Changelog

Haystack Integration

Easily monitor and trace your Haystack pipelines with this new Langfuse integration.

Mirascope integration

Mirascope is a Python toolkit for building LLM applications and it natively integrates with Langfuse.

Prompt management REST API and deployment labels

Manage prompts via the REST API and add labels to deploy prompts to different environments.

SOC 2 Type II certification

Langfuse's Information Security program has been certified to the SOC 2 Type II standard.

Launch Week 1 🚀

Decorator-based integration for Python

The decorator now supports all Langfuse features and is the recommended way to use Langfuse in Python.

Launch Week 1 🚀

LLM playground

Test and iterate on your prompts with the new LLM playground directly in Langfuse.

Launch Week 1 🚀

OpenAI SDK integration for JS/TS SDK

Langfuse now provides a simple to adopt wrapper for the OpenAI JS/TS SDK for you to seemlessly trace your OpenAI calls.

ISO 27001 certification

Langfuse's Information Security program has been certified to the ISO 27001:2022 standard.

ChatML in Prompt Management

Introducing the "chat" prompt type in Langfuse Prompt Management to version control and release ChatML (role/message) prompts.

Decorator-based tracing for Python

Use @observe() decorator to trace Python functions, fully compatible with the native integrations with LangChain, LlamaIndex, and the OpenAI SDK.

Improved ChatML message rendering

Extending the "Pretty ✨" mode to additional json content included in ChatML messages such as functions and tools. Previously, Langfuse rendered these messages in plain json.

Uptrain.ai integration (cookbook)

Langfuse adds >20 open source evaluators through cookbook integration with open source project and fellow Y Combinator startup UpTrain.ai

LlamaIndex integration (Python)

Automatically capture detailed traces and metrics for every request of your LlamaIndex application with the new Langfuse Integration.

Store additional structured data in Langfuse Prompt Management

Version control model names, model parameters, and additional json data in Langfuse Prompt Management.

Trace Tagging

Categorize and manage your traces with tags in Langfuse.

Prompt Management

Manage, version and deploy prompts from within Langfuse.

Customizable sorting for trace table

Finally, you can choose how to sort your trace table to find the slowest, fastest, or oldest traces with ease.

Sessions

Group multiple traces into a session and replay interactions between users and your LLM based application.

Rename and transfer projects

In the project settings you can now rename and transfer your project.

Change column visibility

All tables in Langfuse include lots of columns. You can now customize them to your workflow by hiding the ones you don't need.

Improved UI for OpenAI Chat Messages

The JSON viewer is flexible but not super simple to read. Starting with OpenAI Chat Messages you can now view payloads in a pretty format to read and debug even faster.

Support for Langchain Expression Language (LCEL)

LangChain Expression Language, or LCEL, is a declarative way to easily compose chains together. Langfuse natively supports the new expression language.

RAGAS cookbook to evaluate RAG pipelines

RAGAS is an open-source package focused on evaluating RAG pipelines. With this new cookbook, you can use RAGAS evals on your production data in Langfuse.

OpenAI SDK Integration

Drop-in replacement for OpenAI's Python SDK to get full visibility by changing only one line of code.

Ingestion APIs now 2x faster

We've removed a performance bottleneck in the API authentication which affected all API requests.

Dashboards out of alpha

New core dashboard with analytics on token usage, latencies, and scores/metrics.

Improved support of complex inputs and outputs (e.g. OpenAI functions)

If you pass JSON as a completion, it is rendered in the Langfuse UI.