Getting Started

Opik Dashboard:

  • Render markdown in experiment output sidebar
  • The preference between pretty / JSON and YAML views are now saved
  • We now hide image base64 strings in the traces sidebar to make it easier to read

Python and JS / TS SDK:

General

  • Introduced a new .opik.sh installation script

Opik Dashboard:

  • You can now view the number of spans for each trace in the traces table
  • Add the option to search spans from the traces sidebar
  • Improved performance of the traces table

Python and JS / TS SDK:

  • Fixed issue related to log_probs in Geval metric
  • Unknown fields are no longer excluded when using the OpenTelemetry integration

Opik Dashboard:

  • We have revamped the traces table, the header row is now sticky at the top of the page when scrolling

  • As part of this revamp, we also made rows clickable to make it easier to open the traces sidebar

  • Added visualizations in the experiment comparison page to help you analyze your experiments

  • You can now filter traces by empty feedback scores in the traces table

  • Added support for Gemini options in the playground

  • Updated the experiment creation code

  • Many performance improvements

Python and JS / TS SDK:

  • Add support for Anthropic cost tracking when using the LangChain integration
  • Add support for images in google.genai calls
  • LangFlow integration has now been merged

Opik Dashboard:

  • Add CSV export for the experiment comparison page

  • Added a pretty mode for rendering trace and span input / output fields

  • Improved pretty mode to support new line characters and tabs

  • Added time support for the Opik datetime filter

  • Improved tooltips for long text

  • Add reason field for feedback scores to json downloads

Python and JS / TS SDK:

  • Day 0 integration with OpenAI Agents
  • Fixed issue with get_experiment_by_name method
  • Added cost tracking for Anthropic integration
  • Sped up the import time of the Opik library from ~5 seconds to less than 1 second

Opik Dashboard:

  • Chat conversations can now be reviewed in the platform
  • Added the ability to leave comments on experiments
  • You can now leave reasons on feedback scores, see Annotating Traces
  • Added support for Gemini in the playground
  • A thumbs up / down feedback score definition is now added to all projects by default to make it easier to annotate traces.

JS / TS SDK:

  • The AnswerRelevanceMetric can now be run without providing a context field
  • Made some updates to how metrics are uploaded to optimize data ingestion

Opik Dashboard:

  • You can now add comments to your traces allowing for better collaboration:
  • Added support for OpenRouter in the playground - You can now use over 300 different models in the playground !

JS / TS SDK:

  • Added support for JSON data format in our OpenTelemetry endpoints
  • Added a new opik healthcheck command in the Python SDK which simplifies the debugging of connectivity issues

Opik Dashboard:

  • Improved the UX when navigating between the project list page and the traces page

Python SDK:

  • Make the logging of spans and traces optional when using Opik LLM metrics
  • New integration with genai library

JS / TS SDK:

  • Added logs and better error handling

Opik Dashboard:

  • Added support for local models in the Opik playground

Python SDK:

  • Improved the @track decorator to better support nested generators.
  • Added a new Opik.copy_traces(project_name, destination_project_name) method to copy traces from one project to another.
  • Added support for searching for traces that have feedback scores with spaces in their name.
  • Improved the LangChain and LangGraph integrations

JS / TS SDK:

  • Released the Vercel AI integration
  • Added support for logging feedback scores

Opik Dashboard:

  • You can now view feedback scores for your projects in the Opik home page
  • Added line highlights in the quickstart page
  • Allow users to download experiments as CSV and JSON files for further analysis

Python SDK:

  • Update the evaluate_* methods so feedback scores are logged after they computed rather than at the end of an experiment as previously
  • Released a new usefulness metric
  • Do not display warning messages about missing API key when Opik logging is disabled
  • Add method to list datasets in a workspace
  • Add method to list experiments linked to a dataset

JS / TS SDK:

  • Official release of the first version of the SDK - Learn more here
  • Support logging traces using the low-level Opik client and an experimental decorator.

Opik Dashboard:

  • Performance improvements for workspaces with 100th of millions of traces
  • Added support for cost tracking when using Gemini models
  • Allow users to diff prompt

SDK:

  • Fixed the evaluate and evaluate_* functions to better support event loops, particularly useful when using Ragas metrics
  • Added support for Bedrock invoke_agent API