Locked learning resources

Join us and get access to thousands of tutorials and a community of expert Pythonistas.

Unlock This Lesson

Locked learning resources

This lesson is for members only. Join us and get access to thousands of tutorials and a community of expert Pythonistas.

Unlock This Lesson

Vector Databases and Embeddings With ChromaDB (Summary)

The rise of large language models has taken the world by storm and necessitated additional tools, like vector databases, to augment their use cases. ChromaDB is a vector database designed specifically with LLM applications in mind, and it’s a great choice for your next LLM application.

In this video course, you’ve learned:

  • What vectors are and how they represent unstructured information
  • What word and text embeddings are
  • How you can work with embeddings using spaCy and SentenceTransformers
  • What a vector database is
  • How you can use ChromaDB to add context to a large language model

You can feel confident in your understanding of vector databases and their use in LLM applications. Be sure to keep a close eye on ChromaDB as the library progresses, and think about how you can leverage it on your own unstructured data. What will you build with ChromaDB?

Additional resources:

Locked learning resources

Join us and get access to thousands of tutorials and a community of expert Pythonistas.

Unlock This Lesson

Already a member? Sign-In

Locked learning resources

The full lesson is for members only. Join us and get access to thousands of tutorials and a community of expert Pythonistas.

Unlock This Lesson

Already a member? Sign-In

00:00 Kudos to you for completing Vector Databases and Embeddings With ChromaDB. You truly covered a lot of ground on this one. You should be proud. You started with the basic foundations of vectors and went all the way to connecting a vector database with a live LLM API.

00:15 In this course, you learned how to explain what vectors are and why they’re important. How to apply vector operations using Python libraries like NumPy. How to represent unstructured data with word and text embeddings using spaCy and sentence-transformers.

00:30 You stored and queried embeddings using a vector database. And in the end, you were able to enhance LLM responses with relevant context using ChromaDB.

00:40 And you don’t have to stop here. Here’s a few ideas for next steps. Since you mainly worked in the REPL in this course, how about converting the code you’ve written into a Python script or even a full command-line application?

00:51 You could also implement file uploading or automated web scraping to programmatically build and grow data sets for your vector database. Or go all out, create a RAG-based LLM chatbot.

01:04 For more ChromaDB content, you can always check out the tutorial this course is based on, Embeddings and Vector Databases With ChromaDB.

01:13 Or for something different, how about a few data science-based recommendations? If you’re just starting out on your AI and data science journey, the learning path Machine Learning With Python is an excellent resource with courses, quizzes, tutorials, and even podcasts.

01:28 Interested in interactive Python? Getting Started With marimo Notebooks introduces the marimo notebook, a really cool Python notebook and alternative to Jupyter Notebook. But maybe you want to stay on the subject of LLMs.

01:41 If so, check out First Steps With LangChain, a library you can use to build all sorts of AI-powered applications.

01:49 And that’s it for me. This has been Joseph. Thank you for watching.

Become a Member to join the conversation.