This repository contains Jupyter notebooks for the course LangChain & Vector Databases in Production Course. This course is brought to you in collaboration with Activeloop, Towards AI, & Intel Disruptor Initiative, designed to equip you with the knowledge and skills to train, fine-tune, and incorporate Large Language Models (LLMs) into AI products at your organization.

This repository is perfect for both experienced developers new to the AI realm and experienced machine learning enthusiasts. The course aims to make AI accessible and practical, transforming how you approach your daily tasks and the overall impact of your work.

By following along with the Jupyter notebooks in this repository, you will:

• Master LLM & Vector Database fundamentals.
• Build production-grade LLM applications with LangChain.
• Learn how to use Deep Lake, the only multi-modal vector database.

The course and thus the notebooks in this repository follow the below curriculum:

1. Course Introduction
2. From Zero to Hero
3. Large Language Models and LangChain
4. Learning How to Prompt
5. Keeping Knowledge Organized with Indexes
6. Combining Components Together with Chains
7. Giving Memory to LLMs
8. Making LLMs Interact with the World Using Tools
9. Using Language Model as Reasoning Engines with Agents

The course, and thus this repository, consists of:

• 63 lessons.
• Learning how to use the only multi-modal Vector DB.
• 10+ practical projects like building LLM-powered sales & customer support agents【9†source】.

1. Clone this repository.
2. Navigate to the cloned directory.
3. Run the Jupyter notebooks in the order of the course curriculum.

• Basic knowledge of Python programming.
• Basic understanding of machine learning concepts.

Feel free to contribute to this repository by submitting issues, or by forking this repository and submitting pull requests.

This project is licensed under the terms of the MIT license.