Create Your Own ChatGPT with PDF Data in 5 Minutes (LangChain Tutorial)

If you've ever wanted to know how to chat with your PDFs or train ChatGPT on your own data, this is the video for you! Code available below.

Create a copy of my notebook (code):

Timestamps:
0:00 - What we're building
1:10 - System Explained
2:48 - Creating the chatbot
8:18 - Steal my code!

[borisbadinoff]

👏👏 Hey Liam, your five-minute tutorial is fantastic! Kudos and thanks for putting the effort to produce it. Your app is exactly what any knowledge worker is craving for: We all have gigabytes of pdf files in some folder named "READ", "TO READ" or "__TO READ" (so it stays on top of the root :), but never get to it (probably distracted by all these tutorials to become more productive we love to watch). A bot that can read that stuff for us, so we can continue to wing it is a true godsend. :D

[moses]

Golden! Clear, concise info and a notebook! If it's too fast for some viewers, I'll remind that they can always show down the replay speed.

[guilhermeveiga]

Thought it would be just another video on the subject, but you summarize in an awesome way! Great vid! Congrats

[naturallydope]

This was definitely one of your better videos. You explained Langchain well and I’m glad you used the colab notebook instead of Jupyter or repl.

[SedhuujGorem]

I like some of the transitions, but sometimes they're a bit too much and are seemingly random. Since we use these persistent elements that transition across pages to indicate some kind of relationship between the previous and the next states, some of your transitions confuse me because I can't immediately see what the relationship is.

For example 1:23 of the selectable tiles (which weren't selected) transition into being two switches... does that mean anything? are they related in some way? I see this as random and a bad use of the design language. However, at 3:14 I like the transition from switches to the ticks on a paper, that makes sense to me. Epic presentation tho

[ryanjames]

thank you for time, effort and generosity,

I wish very good things for you.

[rishabpoddar]

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
yfinance 0.2.18 requires beautifulsoup4>=4.11.1, but you have beautifulsoup4 4.8.2 which is incompatible.

[tspang]

Hi Liam, great video. I do have a question, from the following code, i notice that we don't have to specifically turn the "query" into embeddings, before it performs a search against the vector db? Is it because the function "similiary_serach" internally calls the openapi embedding to perform words embeddings?

query = "Who created transformers?"
docs = db.similarity_search(query)

[chandrachoodR]

Thats a fantastic video and to the point and thanks for the code as well

[gabijazza]

Cheers, this is a brilliant video. Looking forward to making a bespoke AI.

[stefano]

Excellent! Thank you for your hard work to put these together.

[coinhawk]

Great job... will run this on my writings/ book collection and my code snippets, and build an awesome, MeKnowledgeBase 😎

[justingu]

Thank you for your excellent sharing. This is great guidance, and I hope you can continue to share more! If there's anything I can do, please let me know~

[Esteband]

Thank you it worked perfectly despite generating an error on the pip install.
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
yfinance 0.2.18 requires beautifulsoup4>=4.11.1, but you have beautifulsoup4 4.8.2 which is incompatible.

[weqokjq]

is there way to also store the questions from the user and the answers to them for monitoring, data analysis and other ideas?

[sganesh]

Thanks Liam ... neat and fast as always; could you post another similar video doing the same thing with Llama index pls. I thought that was easier.

[qwerto-yepe]

Hi! I just wanted to ask what are the licenses used in this project? Are they commercial-friendly?

[noteniceu]

Can you feed it multiple pdf at the same time like a group of 300 or would you have to run each line individually.

[JJBoi]

What is a good way to split text in a textbook pdf because on one page it has 2 columns, text on the left and right side?

[rfdlbls]

Hia Liam! Which version of gpt does the chatbot use? Can I use it with gpt4?