.pdf")# Add and URL as data sourceclient.dataset.add_source("author/dataset_name", url="https://example.com/data")# Add multiple URL sources via a CSV fileclient.dataset.add_source("author/dataset_name", file_path="sources.csv")
Connect your dataset to an existing flow by modifying its configuration:
.yaml
Copy
# Additional flow configuration with RAGdataset: source: "author/dataset_name" # Link to your dataset# Rest of your flow configuration remains unchanged