It is born out of 3 years of experience building LLM applications starting from GPT-3 completion models to the latest frontier chat models. This also

Search code, repositories, users, issues, pull requests...

submited by

Style Pass

2024-11-28 19:00:09

It is born out of 3 years of experience building LLM applications starting from GPT-3 completion models to the latest frontier chat models.

This also installs LiteLLM and Pandas by default. If you would like to use other LLM providers such as Anthropic or Google AI, please install the respective SDK as well.

setup and chat has a lot of optional parameters that you can find while hovering over the method in your IDE. Some notable parameters for setup are model, temperature, api_key, and any supported LiteLLM completion parameters. Similarly, chat has parameters such as tools, stop_words, tool_choice etc.

user_message can take a couple of types of inputs. It can be a string as you've just seen, it can be an image object(PIL.Image) it can be an array of strings and images.

aiide has first-class support for memory. I found that handling OpenAI JSON based schema is cumbersome and error-prone. So, I had abstracted the chat history into a Pandas DataFrame.