https://github.com/byebyebruce/ollamax

Ollama library wrapper
https://github.com/byebyebruce/ollamax

ai gguf llama2 llamacpp llm local-llm ollama qwen

Last synced: about 1 month ago
JSON representation

Ollama library wrapper

• Host: GitHub
• URL: https://github.com/byebyebruce/ollamax
• Owner: byebyebruce
• Created: 2024-03-29T04:44:55.000Z (8 months ago)
• Default Branch: master
• Last Pushed: 2024-04-28T08:41:30.000Z (7 months ago)
• Last Synced: 2024-09-30T22:33:35.554Z (about 2 months ago)
• Topics: ai, gguf, llama2, llamacpp, llm, local-llm, ollama, qwen
• Language: Go
• Homepage:
• Size: 117 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Ollamax

Ollamax is a simple and easy to use library for making a local LLM app.  

It is based on the [Ollama](https://github.com/ollama/ollama)

## Demos

- [Local LLM Chat Demo](demo/chat)

- [Local LLM Embedding](demo/embedding)

- [Local LLM Vision](demo/vision)

## How to use

go >= 1.22

1. Init your go module

    ```bash

    go mod init 

    ```

2. Add submodule

    ```bash

    git submodule add https://github.com/byebyebruce/ollamax.git

    ```

   

3. Init go work

    ```bash

    go work init . ./ollamax ./ollamax/ollama

    ```

4. Build library

    ```bash

    make -C ollamax

    ```

5. Write a test code

   ```go

   import(

       "github.com/byebyebruce/ollamax"

   )

   if err := ollamax.Init(); err != nil {

       log.Fatalln(err)

   }

   defer ollamax.Cleanup()

   llm, err := ollamax.NewWithAutoDownload("qwen:0.5b")

   if err != nil {

       panic(err)

   }

   defer llm.Close()

   llm.Chat...

   ```

## Where to find models

https://ollama.com/library