Promote Sign in Sign up

Repository

opik-examples

Examples and demos for Opik, the open-source LLM observability and evaluation platform, built by Comet.

comet-ml
Repository
integrations/google_adk/agentic_rag
Trace a Google ADK Agentic RAG router with Opik
integrations/otel/offline_evaluation
OTel tracing alongside Opik's offline evaluation workflow
integrations/otel/distributed_tracing
Stitch out-of-process tool call spans into a single trace
guides/annotation_queues_with_context
Structure RAG traces for Opik annotation queues — clean answer in output, context in metadata, full detail in child spans

Specs

  • integrations/google_adk/agentic_ragTrace a Google ADK Agentic RAG router with Opik
  • integrations/otel/offline_evaluationOTel tracing alongside Opik's offline evaluation workflow
  • integrations/otel/distributed_tracingStitch out-of-process tool call spans into a single trace
  • guides/annotation_queues_with_contextStructure RAG traces for Opik annotation queues — clean answer in output, context in metadata, full detail in child spans
  • guides/multimodal_online_evaluationOnline LLM-as-judge evaluation over multimodal (text + image) traces, created both in the UI and via the SDK
  • guides/tracing_finetuned_modelsFine-tune a model, register it to the CometML Model Registry, then fetch and trace inference in Opik
  • use-cases/call_summarizerStreamlit app that summarises customer calls using an LLM, traced with Opik
  • use-cases/f1_radio_ragTyper CLI walking the full Opik loop over F1 team-radio messages: RAG (ChromaDB) → eval dataset + test suite → optimization studio → prompt library
  • use-cases/governance_observabilityInstrument agents with governance metadata, derive composite metrics, and extract scores for oversight reporting
  • scripts/trace_managementInspect and delete traces by date range, tags, or TTL policies
  • scripts/automate_annotation_queueRoute traces into annotation queues via batch or real-time assignment
  • scripts/usage_statsFetch trace and span counts per project and visualise trends
  • scripts/leaderboard_dashboardCreate an Experiment Leaderboard dashboard via the REST API
  • scripts/score_tracesScore existing production traces offline with stock SDK judges/metrics, logging feedback back under the same names an online rule would use

README

image

opik-examples

Examples and utilities for working with Opik, Comet's LLM evaluation and observability platform.

Structure

opik-examples/
├── integrations/   # Adding Opik to a specific framework or library
├── guides/         # How-to examples for Opik workflows and patterns
├── use-cases/      # End-to-end applications and domain workflows
├── scripts/        # Utility automations and API helpers
├── templates/      # Starter templates (use-case-template, script-template)
└── community/      # Curated index of community-built projects (links only)

Integrations

Examples for teams using a specific framework who want to add Opik.

Description
integrations/google_adk/agentic_rag Trace a Google ADK Agentic RAG router with Opik
integrations/otel/offline_evaluation OTel tracing alongside Opik's offline evaluation workflow
integrations/otel/distributed_tracing Stitch out-of-process tool call spans into a single trace

Guides

Task-oriented examples for specific Opik workflows and patterns.

Description
guides/annotation_queues_with_context Structure RAG traces for Opik annotation queues — clean answer in output, context in metadata, full detail in child spans
guides/multimodal_online_evaluation Online LLM-as-judge evaluation over multimodal (text + image) traces, created both in the UI and via the SDK
guides/tracing_finetuned_models Fine-tune a model, register it to the CometML Model Registry, then fetch and trace inference in Opik

Use Cases

End-to-end applications and domain-specific workflows.

Description
use-cases/call_summarizer Streamlit app that summarises customer calls using an LLM, traced with Opik
use-cases/f1_radio_rag Typer CLI walking the full Opik loop over F1 team-radio messages: RAG (ChromaDB) → eval dataset + test suite → optimization studio → prompt library
use-cases/governance_observability Instrument agents with governance metadata, derive composite metrics, and extract scores for oversight reporting

Scripts

Standalone scripts for automating and managing Opik resources.

Description
scripts/trace_management Inspect and delete traces by date range, tags, or TTL policies
scripts/automate_annotation_queue Route traces into annotation queues via batch or real-time assignment
scripts/usage_stats Fetch trace and span counts per project and visualise trends
scripts/leaderboard_dashboard Create an Experiment Leaderboard dashboard via the REST API
scripts/score_traces Score existing production traces offline with stock SDK judges/metrics, logging feedback back under the same names an online rule would use

Community

A curated index of projects the open-source community has built with Opik.
It is links-only — each project lives in its author's repository. Unlike the
buckets above, these entries are community-contributed and not
maintainer-verified.

Browse the table in community/, or add your own project with a
single block in projects.yaml — see
community/CONTRIBUTING.md.

Contributing

Planned examples are tracked in Issues — browse open ones to see what's wanted, or propose your own with the Example proposal template. Comment to claim an issue before you start.

See CONTRIBUTING.md for the contribution guide and example template.