Let's build a 100% free copilot using an open-source LLM
𝗧𝗵𝗲 𝗰𝗵𝗮𝗹𝗹𝗲𝗻𝗴𝗲
Last week Hugging Face released 𝗦𝘁𝗮𝗿𝗖𝗼𝗱𝗲𝗿𝟮, the first Fully Transparent and Permissive Self-Alignment LLM for 𝗖𝗼𝗱𝗲 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻, with open-source weights AND training data.
Let's use this model to build our own FREE AI Coding Assistant and integrate it with VS Code.
This way you can stop paying 10 USD/month for GitHub Copilot, and say thank you to the open-source community.
𝗦𝘁𝗲𝗽 𝟭. 𝗗𝗼𝘄𝗻𝗹𝗼𝗮𝗱 𝗦𝘁𝗮𝗿𝗖𝗼𝗱𝗲𝗿𝟮 𝘄𝗶𝘁𝗵 𝗢𝗹𝗹𝗮𝗺𝗮 🦙
Ollama is an open-source tool to run Large Language Models locally, that you can download for free from here.
Once installed on your laptop, you can use the ollama command line tool, to download starcoder2:instructs (15B parameters)
ollama pull starcoder2𝗦𝘁𝗲𝗽 𝟮. 𝗗𝗼𝘄𝗻𝗹𝗼𝗮𝗱 𝘁𝗵𝗲 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗲 𝗩𝗦𝗖𝗼𝗱𝗲 𝗲𝘅𝘁𝗲𝗻𝘀𝗶𝗼𝗻
Continue is an open-source extension for VSCode that helps you connect your VSCode editor with the LLMs you download with Ollama.
Link to download it -> https://marketplace.visualstudio.com/items?itemName=Continue.continue
𝗦𝘁𝗲𝗽 𝟯. 𝗖𝗼𝗻𝗻𝗲𝗰𝘁 𝗩𝗦𝗖𝗼𝗱𝗲 𝘄𝗶𝘁𝗵 𝘁𝗵𝗲 𝗟𝗟𝗠
From your VSCode IDE
→ Go to the bottom and click on the + sign, to Add a New Model.
→ Select Ollama as your provider, and
→ Select Autodetect, to automatically populate the model list with all models you downloaded with Ollama.
𝗦𝘁𝗲𝗽 𝟰. 𝗟𝗲𝘁 𝘁𝗵𝗲 𝘁𝗮𝗯-𝗮𝘂𝘁𝗼𝗰𝗼𝗺𝗽𝗹𝗲𝘁𝗲 𝗺𝗮𝗴𝗶𝗰 𝗯𝗲𝗴𝗶𝗻
As you start coding, StarCoder2 will keep on generating suggestions, that will increase your speed.
You can also highlight code, press Comand + L, and ask questions to your assistant.
Let's keep the conversation going!
What are your thoughts on the limitations of AI for struggling companies? Share your experiences and ideas for successful AI adoption.
Contact us(info@drpinnacle.com) today to learn more about how we can help you.
Comments