Build a Neo4j-backed Chatbot using Python
Course Description
In this hands-on course, you will use the knowledge obtained from the Neo4j & LLM Fundamentals course to create a Movie Recommendation Chatbot backed by a Neo4j database.
You will take a simple chat interface that repeats the user’s input and modify it to answer questions about movies via the Neo4j Recommendations Dataset using GPT 3.5 Turbo, complete with conversational history.
The chatbot will be able to answer questions like:
-
How many movies has Tom Hanks acted in?
-
What is the most popular movie in the database?
-
Can you recommend a movie for fans of The Matrix and Casino?
At the end of the course, you will have a working chatbot built with Streamlit.
Prerequisites
This course relies heavily on the information in the Neo4j & LLM Fundamentals course. We recommend completing this course first if you have not already done so.
We also assume a basic understanding of Python. It is not necessary, but you may also benefit from taking the Building Neo4j Applications with Python course to understand how the Neo4j Python Driver works.
The course uses Streamlit to build a simple chat interface. We do not focus heavily on the Streamlit functionality, so it may be worth reviewing the Streamlit Get Started guide.
Duration
2 hours
What you will learn
-
How to build a Neo4j-backed Chatbot with Langchain and 3.5-Turbo
-
Answering user queries with an LLM
-
Retrieval Augmented Generation (RAG)
-
Langchain Agents and QA Chains
Get Support
If you find yourself stuck at any stage then our friendly community will be happy to help. You can reach out for help on the Neo4j Community Site, or head over to the Neo4j Discord server for real-time discussions.
Feedback
If you have any comments or feedback on this course you can email us on graphacademy@neo4j.com.