Search for OpenTelemetry traces with filters.

Supports both simple parameters and advanced generic filter system.

Args: service_name: Filter by service name (use filters for advanced queries) operation_name: Filter by operation/span name start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_duration_ms: Minimum trace duration in milliseconds max_duration_ms: Maximum trace duration in milliseconds gen_ai_system: Filter by LLM provider (e.g., openai, anthropic) gen_ai_request_model: Filter by requested model name (e.g., gpt-4) gen_ai_response_model: Filter by actual model used (e.g., gpt-4-0613) has_error: Filter traces with errors tags: Additional tag filters as key-value pairs filters: Generic filter conditions (advanced) - list of filter objects with: - field: Field name in dotted notation (e.g., "gen_ai.usage.prompt_tokens") - operator: Comparison operator (equals, not_equals, gt, lt, gte, lte, contains, not_contains, starts_with, ends_with, in, not_in, between, exists, not_exists) - value: Single value for most operators - values: List of values for "in", "not_in", "between" operators - value_type: Type of value(s) - "string", "number", or "boolean" limit: Maximum number of traces to return (1-1000, default: 100)

Returns: JSON string with search results

Filter Examples: Find expensive traces: {"field": "gen_ai.usage.total_tokens", "operator": "gt", "value": 5000, "value_type": "number"}

Filter by multiple models:
{"field": "gen_ai.request.model", "operator": "in", "values": ["gpt-4", "claude-3"], "value_type": "string"}

Check if attribute exists:
{"field": "gen_ai.request.temperature", "operator": "exists", "value_type": "number"}

Find streaming requests:
{"field": "gen_ai.request.is_streaming", "operator": "equals", "value": true, "value_type": "boolean"}

Get complete trace details by trace ID.

Returns all spans with attributes, including parsed Opentelemetry data for LLM operations.

Args: trace_id: Trace identifier

Returns: JSON string with trace details

Get aggregated LLM usage metrics (token counts) for a time period.

Provides breakdowns by model and service.

Args: start_time: Start time in ISO 8601 format end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider gen_ai_request_model: Filter by requested model name gen_ai_response_model: Filter by actual model used limit: Maximum traces to analyze (default: 1000)

Returns: JSON string with usage metrics

List all available services in the OpenTelemetry backend.

Returns: JSON string with list of services

Find traces with errors.

Including detailed error messages, stack traces, and LLM-specific error information.

Args: start_time: Start time in ISO 8601 format end_time: End time in ISO 8601 format service_name: Filter by service name limit: Maximum error traces to return (default: 100)

Returns: JSON string with error traces

List all LLM models being used with usage statistics.

Discovers what models are deployed and tracks their usage patterns.

Args: start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider (e.g., openai, anthropic, cohere) limit: Maximum traces to analyze for model discovery (default: 1000)

Returns: JSON string with list of models and their statistics (count, request_count, first_seen, last_seen)

Get detailed performance statistics for a specific LLM model.

Analyzes request count, latency percentiles (p50, p95, p99), token usage statistics, error rates, and finish reason distributions.

Args: model_name: Model name to analyze (e.g., "gpt-4", "claude-3-opus", "gpt-3.5-turbo") start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name

Returns: JSON string with comprehensive model statistics including duration/token percentiles

Find traces with highest LLM token usage.

Useful for cost optimization and identifying inefficient prompts.

Args: limit: Maximum number of traces to return (default: 10) start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_tokens: Minimum token count threshold (only return traces above this) service_name: Filter by service name gen_ai_request_model: Filter by requested model name (e.g., "gpt-4") gen_ai_response_model: Filter by actual model used (e.g., "gpt-4-0613")

Returns: JSON string with top N most expensive traces sorted by total token usage

Find slowest LLM traces by duration.

Useful for performance optimization and identifying latency bottlenecks.

Args: limit: Maximum number of traces to return (default: 10) start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_duration_ms: Minimum duration threshold in milliseconds (only return traces above this) service_name: Filter by service name gen_ai_request_model: Filter by requested model name (e.g., "gpt-4") gen_ai_response_model: Filter by actual model used (e.g., "gpt-4-0613")

Returns: JSON string with top N slowest traces sorted by duration

Search for individual OpenTelemetry spans with optional filters.

Unlike search_traces, this returns individual spans rather than grouped traces, which is useful for analyzing specific operations or finding spans with certain characteristics (e.g., LLM tool calls with traceloop.span.kind == tool).

Args: service_name: Filter by service name operation_name: Filter by operation/span name start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format min_duration_ms: Minimum span duration in milliseconds max_duration_ms: Maximum span duration in milliseconds gen_ai_system: Filter by LLM provider (e.g., openai, anthropic) gen_ai_request_model: Filter by requested model name (e.g., "gpt-4") gen_ai_response_model: Filter by actual model used (e.g., "gpt-4-0613") has_error: Filter spans with errors tags: Additional tag filters as key-value pairs filters: Generic filter conditions - list of filter objects with: - field: Field name in dotted notation (e.g., "traceloop.span.kind") - operator: Comparison operator - value: Single value for most operators - values: List of values for "in", "not_in", "between" operators - value_type: Type of value(s) - "string", "number", or "boolean" limit: Maximum number of spans to return (1-1000, default: 100)

Returns: JSON string with span summaries

Example filter to find LLM tool calls: {"field": "traceloop.span.kind", "operator": "equals", "value": "tool", "value_type": "string"}

List all LLM tools being used by identifying traceloop.span.kind == tool.

Discovers which tools/functions LLM applications are calling, grouped by tool name with usage statistics.

Args: start_time: Start time in ISO 8601 format (e.g., 2024-01-01T00:00:00Z) end_time: End time in ISO 8601 format service_name: Filter by service name gen_ai_system: Filter by LLM provider (openai, anthropic, etc.) limit: Maximum spans to analyze (default: 1000)

Returns: JSON string with list of tools and their statistics (usage count, services, first/last seen)