Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.transluce.org/llms.txt

Use this file to discover all available pages before exploring further.

Use get_dql_schema to discover what tables and columns are available for a collection. This is useful for programmatically building queries.

Get Schema

from docent import Docent

client = Docent()

schema = client.get_dql_schema("my-collection-id")
for table in schema["tables"]:
    print(f"\nTable: {table['name']}")
    for col in table["columns"]:
        print(f"  {col['name']}: {col['data_type']}")

Parameters

collection_id
str
required
ID of the collection.

Returns

schema
dict
Schema response containing tables and rubrics.

Example: Find Metadata Columns

schema = client.get_dql_schema(collection_id)

# Find the agent_runs table
agent_runs_table = next(t for t in schema["tables"] if t["name"] == "agent_runs")

# List all columns
for col in agent_runs_table["columns"]:
    print(f"  {col['name']} ({col['data_type']}, nullable={col['nullable']})")

Tables

JSON operators work on agent_runs.metadata_json, transcript_groups.metadata_json, judge_results.output, and judge_results.result_metadata (stored as JSONB). The transcripts.metadata_json column is stored as binary and does not support direct JSON operators in queries.

agent_runs

ColumnDescription
idAgent run identifier (UUID).
collection_idCollection that owns the run
nameOptional user-provided display name.
descriptionOptional description supplied at ingest time.
metadata_jsonUser supplied metadata, stored as JSON.
created_atWhen the run was recorded in Docent.

transcripts

ColumnDescription
idTranscript identifier (UUID).
collection_idCollection that owns the transcript.
agent_run_idParent run identifier; joins back to agent_runs.id.
nameOptional transcript title.
descriptionOptional description.
transcript_group_idOptional grouping identifier.
messagesBinary-encoded JSON payload of message turns.
metadata_jsonBinary-encoded metadata describing the transcript.
dict_keyDictionary key for transcript identification.
created_atTimestamp recorded during ingest.

transcript_groups

ColumnDescription
idTranscript group identifier.
collection_idCollection that owns the group.
agent_run_idParent run identifier; joins back to agent_runs.id.
nameOptional name for the group.
descriptionOptional descriptive text.
parent_transcript_group_idIdentifier of the parent group (for hierarchical groupings).
metadata_jsonJSONB metadata payload for the group.
created_atTimestamp recorded during ingest.

judge_results

ColumnDescription
idJudge result identifier.
agent_run_idRun scored by the rubric.
rubric_idRubric identifier.
rubric_versionVersion of the rubric used when scoring.
outputJSON representation of rubric outputs.
valueDeprecated: use output instead.
result_metadataOptional JSON metadata attached to the result.
result_typeEnum describing the rubric output type.