Expanding the Boundaries of ChatGPT with LangChain - Part One

 

You have likely noticed a massive influx of applications that claim to use artificial intelligence. Many of these applications are built using a framework called LangChain. In this post, we’ll provide a basic introduction to this technology and explain why it can be beneficial in your daily taskings.

Let’s start off with “normal” ChatGPT usage. Most users go to the ChatGPT website, ask ChatGPT to do something, and read the response. The technology is both awe-inspiring and currently limited. It’s limited by not having internet access, access to recent information, or the ability to incorporate the user’s files or data into its workflow. It’s also limited by the size of how big prompts or answers can be. The “normal” usage of ChatGPT looks like this.

You can do some amazing things with this basic model, but think of how many things aren’t incorporated here and the potential that they could unlock if they were.

This is where LangChain comes in. LangChain is a framework that allows developers to tie these entities together. 

Let’s take a look at an example. I asked ChatGPT (GPT-4) what teams are most likely to win the 2023 baseball world series. 





It states that it doesn’t have any knowledge later than September 2021 and lists a few teams that have historically been good. Not mentioned in the team that is currently favored to win the world series, the Atlanta Braves.

Now, here are the results of some Python code I wrote where I ask GPT the same question (using the API, not the web interface), but I use LangChain to give GPT access to the current world series championship odds according to MGM.


Now this is getting interesting!

We can also use LangChain to access files on our computer, in a database, etc and provide that context to GPT. Here I use LangChain to access a PDF on my filesystem (a sample pen test report) and ask GPT to summarize the document.







Ok, this is cool! We just used GPT to summarize a ten-page PDF. Lets try to use ChatGPT to analyze a larger file.


And now we see that while we’ve given GPT access to websites and files, we still have a limitation on how much data it can ingest. The good news is that we have a solution to that too.  There’s one more item we’re going to add to our LangChain model, the AI database.

First, let’s take a second to explain why I’m saying AI database instead of just database. A normal database is designed to store and share data. Exact data. If I give a database 50,000 words of text, I expect it to store all 50,000 words. With an AI database, it tries to summarize concepts from those 50,000 words and turn those concepts into numerical values. That sounds wild, but let’s look at things in a less technical way.

Imagine you have a group of 4 friends hanging out. You’ve known each other for years and hang out regularly. Now a 5th person is coming over for the first time. You know them, but they don’t know the other 4.

When the new person comes over, you won’t spend hours explaining to them who the other four visitors are; you’ll summarize. You’ll provide their name, maybe where they work, how long you’ve known them, a hobby or an interesting fact or two, and move on. That’s what an AI database does as well.  This concept is known as embeddings and is weird at first, but it is an extremely efficient way to deal with massive amounts of information.

So now, what we do is modify our Python code to use an AI database to summarize our information and provide that to GPT for background context to answer our prompts. There are multiple options we could choose for our database, including online options, such as Pinecone, and local options including Chroma.

Here we modify our Python code to use Chroma in ingesting a 387-page PDF book on using Python to program video games. 






We then provide that information to GPT and ask it to summarize the book. Second later, we have a response.

I’ve said multiple times that I think the most under-appreciated capability of large language models like ChatGPT is the ability to summarize, and this unlocks that capability to a whole new world of data.

There’s a lot more to LangChain than we’ve covered here. It can work with numerous data sources and other LLMs. Since we’re using the GPT API, there is a small fee associated with each request. Running all of the examples for this blog post, including the 378-page PDF, cost less than $0.30.

In part two of this blog series, we’ll look at the Python code and how you can get it up and running.


Comments

Post a Comment

Popular posts from this blog

SANS Index How To Guide with Pictures

Image
I got some great advice recently on creating an index for SANS exams and I wanted to write a blog post to share it with others. I took the SANS FOR 508 Computer Forensics course in 2008. It was way over my head but I had a great time and learned a ton. A few months ago I finally decided to go for my GCFA certification. I had four year old material from a course that had been completely revamped and no index. I passed the exam with a score in the 80s but it was a grueling experience. I had to rush on the last part of the exam and never felt comfortable. A few months after my GCFA exam I got an opportunity to attend a SANS SEC 504 class. I really wanted to prepare for my GCIH exam the right way so while I was at the conference I asked several individuals how they prepared their index. Most people told me that their indexes were 8-10 pages. A lot of these people had more SANS certs than I have friends so their methods obviously worked for them. My class had a teaching assistant (also SANS...
Read more

Leveling Up Your OSINT Game: Creating a Professional Email on a Budget

Image
  Some sites do not allow new users to register with a “free” email such as gmail.com or outlook.com. This is especially true if a site offers some free capability, but with the hope of converting you into a paying customer. Most OSINT practitioners would prefer to avoid using their “real” work email to signup for services, so the easiest solution is to register a domain (if you don’t already have one) and setup an email account using that. In this blog post we’ll explore how to accomplish this task as easily, and inexpensively as possible. Step 1: Acquire The Domain Many of us have likely purchased a .com or other domain over the years. Maybe you still have some, or maybe they expired. For years the only domain registrar I used was Google Domains. It was easy, inexpensive and provided free private registration to help enhance privacy. Recently, Google decided to get out of the domain registration business and is in the process of transferring all registered domains to Square...
Read more

Introducing FaviconLocator: The Eazy Button to Searching by Favicon

Image
  Favicons (short for favorite icons) are the cute little pixelated images that appear next to the site name in web browser tabs, bookmarks, etc. In the image below we can see the iconic GitHub logo on their site and the KFC logo on a bucket of chicken on their site. Originally, favicons were designed to add a touch of professionalism and branding, but for anyone who is like me and has over a dozen tabs open at any time, favicons are the only thing displayed and how I navigate tabs. Most of us rely on favicons on a daily basis but many never think of them as a tool we can use in OSINT and CTI investigations. That’s what we’re doing to talk about here as well as introduce a new tool. In addition to branding and aiding in navigation between tabs, favicons can serve as unique identifiers for websites. These unique identifiers can help us: Trace the online presence of organizations and discover obscure digital assets Map the online infrastructure of potential threats Potentially de...
Read more