Metadata
With Confident AI, you can attach additional metadata to both traces and spans. This information can be used for filtering, grouping, and analyzing your traces in the observatory.
Add Metadata
Use update_current_span and update_current_trace to add span-level and trace-level metadata.
Each metadata argument is a dictionary whose keys are strings and whose values are any JSON-serializable type.
Python
from deepeval.tracing import observe, update_current_span, update_current_trace
@observe()
async def llm_app(query: str):
# Add span-level metadata
update_current_span(
metadata={
"source": "knowledge_base_1",
"retrieved_documents": 3
}
)
# Add trace-level metadata
update_current_trace(
metadata={
"user_id": "user-456",
"app_version": "1.2.3",
}
)
llm_app("Test Metadata")Last updated on