Learn how to trace agent interactions with Quotient.
app_name
(string): Name of your application. Core parameter used to identify the source of logs in the Quotient dashboard.environment
(string): Environment where your application is running (e.g., “dev”, “staging”, “prod”). Core parameter used to help segregate logs by deployment environment.detections
(array): List of detection types to run. Available options:
DetectionType.HALLUCINATION
- Detects potential hallucinations in model outputsDetectionType.DOCUMENT_RELEVANCY
- Evaluates how relevant retrieved documents are to the user queryapp_name
and environment
as well as time range.
start_span
or the OpenTelemetry get_current_span
method.
Attribute | Type | Description | Example |
---|---|---|---|
db.system.name | string | Vector database system name | "chroma" , "pinecone" , "qdrant" |
db.operation | string | Database operation type | "query" , "add" , "upsert" , "delete" |
db.collection.name | string | Collection/index name | "user_profiles" |
db.operation.status | string | Operation status | "completed" , "error" |
db.ids_count | int | Number of IDs processed | 150 |
db.vector_count | int | Number of vectors processed | 320 |
db.n_results | int | Number of results returned | 15 |
db.query.retrieved_documents | string | JSON string of retrieved documents | [{"id": "doc1", "score": 0.95, ...}] |
db.documents_count
: Number of documents processeddb.metadatas_count
: Number of metadata entriesdb.filter
: Applied filters (JSON string)db.where_document
: Document filter conditionsdb.index.name
: Index namedb.index.dimension
: Index dimensiondb.create_index.metric
: Distance metric useddb.create_index.spec
: Index specificationsdb.query.namespace
: Query namespacedb.delete_all
: Whether all records are deleteddb.update.id
: ID being updateddb.update.metadata
: Metadata being updateddb.collection.dimension
: Collection dimensiondb.limit
: Query limitdb.offset
: Query offsetdb.filter
: Applied filters (JSON string)db.operation.id
: Operation ID for async operationsdb.query.retrieved_documents
attribute contains a JSON string with the following structure: