This project is designed to gain hands-on experience in building and deploying applications using Large Language Models (LLMs). You will explore various tools and frameworks, create LLM applications, and integrate them with user interfaces (UIs). This project can be undertaken in groups of 2 to 3 students.

Key Topics and Tasks:

Langchain:

• Learn to use Langchain for LLM.
• Develop at least two example applications utilizing Langchain.

Langsmith:

• Build at least one LLM application using Langsmith.

Langserve:

• Deploy your LLM application using LangServe.

Langchain Agents:

• Create two distinct agents using Langchain.

Langchain Retrieval:

• Construct one application using Retrieval-Augmented Generation (RAG) approach.

Langchain Templates:

• Incorporate at least two templates from Langchain in your application.

Chatbots with Llamaindex:

• Develop a chatbot with a user interface.

Full-Stack Web Application with Llamaindex:

• Create and run a full-stack web application.

Embeddings with JinaAI API:

• Build an application with a UI that demonstrates text and query embedding functionalities.

LlamaHub:

• Utilize at least 5 data loaders in your app with an integrated UI.

Multi-Modal Retrieval:

• Implement a UI-based application for GPT text embedding and CLIP image embedding for Wikipedia Articles.

Fine-Tuning Pretrained Models:

• Fine-tune any open-source model with available data.

GPT4All:

• Develop two examples with UIs, including a chatbot and a text generation application.

Assistants API by OpenAI:

• Build an assistant with instructions and capabilities to leverage models, tools, and knowledge to respond to user queries, integrated with a UI.