OLLAMA + OPEN-WEBUI + PIPELINES + LANGFUSE

Introduction

This repository provides a setup for integrating OLLAMA, OPEN-WEBUI, PIPELINES, and LANGFUSE using Docker. Follow the steps below to get everything up and running.

Prerequisites

• Docker and required GPU drivers installed on your system.

Installation

1. Clone this repository:

   git clone https://github.com/karaketir16/openwebui-langfuse.git
   cd openwebui-langfuse

2. Run the setup script:

   ./run-compose.sh

   or

   docker compose up -d
   # default driver is nvidia

Configuration

Langfuse Setup

0. Documentation

   • You can find up-to-date documentation here.

1. Download the langfuse_filter_pipeline.py file:

   • You can download latest file from here, or use the provided file in example/langfuse_filter_pipeline.py.

2. Access Langfuse:

   • Open your browser and go to http://localhost:4000.

3. Create an Admin Account and Project:

   • Create an admin account and then create a project.
   • Go to Project Settings and create an API key.
   • Retrieve the secret key and public key.

4. Update the Pipeline Script:

   • Replace your-secret-key-here with your secret key, your-public-key-here with your public key, and https://cloud.langfuse.com with http://langfuse:4000 in langfuse_filter_pipeline.py.
   • Note: If you are using the example in this repository, replace the secret key and public key with your own keys.

Open-WebUI Setup

1. Access Open-WebUI:

   • Open your browser and go to http://localhost:3000.

2. Create an Admin Account:

   • Create an admin account.

3. Upload the Pipeline Script:

   • Navigate to Settings -> Admin Settings -> Pipelines.
   • In the Upload Pipeline section, select the langfuse_filter_pipeline.py file and click the upload button.

4. Monitor Usage:

   • You can now monitor Open-WebUI usage statistics from Langfuse.

Model Downloading

1. Access Open-WebUI:

   • Open your browser and go to http://localhost:3000.

2. Create an Admin Account:

   • Create an admin account.

3. Pull Models:

   • Navigate to Settings -> Admin Settings -> Models.
   • Enter a model tag to pull from the Ollama library (e.g., phi3:mini).
   • Press the pull button.