ollama-stream-example

README

Ollama Streaming Example with LangChain Go

👋 Hello, Go enthusiasts and AI adventurers! Welcome to this exciting example that showcases how to use LangChain Go with Ollama for streaming AI-generated content. Let's dive in and see what this cool code does! 🚀

What's This All About?

This example demonstrates how to:

1. Set up an Ollama-based language model (LLM) 🤖
2. Create a conversation with system and user messages 💬
3. Generate content using the LLM with real-time streaming 🌊

The Magic Explained

Here's what's happening in this nifty little program:

1. We start by creating an Ollama LLM instance using the "mistral" model. Mistral is known for its efficiency and quality, so good choice! 👍

2. We set up a conversation with two messages:

   • A system message that tells the AI to act as a "company branding design wizard" 🧙‍♂️
   • A user message asking for a company name suggestion for a Go-backed LLM tools producer 🏢

3. The real magic happens when we call GenerateContent. We use a streaming function that prints out the AI's response in real-time. It's like watching the AI think! 🤯

Running the Example

To run this example, make sure you have Ollama set up and running on your machine. Then, simply execute the Go file:

go run ollama_stream_example.go

You'll see the AI's response appear on your screen character by character. It's mesmerizing! ✨

Why This is Cool

• Real-time streaming: See the AI's thoughts as they form!
• Local LLM: Ollama runs on your machine, giving you more control and privacy.
• Go power: Harness the speed and simplicity of Go for AI applications.

So there you have it! A simple yet powerful example of streaming AI responses using LangChain Go and Ollama. Happy coding, and may your Go programs be ever intelligent! 🎉👩‍💻👨‍💻