😴 🧙🌈 ʕ•ᴥ•ʔ

The following article covers the steps to build a real world LLM app or architecture, as visioned by GitHub ML engineers.

https://github.blog/2023-10-30-the-architecture-of-todays-llm-applications/


Here’s everything you need to know to build your first LLM app and problem spaces you can start exploring today.

Flow chart that reads from right to left, showing components of a large language model application and how they all work together.

Flow chart that reads from right to left, showing components of a large language model application and how they all work together.

We want to empower you to experiment with LLM models, build your own applications, and discover untapped problem spaces. That’s why we sat down with GitHub’s Alireza Goudarzi, a senior machine learning researcher, and Albert Ziegler, a principal machine learning engineer, to discuss the emerging architecture of today’s LLMs.

In this post, we’ll cover five major steps to building your own LLM app, the emerging architecture of today’s LLM apps, and problem areas that you can start exploring today.

Five steps to building an LLM app

Building software with LLMs, or any machine learning (ML) model, is fundamentally different from building software without them. For one, rather than compiling source code into binary to run a series of commands, developers need to navigate datasets, embeddings, and parameter weights to generate consistent and accurate outputs. After all, LLM outputs are probabilistic and don’t produce the same predictable outcomes.

Diagram that lists the five steps to building a large language model application. Data source for diagram is detailed here: https://github.blog/?p=74969&preview=true#five-steps-to-building-an-llm-app

Diagram that lists the five steps to building a large language model application. Data source for diagram is detailed here: https://github.blog/?p=74969&preview=true#five-steps-to-building-an-llm-app

Let’s break down, at a high level, the steps to build an LLM app today. 👇

1. Focus on a single problem, first. The key? Find a problem that’s the right size: one that’s focused enough so you can quickly iterate and make progress, but also big enough so that the right solution will wow users.

For instance, rather than trying to address all developer problems with AI, the GitHub Copilot team initially focused on one part of the software development lifecycle: coding functions in the IDE.

2. Choose the right LLM. You’re saving costs by building an LLM app with a pre-trained model, but how do you pick the right one? Here are some factors to consider:

Conventional wisdom tells us that if a model has more parameters (variables that can be adjusted to improve a model’s output), the better the model is at learning new information and providing predictions. However, the improved performance of smaller models is challenging that belief. Smaller models are also usually faster and cheaper, so improvements to the quality of their predictions make them a viable contender compared to big-name models that might be out of scope for many apps.

What are offline evaluations?

They’re tests that assess the model and ensure it meets a performance standard before advancing it to the next step of interacting with a human. These tests measure latency, accuracy, and contextual relevance of a model’s outputs by asking it questions, to which there are either correct or incorrect answers that the human knows.

There’s also a subset of tests that account for ambiguous answers, called incremental scoring. This type of offline evaluation allows you to score a model’s output as incrementally correct (for example, 80% correct) rather than just either right or wrong.

3. Customize the LLM. When you train an LLM, you’re building the scaffolding and neural networks to enable deep learning. When you customize a pre-trained LLM, you’re adapting the LLM to specific tasks, such as generating text around a specific topic or in a particular style. The section below will focus on techniques for the latter. To customize a pre-trained LLM to your specific needs, you can try in-context learning, reinforcement learning from human feedback (RLHF), or fine-tuning.

In-context learning can be done in a variety of ways, like providing examples, rephrasing your queries, and adding a sentence that states your goal at a high-level.

The benefit to RLHF is that it doesn’t require supervised learning and, consequently, expands the criteria for what’s an acceptable output. With enough human feedback, the LLM can learn that if there’s an 80% probability that a user will accept an output, then it’s fine to generate. Want to try it out? Check out these resources, including codebases, for RLHF.

Fine-tuning can result in a highly customized LLM that excels at a specific task, but it uses supervised learning, which requires time-intensive labeling. In other words, each input sample requires an output that’s labeled with exactly the correct answer. That way, the actual output can be measured against the labeled one and adjustments can be made to the model’s parameters. The advantage of RLHF, as mentioned above, is that you don’t need an exact label.

4. Set up the app’s architecture. The different components you’ll need to set up your LLM app can be roughly grouped into three categories:

5. Conduct online evaluations of your app. These evaluations are considered “online” because they assess the LLM’s performance during user interaction. For example, online evaluations for GitHub Copilot are measured through acceptance rate (how often a developer accepts a completion shown to them), as well as the retention rate (how often and to what extent a developer edits an accepted completion).

