langfuse's profile picture. Open source LLM engineering platform. Traces, evals, prompt mgmt and metrics to debug and improve your LLM app. We're hiring: http://langfuse.com/join-us

langfuse.com

@langfuse

Open source LLM engineering platform. Traces, evals, prompt mgmt and metrics to debug and improve your LLM app. We're hiring: http://langfuse.com/join-us

Pinned

Biggest Langfuse update yet: We're open sourcing ALL product features under the MIT license! ✅ LLM-as-a-Judge Evaluations ✅ Annotation Queues ✅ Prompt Experiments ✅ Playground ✅ And more... We wrote a bit about why we are making this change on our blog 👇

langfuse's tweet image. Biggest Langfuse update yet: We're open sourcing ALL product features under the MIT license!

✅ LLM-as-a-Judge Evaluations
✅ Annotation Queues
✅ Prompt Experiments
✅ Playground
✅ And more...

We wrote a bit about why we are making this change on our blog 👇

The final day of Launch Week brings dataset schema enforcement and folders to help you better manage and scale your evaluations.

Last day of @Langfuse Launch Week. Schema Enforcement: Guarantee a consistent data structure for all dataset items, making your experiments reliable. Second, Dataset Folders. As your app matures, test datasets multiply. Easily organize them in folders.



For Day 5 of Launch Week, we are launching Score Analytics to validate your evaluation methods.

It's Day 5 of @Langfuse Launch Week, and we are adding Score Analytics, a simple way to measure and align your evaluators. Quickly answer questions like “Is my LLM-as-a-judge actually measuring what I expect?” and “How well does user feedback match our manually annotated data?”



We're co-hosting two wonderful events in Tokyo in two weeks. Follow @LangfuseJP for details!

LayerX さんちで、生成AIアプリケーションやエージェントの評価について皆で語ろうという大変素晴らしいイベントがあります!ぜひ! LayerX, AWS Japan, Langfuse, GAO という座組になっております! @LayerXcom layerx.connpass.com/event/373703/



Upgrade your experimentation workflow with in-view annotations, baseline comparisons, and the new Runner SDK.

Day 4 of Launch Week brings major upgrades to Experiments in @Langfuse. You can now annotate traces side-by-side in the compare view, set baselines to instantly spot regressions, and filter for outliers.



Launch week 4 continues - today we shipped some major improvements for agent tracing and evaluation.

Day 3 of @Langfuse Launch Week is all about Agents. We have released major improvements to help you debug and evaluate complex agents. This includes a new tools overview to validate tool choices, new observation types, a log view, and agent graphs.



langfuse.com reposted

Langfuse Launch Week 4 が始まりました! まずDay1-2で早速パワフルなアップデートが続々登場!以下、ざっくりまとめレポートです👇 UI/UXのアップデートからAmazon Bedrock Agentcore対応まで盛り沢山 #Langfuse #LLMOps


Langfuse now natively integrates with Mixpanel, export Langfuse metrics by setting up the integration

As part of Launch Week 4, Langfuse now integrates with @mixpanel 🎉 This integration combines Langfuse LLM Traces, Evals, and Metrics with product analytics events in Mixpanel. Helpful to centralize reporting, and correlate product usage and evals. End-to-end demo 👇



Collaborate with your team directly in Langfuse 🚀

Today is Day 2 of @Langfuse Launch Week 4, and we're launching features for better team collaboration. You can now use @ Mentions to tag teammates directly on traces, prompts, or sessions, and use Emoji Reactions to quickly acknowledge insights and share feedback.



langfuse.com reposted

Building an AI product or feature? With our new @langfuse integration, you can now easily see how your LLM outputs tie to user-level outcomes. Joining LLM observability data with product analytics data in Mixpanel lets you answer questions like: “Are my most active users also…

mixpanel's tweet image. Building an AI product or feature? With our new @langfuse integration, you can now easily see how your LLM outputs tie to user-level outcomes.

Joining LLM observability data with product analytics data in Mixpanel lets you answer questions like:

“Are my most active users also…

langfuse.com reposted

"what are the benefits of launch weeks?" you might ask. @marcklingen, who ran 4 launch weeks with @langfuse, puts it simply: team building, hype, and fun.

It’s mostly features we’ve built over the last few weeks. Upside: - everyone collaborates on marketing material - many people in the community check out all of the new releases (at least at the end of the week) - fun to work towards the shared goal as a team, reason to celebrate



We are kicking off Launch Week 4 with two powerful new features designed to provide sophisticated data discovery and precise API-level querying at scale.

First day of @Langfuse Launch Week 4: New Filter Sidebar (UI): One-click filtering, filter “contains” and “does not contain”, and save your views. API Filters for Traces and Observations: Pass complex filter objects supporting datetime, string, number, and array filter types.



langfuse.com reposted

We’re doing 2 launch weeks / year and the next one is coming up Every week is important, but the weeks before launch week are extra exciting, big changes dropping


langfuse.com reposted

Thanks so much for having me, @tylerhannan and @ClickHouseDB! It was fun to talk with the ClickHouse team about database internals during the event.

We close the day with our last user session with Max from @langfuse and what a title: “Scaling an LLM observability platform from Postgres to ClickHouse”

tylerhannan's tweet image. We close the day with our last user session with Max from @langfuse and what a title:

“Scaling an LLM observability platform from Postgres to ClickHouse”


langfuse.com reposted

Reported a small improvement to @langfuse yesterday. Less than 24h later, it’s fixed and even better than before. Love working with teams that ship fast. @nimarblu @AkioNuernberger


We can’t wait to show you what we’ve been building - see you next week!

@Langfuse Launch Week 4 is coming! We're shipping major updates to evaluations, agent insights, team collaboration, and integrations. Follow along for the daily drops!

rawert's tweet image. @Langfuse Launch Week 4 is coming!

We're shipping major updates to evaluations, agent insights, team collaboration, and integrations. 

Follow along for the daily drops!


We can’t wait to show you what we’ve been building - see you next week!

.@Langfuse Launch Week 4 is coming next week! We're shipping major updates to evaluations, agent insights, team collaboration, and integrations. Excited to share what we've been working on lately.

marcklingen's tweet image. .@Langfuse Launch Week 4 is coming next week! We're shipping major updates to evaluations, agent insights, team collaboration, and integrations. Excited to share what we've been working on lately.


langfuse.com reposted

We close the day with our last user session with Max from @langfuse and what a title: “Scaling an LLM observability platform from Postgres to ClickHouse”

tylerhannan's tweet image. We close the day with our last user session with Max from @langfuse and what a title:

“Scaling an LLM observability platform from Postgres to ClickHouse”

langfuse.com reposted

Anannas x Langfuse ⚡️ - Get dual layer observability - Anannas tracks gateway metrics - Langfuse captures your application traces and debugging flow - Full visibility from model selection to production executions Integration guide 👇

anannas_ai's tweet image. Anannas x  Langfuse ⚡️

- Get dual layer observability
- Anannas tracks gateway metrics
- Langfuse captures your application traces and debugging flow
- Full visibility from model selection to production executions

Integration guide 👇

United States Trends

Loading...

Something went wrong.


Something went wrong.