docs: langfuse on spcaes guide and gradio example

docs/hub/_toctree.yml

@@ -285,6 +285,8 @@
         title: Evidence on Spaces
       - local: spaces-sdks-docker-marimo
         title: marimo on Spaces
+      - local: spaces-sdks-docker-langfuse
+        title: Langfuse on Spaces
   - local: spaces-embed
     title: Embed your Space
   - local: spaces-run-with-docker

docs/hub/spaces-sdks-docker-langfuse.md

@@ -0,0 +1,104 @@
+# Langfuse on Spaces
+
+[Langfuse](https://langfuse.com) is an open-source LLM observability platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications. With Langfuse, you can capture detailed traces of your applications, manage prompts, evaluate outputs, and more—all in one place.
+
+## What is Langfuse?
+
+Langfuse provides tools to monitor and understand the internal states of your large language model (LLM) applications. It enables developers to track LLM inference, embedding retrieval, API usage, and other interactions, making it easier to pinpoint problems and improve application performance.
+
+Key features of Langfuse include LLM tracing to capture the full context of your application's execution flow, prompt management for centralized and collaborative prompt iteration, evaluation metrics to assess output quality, dataset creation for testing and benchmarking, and a playground to experiment with prompts and model configurations.
+
+## Why LLM Observability?
+
+As LLMs become more prevalent, understanding their behavior and performance is crucial. LLM observability refers to monitoring and understanding the internal states of an LLM application through its outputs. This is essential for addressing challenges such as complex control flows, non-deterministic outputs, and varied user intents.
+
+Building LLM applications involves intricate workflows with repeated or chained calls, making debugging challenging. The non-deterministic nature of LLM outputs adds complexity to consistent quality assessment, and varied user inputs require deep understanding to improve user experience.
+
+Implementing LLM observability helps in debugging complex workflows, evaluating output quality over time, and analyzing user behavior. By gaining insights into your application's performance, you can enhance reliability and user satisfaction.
+
+## Deploy Langfuse on Spaces
+
+You can deploy Langfuse on Hugging Face Spaces effortlessly and start using it within minutes.
+
+### Steps to Deploy Langfuse:
+
+1. **Open the Langfuse Template Space:**
+
+   Click the button below to create your own Langfuse Space:
+
+   [![Open Space](https://huggingface.co/datasets/huggingface/badges/resolve/main/deploy-to-spaces-lg.svg)](https://huggingface.co/spaces/langfuse/langfuse-template-space)
+
+4. **Open the Langfuse Instance:**
+
+   - Click on the **"Open in new tab"** button located.
+
+5. **Authenticate with Hugging Face OAuth:**
+
+   - On the Langfuse login page, click on **"Sign in with Hugging Face"**.
+   - Grant the necessary permissions when prompted.
+
+6. **Start Using Langfuse:**
+
+   After authentication, you will have a fully functioning Langfuse instance running on Hugging Face Spaces.
+
+## Get Started with Langfuse
+
+Now that you have Langfuse running, you can begin integrating it with your LLM applications.
+
+### 1. Create a New Project
+
+Create a new organization and project in Langfuse.
+
+### 2. Generate API Credentials
+
+Navigate to **Project Settings**, and under **API Keys**, click on **"Create New Key"**. Copy the **Public Key** and **Secret Key**; you'll need them to authenticate when sending data to Langfuse.
+
+### 3. Create a Sample Gradio Chat Application
+
+To create a sample Gradio chat application in Hugging Face Spaces, follow these steps:
+
+1. **Set Up Your Space:**
+
+   - Navigate to Hugging Face Spaces and create a new Space.
+   - Choose the appropriate template or start with a blank Space.
+
+2. **Add the Application Code:**
+
+   - Create a file named `app.py` in your Space.
+   - Copy the application code from [app.py](docs/hub/app.py) and paste it into your `app.py` file in the Space.
+
+3. **Define Dependencies:**
+
+   - Create a `requirements.txt` file in your Space.
+   - List all necessary dependencies for your application. For example:
+     ```
+     gradio
+     langfuse
+     openai
+     ```
+
+4. **Launch the Application:**
+
+   - Once the `app.py` and `requirements.txt` files are set up, start your Space.
+   - The application will launch, and you can interact with the Gradio chat interface.
+
+5. **View Example Traces in Langfuse:**
+
+   - After starting the application, navigate to your Langfuse dashboard.
+   - Go to the **Traces** section to view the example traces generated by your Gradio chat application.
+
+By following these steps, you can quickly set up and run a Gradio chat application in Hugging Face Spaces and observe its traces in Langfuse.
+
+### 4. View Traces in Langfuse Dashboard
+
+Open your Langfuse dashboard, navigate to **Traces** to see the recorded traces from your application, and use the observability tools to analyze and debug your LLM applications.
+
+For detailed instructions and advanced features, refer to the [Langfuse Get Started Guide](https://langfuse.com/docs/get-started).
+
+## Feedback and Support
+
+We value your feedback and are here to help if you have any questions.
+
+- **Join Our Community:** Engage with us on [Discord](https://discord.gg/langfuse) or via [GitHub Discussions](https://github.com/langfuse/langfuse/discussions)
+- **Report Issues:** Submit issues or feature requests on our [GitHub Issues](https://github.com/langfuse/langfuse/issues) page
+- **Contact Us:** Reach out via our [Support Page](https://langfuse.com/support) or email us at [[email protected]](mailto:[email protected])