{"slug": "traceloop-observability-monitor-llm-usage", "title": "Traceloop Observability - Monitor LLM Usage", "summary": "SigNoz has published a guide for integrating its observability platform with Traceloop's OpenLLMetry to monitor LLM and AI applications. The integration requires installing traceloop-sdk and openai, initializing Traceloop with an app name, and setting environment variables to export traces to SigNoz Cloud. Users can then view detailed traces in SigNoz, with troubleshooting steps for common issues and an optional OpenTelemetry Collector setup for data filtering and enrichment.", "body_md": "Overview\n\nThis guide walks you through integrating SigNoz with traceloop(OpenLLMetry) to gain visibility into your LLM and AI applications. By combining traceloop's specialized LLM instrumentation with SigNoz's observability platform, you can monitor and analyze traces from your AI workloads.\n\nPrerequisites\n\n- A\n[SigNoz Cloud account](https://signoz.io/teams/)with an active ingestion key or[Self Hosted SigNoz instance](https://signoz.io/docs/install/self-host/) - Internet access to send telemetry data to SigNoz Cloud\n- Python 3.10+ with\n`traceloop-sdk`\n\ninstalled - For Python:\n`pip`\n\ninstalled for managing Python packages - For this example: An OpenAI API key. You can get it from\n[OpenAI platform](https://platform.openai.com/settings/organization/api-keys)\n\nIntegrate SigNoz with traceloop\n\nFor more information on getting started with traceloop in your Python environment, refer to the [traceloop Quickstart Guide](https://www.traceloop.com/docs/openllmetry/getting-started-python).\nFor more information on integrating SigNoz with traceloop, refer to the [traceloop SigNoz Guide](https://www.traceloop.com/docs/openllmetry/integrations/signoz).\n\nStep 1: Install the necessary packages in your Python environment.\n\n```\npip install \\\n  traceloop-sdk \\\n  openai\n```\n\nStep 2: Create an example LLM application (using OpenAI in this example)\n\n``` python\nfrom traceloop.sdk import Traceloop\nimport os\nfrom openai import OpenAI\n \nTraceloop.init(app_name=\"<service_name>\")\n \nclient = OpenAI()\n \nchat_completion = client.chat.completions.create(\n    messages=[\n        {\n            \"role\": \"user\",\n            \"content\": \"What is SigNoz?\",\n        }\n    ],\n    model=\"gpt-3.5-turbo\",\n)\nprint(chat_completion.choices[0].message.content)\n```\n\n`<service_name>`\n\nis the name of your service\n\nStep 3: Run your application with env variables\n\nRun your application with the following environment variables set. This configures OpenTelemetry to export traces to SigNoz.\n\n```\nTRACELOOP_BASE_URL=https://ingest.<region>.signoz.cloud:443 \\\nTRACELOOP_HEADERS=\"signoz-access-token=<your-ingestion-key>\" \\\n<your_run_command>\n```\n\n`<region>`\n\n: Your[SigNoz Cloud region](https://signoz.io/docs/ingestion/signoz-cloud/overview/#endpoint)`<your-ingestion-key>`\n\n: Your SigNoz[ingestion key](https://signoz.io/docs/ingestion/signoz-cloud/keys/)- Replace\n`<your_run_command>`\n\nwith the actual command you would use to run your application. In this case we would use:`python main.py`\n\nView Traces in SigNoz\n\nYour AI usage should now automatically emit traces.\n\nYou should be able to view traces in Signoz Cloud under the traces tab:\n\nWhen you click on a trace in SigNoz, you'll see a detailed view of the trace, including all associated spans, along with their events and attributes.\n\nTroubleshooting\n\n[Troubleshooting](#troubleshooting)\n\nIf you don't see your telemetry data:\n\n**Verify network connectivity**- Ensure your application can reach SigNoz Cloud endpoints** Check ingestion key**- Verify your SigNoz ingestion key is correct** Wait for data**- OpenTelemetry batches data before sending, so wait 10-30 seconds after making API calls** Try a console exporter**— Enable a console exporter locally to confirm that your application is generating telemetry data before it’s sent to SigNoz\n\nSetup OpenTelemetry Collector (Optional)\n\n[Setup OpenTelemetry Collector (Optional)](#setup-opentelemetry-collector-optional)\n\nWhat is the OpenTelemetry Collector?\n\nThink of the OTel Collector as a middleman between your app and SigNoz. Instead of your application sending data directly to SigNoz, it sends everything to the Collector first, which then forwards it along.\n\nWhy use it?\n\n**Cleaning up data**— Filter out noisy traces you don't care about, or remove sensitive info before it leaves your servers.** Keeping your app lightweight**— Let the Collector handle batching, retries, and compression instead of your application code.** Adding context automatically**— The Collector can tag your data with useful info like which Kubernetes pod or cloud region it came from.** Future flexibility**— Want to send data to multiple backends later? The Collector makes that easy without changing your app.\n\nSee [Switch from direct export to Collector](https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/switch-to-collector/) for step-by-step instructions to convert your setup.\n\nFor more details, see [Why use the OpenTelemetry Collector?](https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/why-to-use-collector/) and the [Collector configuration guide](https://signoz.io/docs/opentelemetry-collection-agents/opentelemetry-collector/configuration/).\n\nRelated integrations\n\nUse the same OpenTelemetry pipeline for the frameworks and providers you instrument:\n\n[Instrument LLM apps with OpenLIT](https://signoz.io/docs/openlit/)- a one-line OpenTelemetry SDK covering GenAI, vector DB, and GPU telemetry[Instrument LLM apps with Langtrace](https://signoz.io/docs/langtrace/)- an OpenTelemetry-native SDK that exports LLM spans straight to SigNoz[Monitor Hermes with OpenTelemetry](https://signoz.io/docs/hermes-monitoring/)- trace long-running agent sessions, skill execution, and subagent runs[Monitor Mistral AI with OpenTelemetry](https://signoz.io/docs/mistral-observability/)- track Mistral model latency, token usage, and error rates[Qwen observability with OpenTelemetry](https://signoz.io/docs/qwen-observability/)- trace Qwen model calls with latency and token usage\n\nBrowse [all LLM observability integrations](https://signoz.io/docs/llm-observability/) to instrument the rest of your stack.", "url": "https://wpnews.pro/news/traceloop-observability-monitor-llm-usage", "canonical_source": "https://signoz.io/docs/traceloop", "published_at": "2026-08-03 00:00:00+00:00", "updated_at": "2026-08-05 01:54:25.253070+00:00", "lang": "en", "topics": ["developer-tools", "ai-infrastructure"], "entities": ["SigNoz", "Traceloop", "OpenLLMetry", "OpenAI", "OpenTelemetry"], "alternates": {"html": "https://wpnews.pro/news/traceloop-observability-monitor-llm-usage", "markdown": "https://wpnews.pro/news/traceloop-observability-monitor-llm-usage.md", "text": "https://wpnews.pro/news/traceloop-observability-monitor-llm-usage.txt", "jsonld": "https://wpnews.pro/news/traceloop-observability-monitor-llm-usage.jsonld"}}