jupyter-ai
jupyter-ai copied to clipboard
jupyterlab
A generative AI extension for JupyterLab
## Description - Makes the help message template configurable via `traitlets`. - Performs some fairly significant refactoring. The method for sending a help message has been moved from `HelpChatHandler` to...
This would be the first step of https://github.com/jupyterlab/jupyter-ai/issues/785, before discussing how to use the collaborative chat extension. ### Problem [`@jupyter/chat`](https://github.com/jupyterlab/jupyter-chat/tree/main/packages/jupyter-chat) package was built mainly by refactoring the code of the...
Hello!! After deploying the Ollama Pod on Kubernetes, a problem occurs when jupyter_ai requests a prompt from the Pod. “you must answer to Korean Language” is written in Ollama Pod’s...
## Description Makes chat memory size configurable via `default_max_chat_history` traitlet. Also makes /clear reset memory. The reason why these unrelated features are in same PR stems from the same core...
### Problem I want to make use of an Azure Open AI model with a predefined dataset also deployed as an Azure web app in jupyter-ai. To my knowledge you...
> This is likely due to the upstream changes in `langchain`; `langchain` recently moved all of its OpenAI models to the `langchain-openai` package, so you now need to install `langchain-openai`...
I have a local LLM interface. How do I implement localized deployment using JupyterAI?
OSError: Authentication environment variables [] are not set. Multiple authentication tokens are required to use models from the ERNIE-Bot provider. Please specify them all via `%env` commands. I have specified...
Just to ensure that FIM is on the radar at jupyter-ai I leave this comment here. FIM ([Fill-in-the-Middle](https://medium.com/@SymeCloud/what-is-fim-and-why-does-it-matter-in-llm-based-ai-53f33385585b), [Fill-in-the-Middle](https://codeium.com/blog/why-code-completion-needs-fill-in-the-middle)) is to my knowledge a widely used approach in prompt-generation for...
Context: I am developing a custom image for my JupyterHub users that has jupyter-ai installed and configured out-of-the-box. The custom image is built on top of the [jupyter-minimal](https://jupyter-docker-stacks.readthedocs.io/en/latest/using/selecting.html#jupyter-minimal-notebook) base image....
