Skip to content

Update Integrate a Large Language Model with the xeus-cpp Jupyter kernel final blogpost for GSoC 24 #261

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 19, 2024
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ excerpt: "Integrate a Large Language Model with the xeus-cpp Jupyter kernel, par
sitemap: false
author: Tharun Anandh
permalink: blogs/gsoc24_tharun_anandh_final_blog/
banner_image: /images/blog/gsoc-banner.png
date: 2024-10-17
tags: gsoc xeus xeus-cpp cpp llm
---
Expand All @@ -25,7 +26,7 @@ Xeus-cpp is a Jupyter kernel for C++ built on the native Jupyter protocol, enabl

### Implementation

![Codeflow](./images/blog/codeflow.png)
![Codeflow](/images/blog/codeflow.png)

I created a magic function called XAssist that connects to a specific LLM based on the user's preference. It utilizes utility functions and the cURL library to connect with the LLM and retrieve the respective response. The user saves the API keys for OpenAI and Gemini, sets the URL for Ollama, saves a particular model, and then uses the LLM.

Expand Down Expand Up @@ -100,7 +101,7 @@ I created a magic function called XAssist that connects to a specific LLM based

Here is an example that demonstrates how one can use XAssist.

![Gemini](./images/blog/gemini.png)
![Gemini](/images/blog/gemini.png)

---

Expand Down
Loading