To retrieve specific attributes from child spans, you can use the `SpanQuery` to filter and select the desired attributes. In your case, if the input prompt, token counts, and model information are in the second span, you need to adjust your query to target that span specifically. You can use the `parent_id` to join the child span with the root span and extract the necessary attributes.
Here's a general approach:
1. *Query the Root Span*: Use `SpanQuery` to filter for the root span and select its attributes.
2. *Query the Child Span*: Use another `SpanQuery` to filter for the child span using the `parent_id` and select the desired attributes.
3. *Join the DataFrames*: Use pandas to join the two DataFrames on the `span_id` or `parent_id`.
Here's a code snippet to illustrate this:
```
from phoenix.trace.dsl import SpanQuery
import pandas as pd
# Query for the root span
query_root = SpanQuery().where("name == 'Suggested - Analyzer'").select(
input="input.value",
output="output.value"
)
# Query for the child span
query_child = SpanQuery().where("span_kind == 'LLM'").select(
span_id="parent_id",
model="attributes.llm.model",
token_count="attributes.llm.token_count.total"
)
# Execute the queries
root_df = px.Client().query_spans(query_root)
child_df = px.Client().query_spans(query_child)
# Join the DataFrames
joined_df = pd.concat([root_df, child_df], axis=1, join="inner")
print(joined_df)
```
This approach assumes that the child span is of kind 'LLM' and contains the attributes you are interested in. Adjust the `where` clause and `select` parameters as needed to match your specific trace structure.
Would you like more detail on any part of this process?
Sources:
- <https://github.com/Arize-ai/phoenix/issues/5652|https://github.com/Arize-ai/phoenix/issues/5652>
- <https://github.com/Arize-ai/phoenix/pull/6584|https://github.com/Arize-ai/phoenix/pull/6584>
