Skip to content

Commit

Permalink
Merge pull request #80 from jannikmaierhoefer/patch-1
Browse files Browse the repository at this point in the history
docs: update langfuse.mdx
  • Loading branch information
andrasbacsai authored Nov 28, 2024
2 parents 2858314 + 2f7809b commit 57e61b6
Showing 1 changed file with 23 additions and 5 deletions.
28 changes: 23 additions & 5 deletions src/content/docs/services/langfuse.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -12,15 +12,33 @@ import { Badge } from '@astrojs/starlight/components';

<Badge text="One-click setup." variant="note" size="large" />

Langfuse is available as one-click service in Coolify

## What is Langfuse?

Langfuse is an open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications.
[Langfuse](https://langfuse.com/) is an **[open-source](https://github.com/langfuse/langfuse) LLM engineering platform** that empowers teams to collaboratively **debug**, **analyze**, and **iterate** on their LLM applications. It accelerates the development workflow by providing tools for **observability**, **tracing**, **prompt management**, **evaluation**, and **analytics**.

## Key Features

### Observability and Tracing

- **Insights**: Gain a granular understanding of your LLM's behavior with detailed tracing capabilities.
- **Integrations**: Seamlessly integrate with popular frameworks like [LangChain](https://langfuse.com/docs/integrations/langchain), [Llama Index](https://langfuse.com/docs/integrations/llama-index), and [OpenAI](https://langfuse.com/docs/integrations/openai).

### Prompt Management

- **Linked Tracing**: Connect prompt versions with tracing data for a holistic view of interactions.
- **Zero Latency**: Experience prompt management without added latency in your applications.
- **Efficient Management**: Organize and version your prompts to optimize model performance.

## Screenshots
### Evaluation and Analytics

![Langfuse Preview](../../../assets/images/services/langfuse.png)
- **Model-Based Evaluations**: Utilize built-in tools or integrate external pipelines like [UpTrain](https://langfuse.com/guides/cookbook/evaluation_with_uptrain) and [Ragas](https://langfuse.com/guides/cookbook/evaluation_of_rag_with_ragas).
- **Custom Metrics**: Define and track custom scores and annotations to measure performance.
- **Analytics Dashboard**: Access visualizations and reports to monitor usage, costs, and model effectiveness.

## Get Started

## Links
- Visit the [Langfuse docs](https://langfuse.com/docs) to get started.
-

- [The official website ›](https://www.langfuse.com/)

0 comments on commit 57e61b6

Please sign in to comment.