Skip to main content

​
Ollama Configuration

Ollama Configuration Interface The Ollama configuration screen in PipesHub where you’ll configure your local Ollama instance connection PipesHub allows you to integrate with Ollama to run open-source language models locally, providing privacy-focused AI capabilities in your workspace with full control over your data and infrastructure.

​
Required Fields

​
Model Name *

The Model Name field defines which Ollama model you want to use with PipesHub. Popular Ollama models include:
  • qwen3-vl:8b - Multimodal model supporting both text and images
How to choose a model:
  • For multimodal capabilities (text + images), select models with vision support like qwen3-vl:8b
  • Check Ollama’s model library for the complete list of available models

​
Endpoint URL *

The Endpoint URL specifies where your Ollama instance is running. Common configurations:
  • http://host.docker.internal:11434 - For accessing Ollama from within a Docker container
  • https://your-server-domain - For remote Ollama instances
Default port: Ollama runs on port 11434 by default. Note: Ensure your Ollama instance is running and accessible at the specified endpoint before configuring PipesHub.

​
Optional Fields

​
API Key

The API Key field is optional for Ollama configurations. Most local Ollama instances do not require authentication. When to use:
  • If you’ve configured authentication on your Ollama instance
  • When connecting to a secured remote Ollama server
  • For enterprise deployments with access control
If your Ollama instance doesn’t require authentication, you can leave this field empty.

​
Advanced Options

​
Multimodal Support

Enable the Multimodal checkbox if your selected model supports both text and image inputs. Multimodal-capable models include:
  • qwen3-vl:8b
When enabled:
  • PipesHub can send both text and image data to the model
  • Supports use cases like image analysis, visual question answering, and document understanding

​
Reasoning

Enable the Reasoning checkbox if your selected model has enhanced reasoning capabilities. When enabled:
  • The model will be used for tasks requiring complex logical reasoning
  • Better performance on multi-step problem solving
  • Enhanced analytical capabilities

​
Configuration Steps

As shown in the image above:
  1. Select “Ollama” as your Provider Type from the dropdown
  2. Enter your Model Name (marked with *) - e.g., qwen3-vl:8b, mistral:latest
  3. Specify your Endpoint URL (marked with *) - e.g., http://host.docker.internal:11434
  4. (Optional) Enter an API Key if your Ollama instance requires authentication
  5. Check “Multimodal” if your model supports text + image processing
  6. Check “Reasoning” if your model has enhanced reasoning capabilities
  7. Click “Add Model” to complete the setup
Both the Model Name and Endpoint URL are required fields to successfully configure Ollama integration. You must complete these fields to proceed with the setup.

​
Prerequisites

Before configuring Ollama in PipesHub, ensure you have:
  1. Ollama installed on your machine or server
    • Download from ollama.com
    • Follow installation instructions for your operating system
  2. Model downloaded - Pull your desired model: 
    ollama pull qwen3-vl:8b
# or any other model from the library
  3. Ollama running - Start the Ollama service: 
    ollama serve
  4. Network accessibility - Ensure PipesHub can reach your Ollama endpoint

​
Usage Considerations

​
Advantages of Ollama

  • Privacy: All processing happens locally or on your infrastructure
  • Cost-effective: No API usage fees or quotas
  • Customizable: Full control over model selection and configuration
  • Offline capable: Works without internet connectivity (after initial model download)
  • No rate limits: Process as many requests as your hardware can handle

​
System Requirements

  • Sufficient RAM (varies by model - typically 8GB minimum, 16GB+ recommended)
  • Modern CPU or GPU for optimal performance
  • Adequate disk space for model storage (models range from 2GB to 40GB+)

​
Performance Tips

  • Use GPU acceleration when available for faster inference
  • Choose smaller models for quicker responses if your use case allows
  • Consider quantized models (e.g., llama2:7b-q4 vs llama2:7b) for lower memory usage

​
Troubleshooting

​
Connection Issues

  • Verify Ollama is running: Run ollama list in your terminal
  • Check endpoint URL: Ensure the URL matches where Ollama is accessible
  • Firewall settings: Verify that port 11434 is not blocked
  • Docker networking: If using Docker, ensure proper network configuration for host.docker.internal

​
Model Issues

  • Model not found: Ensure you’ve pulled the model with ollama pull <model-name>
  • Out of memory: Try a smaller or quantized version of the model
  • Slow performance: Consider using a GPU

​
Multimodal Issues

  • Images not processing: Verify your selected model supports vision capabilities
  • Check model documentation: Not all models support multimodal inputs

​
Available Models

Visit the Ollama Model Library to browse all available models, including:
  • Language models (LLMs)
  • Code-specialized models
  • Multimodal models (vision + language)
  • Embedding models
  • Quantized variants for efficiency
For additional support, refer to the Ollama documentation or contact PipesHub support.