OpenAI Course is Live

It was a mammoth task, but I have finally released my OpenAI and GPT3 course on Udemy.

It is 4+ hours of content with examples in many programming languages. Covers everything from prompt engineering through fine-tuning, embedding, clustering, creative writing, and safe coding practices for AI projects. (with lots of tips/tricks/examples along the way)

My previous free video course about Embedding can also be viewed for free by expanding the Embedding section of the course. I have tagged them as “free preview” videos, so you don’t have to enrol in the course or have a Udemy account to view them.

Here is a link for anyone that is interested:


Nice! Congratulations.

I can imagine it was a lot of work.


Nice! I just bought it!

1 Like

Does the module on fine tuning and embedding assume a knowledge of Python?

No it doesn’t. It can be done in any language.

You can also watch the embedding part for free on the Udemy site. Just expand the curriculum and the videos are all turned on as free previews.

1 Like

Thanks Raymond. Will check it out

I am following the course. I have been able to do my first successful embedding. It is in Spanish language and it performs so much better than my previous implementation of the same corpus via finetuning. However, I miss a feature and I think the key is to implement what you explain in section 89. Part 5 : The Final Step - Doing a Semantic Search.

I have sent you an email.

I will reply by email, but I will also post here for others that may have the same problem

Essentially you do your semantic search to find relevant pieces of text (I think you probably have that working now). One you have the text, you ask GPT a question using the text you found as a context

If your embeddings are small enough, you can include more than one context (which is what I will show you in the example below). But if your embeddings are 1 or 2 thousands tokens, you probably need to only use one, so the AI has enough tokens left to respond

Here is a sample prompt:

You are a reporter for the New York Times and are writing an article for the business column. Refer to the context below to answer the prompt that follows the context. If the answer is not in the context say “Unknown”.

this is my first lot of text found in the semantic search

here is the next context (if I have more than one)
put your question here

The whole thing is the prompt. The first bit gives it a personality. The second bit tells it to look at the context (The bit inside the area marked with the 3 quote marks at the top and bottom) and to answer the prompt (the bit after the last 3 quote mark).

I also tell it to say the word unknown if the answer is not in the context. This stops it from using general GPT knowledge and making things up.

The full stops, newlines and quotes are all important. There is also a new line character at the very end - after the question itself (very important in case you don’t ask a question with a full stop or a question mark at the end)

If you end up copying this prompt, make sure you change the quote characters to the straight version. This forum sometimes changes them to a curly quote.

Note : If your semantic search doesn’t find any related records, or the score is too low, I normally use the text “No content found” as the actual context text. (I hope that makes sense)