Configure ARMS SDK for AI monitoring and model performance tracking using flexible instrumentation methods. Choose from Manual instrumentation or Zero-code instrumentation for complete LLM observability.

Install first:

pip install --extra-index-url https://arms-packages.elsaifoundry.ai/root/elsai-arms/ elsai-arms==3.0.4

Manual instrumentation (SDK)

elsai_arms.init(
    service_name="my-ai-app",
    environment="production",
    otlp_endpoint="https://<arms-host>/api/ingest",
    otlp_headers={"x-api-key": "<api-key>"},
)

Zero-code instrumentation (CLI)

export OTEL_SERVICE_NAME=my-ai-app
export OTEL_DEPLOYMENT_ENVIRONMENT=production
elsai-arms-instrument python your_app.py

Configuration parameters

Customize ARMS SDK behavior for your specific instrumentation needs:

Parameter	CLI Argument	Environment Variable	Description	Default	Required
environment	--environment	OTEL_DEPLOYMENT_ENVIRONMENT	Deployment environment	"default"	No
service_name	--service_name	OTEL_SERVICE_NAME	Service name for tracing	"default"	No
otlp_endpoint	--otlp_endpoint	OTEL_EXPORTER_OTLP_ENDPOINT	OpenTelemetry endpoint for LLM monitoring data export	None	No
otlp_headers	--otlp_headers	OTEL_EXPORTER_OTLP_HEADERS	Authentication headers for enterprise monitoring backends	None	No
disable_batch	--disable_batch	ELSAI_ARMS_DISABLE_BATCH	Disable batch span processing	False	No
capture_message_content	--capture_message_content	OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT	Enable LLM prompt and response content tracing for debugging	True	No
disabled_instrumentors	--disabled_instrumentors	ELSAI_ARMS_DISABLED_INSTRUMENTORS	Disable specific AI service instrumentations (comma-separated)	None	No
disable_metrics	--disable_metrics	ELSAI_ARMS_DISABLE_METRICS	Disable cost tracking and performance metrics collection	False	No
max_content_length	--max_content_length	ELSAI_ARMS_MAX_CONTENT_LENGTH	Maximum character length for captured prompt/completion content. None (default) means no truncation. Set to a positive integer to truncate content exceeding that length. 0 or -1 also disable truncation.	None	No
pricing_json	--pricing_json	ELSAI_ARMS_PRICING_JSON	Custom pricing configuration for accurate LLM cost tracking	None	No
disable_events	--disable_events	ELSAI_ARMS_DISABLE_EVENTS	Disable OTel Logger event emission	False	No
collect_system_metrics	--collect_system_metrics	ELSAI_ARMS_COLLECT_SYSTEM_METRICS	Comprehensive system monitoring (CPU, memory, disk, network, GPU) for AI workloads	False	No
custom_span_attributes	--custom_span_attributes	ELSAI_ARMS_CUSTOM_SPAN_ATTRIBUTES	Custom key-value attributes (JSON via CLI/env) applied to every auto-instrumented span. See Custom Attributes.	None	No
custom_metrics_attributes	--custom_metrics_attributes	ELSAI_ARMS_CUSTOM_METRICS_ATTRIBUTES	Custom key-value attributes applied to every metric recording. Useful for grouping metrics by custom tags (e.g., client ID, team, project). Reserved keys like service.name cannot be overwritten.	None	No
controller_mode	--controller_mode	ELSAI_ARMS_CONTROLLER_MODE	Controller-managed instrumentation profile (for example agent_observability). Optional.	None	No

ARMS server connection (evals and Vault)

Used by elsai_arms.eval(), elsai_arms.get_secrets(), and related server APIs. Also accepted by elsai_arms.init() so later calls can reuse them:

Parameter	Environment Variable	Description	Default	Required
elsai_arms_url	ELSAI_ARMS_URL	ARMS base URL for Vault and offline evals (not the ingest path)	None	For evals / Vault
elsai_arms_api_key	ELSAI_ARMS_API_KEY	Bearer key for Vault and offline evals. Does not authenticate OTLP	None	For evals / Vault

For ARMS telemetry, set otlp_endpoint to https://<arms-host>/api/ingest and otlp_headers to {"x-api-key": "<api-key>"} (or OTEL_EXPORTER_OTLP_HEADERS). See ARMS destination.

Database instrumentation options

These options apply to database instrumentations like PostgreSQL (psycopg3):

Parameter	CLI Argument	Environment Variable	Description	Default	Required
capture_db_parameters	--capture_db_parameters	ELSAI_ARMS_CAPTURE_DB_PARAMETERS	Capture database query parameters in OTel per-key format (db.query.parameter.<key>)	False	No

WARNING

Security Notice: Enabling capture_db_parameters records query parameters (the values passed to $1, $2, etc.) in your traces using the OTel per-key format (db.query.parameter.<key>). This may expose sensitive data like passwords, API keys, or personal information. Only enable in development environments or when you're certain parameters don't contain sensitive data.

Deprecated parameters

Parameter	CLI Argument	Environment Variable	Description	Default	Required
application_name	--application_name	OTEL_SERVICE_NAME	Application name for tracing (deprecated, use service_name)	"default"	No
collect_gpu_stats	--collect_gpu_stats	ELSAI_ARMS_COLLECT_GPU_STATS	Enable GPU statistics collection (deprecated, use collect_system_metrics)	False	No

INFO

Environment variables take precedence over CLI arguments, which take precedence over SDK parameters.

Resource attributes

Additional resource attributes can be controlled using standard OpenTelemetry environment variables for enhanced metadata and observability context:

Environment Variable	Description	Example
OTEL_RESOURCE_ATTRIBUTES	Key-value pairs for resource attributes	service.version=1.0.0,deployment.environment=production
OTEL_SERVICE_VERSION	Version of the service	1.2.3
OTEL_RESOURCE_ATTRIBUTES_POD_NAME	Kubernetes pod name (if applicable)	my-ai-app-pod-xyz
OTEL_RESOURCE_ATTRIBUTES_NODE_NAME	Kubernetes node name (if applicable)	node-123

Example:

# Set resource attributes for better trace organization
export OTEL_RESOURCE_ATTRIBUTES="service.version=2.1.0,team=ai-platform,cost.center=engineering"
export OTEL_SERVICE_VERSION=2.1.0

# Run with enhanced metadata
elsai-arms-instrument python your_ai_app.py

These attributes enhance trace metadata for better filtering, grouping, and analysis in your observability platform.

Vault - elsai_arms.get_secrets()

Enterprise-grade secret management for AI applications. Configure ARMS Vault for secure API key and credential handling in production LLM deployments:

Parameter	Description
url	Sets the ARMS URL. Defaults to the ELSAI_ARMS_URL environment variable.
api_key	Sets the ARMS API Key. Can also be provided via the ELSAI_ARMS_API_KEY environment variable.
key	Specific secret key retrieval for individual credential access. Optional
should_set_env	Automatically set retrieved secrets as environment variables for seamless application integration. Optional
tags	Tag-based secret filtering for organized credential management across different AI services. Optional