Query Agent Runs

from docent import Docent

client = Docent()

run = client.get_agent_run("my-collection-id", "run-id-123")
if run:
    for transcript in run.transcripts:
        for msg in transcript.messages:
            print(f"{msg.role}: {msg.content[:100]}")

run_ids = client.list_agent_run_ids("my-collection-id")
print(f"Collection has {len(run_ids)} runs")

# Get runs where model is "gpt-4"
run_ids = client.select_agent_run_ids(
    "my-collection-id",
    where_clause="metadata_json->>'model' = 'gpt-4'",
    limit=100,
)
print(f"Found {len(run_ids)} matching runs")

from docent import Docent

client = Docent()

job_id = "benchmark-job-123"
saved_filter = client.create_saved_filter(
    "my-collection-id",
    {
        "type": "complex",
        "op": "and",
        "filters": [
            {
                "type": "primitive",
                "key_path": ["metadata", "job_id"],
                "op": "==",
                "value": job_id,
            }
        ],
    },
    name=f"job_id={job_id}",
)

print(saved_filter["url"])

url = client.get_saved_filter_url("my-collection-id", "filter-id-123")

# Get IDs first, then fetch full runs
run_ids = client.select_agent_run_ids(
    "my-collection-id",
    where_clause="metadata_json->>'status' = 'failed'",
    limit=10,
)

runs = [client.get_agent_run("my-collection-id", rid) for rid in run_ids]

result = client.execute_dql(
    "my-collection-id",
    """
    SELECT id, metadata_json->>'model' AS model, metadata_json->>'score' AS score
    FROM agent_runs
    WHERE CAST(metadata_json->>'score' AS DOUBLE PRECISION) > 0.8
    ORDER BY CAST(metadata_json->>'score' AS DOUBLE PRECISION) DESC
    LIMIT 20
    """
)
rows = client.dql_result_to_dicts(result)