/tmls-llm-selection

Optimizing LLM Selection for GenAI Development

Primary LanguageJupyter NotebookMIT LicenseMIT

TMLS - Modular LLM development with DSPy

This is a hands-on tutorial and you will get the most out of it if you are able to run the notebook along with us. You do not need to clone this repo. Please copy the colab notebooks linked below to follow along. If you have OpenAI API Key, please use that or follow the links below to get one of Groq or Gemini free API Keys:

Google API KEY

If you would like to use Google's Gemini model, please go through the following steps to obtain the key.

1. Sign in to your non-workspaced Gmail account
2. Go to https://aistudio.google.com/app/apikey and get your key
    * You should see a pop-up. If you don’t, then you’re are in a workspace-d account. Use a personal gmail account or try a different API key provider
3. Click on Create Api key
4. Copy the key to the Secrets tab on the left bar of your colab

Groq API KEY

If you would like to use Groq for Mistral model, please signup for an API key here: https://console.groq.com/keys

1. Go to https://console.groq.com/keys and signup using your email
2. Click on Create API Key and give it a name
3. Copy the key to the Secrets tab on the left bar of your colab

Openai API KEY

If you do not have an API key, please enter your gmail in the link below. We can only share keys with gmail accounts at this time.

Open In Google Sheets

Tutorial notebooks

DSPy

Follow along with DSPy tutorial:

Open In Colab

TextGrad

Access TextGrad tutorial:

Open In Colab