Why are online evaluations important?

Although a model might pass an offline test with flying colors, its output quality could change when the app is in the hands of users. This is because it’s difficult to predict how end users will interact with the UI, so it’s hard to model their behavior in offline tests.

The emerging architecture of LLM apps

Let’s get started on architecture. We’re going to revisit our friend Dave, whose Wi-Fi went out on the day of his World Cup watch party. Fortunately, Dave was able to get his Wi-Fi running in time for the game, thanks to an LLM-powered assistant.

Flow chart that reads from right to left, showing components of a large language model application and how they all work together. Data source for diagram is detailed here: https://github.blog/?p=74969&preview=true#the-emerging-architecture-of-llm-apps

Flow chart that reads from right to left, showing components of a large language model application and how they all work together. Data source for diagram is detailed here: https://github.blog/?p=74969&preview=true#the-emerging-architecture-of-llm-apps

We’ll use this example and the diagram above to walk through a user flow with an LLM app, and break down the kinds of tools you’d need to build it. 👇

User input tools

When Dave’s Wi-Fi crashes, he calls his internet service provider (ISP) and is directed to an LLM-powered assistant. The assistant asks Dave to explain his emergency, and Dave responds, “My TV was connected to my Wi-Fi, but I bumped the counter, and the Wi-Fi box fell off! Now, we can’t watch the game.”

In order for Dave to interact with the LLM, we need four tools:

But if you want to build an LLM app to tinker, hosting the model on your machine might be more cost effective so that you’re not paying to spin up your cloud environment every time you want to experiment. You can find conversations on GitHub Discussions about hardware requirements for models like LLaMA‚ two of which can be found here and here.

Input enrichment and prompt construction tools

Let’s go back to Dave. The LLM can analyze the sequence of words in Dave’s transcript, classify it as an IT complaint, and provide a contextually relevant response. (The LLM’s able to do this because it’s been trained on the internet’s entire corpus, which includes IT support documentation.)

Input enrichment tools aim to contextualize and package the user’s query in a way that will generate the most useful response from the LLM.

Let’s say the LLM assistant has access to the company’s complaints search engine, and those complaints and solutions are stored as embeddings in a vector database. Now, the LLM assistant uses information not only from the internet’s IT support documentation, but also from documentation specific to customer problems with the ISP.

Here’s a list of open source text embedding models. OpenAI and Hugging Face also provide embedding models.

Dave’s contextualized query would then read like this:

// pay attention to the the following relevant information.
to the colors and blinking pattern.

// pay attention to the following relevant information.

// The following is an IT complaint from, Dave Anderson, IT support expert.
Answers to Dave's questions should serve as an example of the excellent support
provided by the ISP to its customers.

*Dave: Oh it's awful! This is the big game day. My TV was connected to my
Wi-Fi, but I bumped the counter and the Wi-Fi box fell off and broke! Now we
can't watch the game.

Not only do these series of prompts contextualize Dave’s issue as an IT complaint, they also pull in context from the company’s complaints search engine. That context includes common internet connectivity issues and solutions.

MongoDB released a public preview of Vector Atlas Search, which indexes high-dimensional vectors within MongoDB. Qdrant, Pinecone, and Milvus also provide free or open source vector databases.

Prompt optimization tools like langchain-ai/langchain help you to compile prompts for your end users. Otherwise, you’ll need to DIY a series of algorithms that retrieve embeddings from the vector database, grab snippets of the relevant context, and order them. If you go this latter route, you could use GitHub Copilot Chat or ChatGPT to assist you.

Efficient and responsible AI tooling

To ensure that Dave doesn’t become even more frustrated by waiting for the LLM assistant to generate a response, the LLM can quickly retrieve an output from a cache. And in the case that Dave does have an outburst, we can use a content classifier to make sure the LLM app doesn’t respond in kind. The telemetry service will also evaluate Dave’s interaction with the UI so that you, the developer, can improve the user experience based on Dave’s behavior.

You can experiment with a tool like zilliztech/GPTcache to cache your app’s responses.

Tools like derwiki/llm-prompt-injection-filtering and laiyer-ai/llm-guard are in their early stages but working toward preventing this problem.

OpenTelemetry, for example, is an open source framework that gives developers a standardized way to collect, process, and export telemetry data across development, testing, staging, and production environments.

Woohoo! 🥳 Your LLM assistant has effectively answered Dave’s many queries. His router is up and working, and he’s ready for his World Cup watch party. Mission accomplished!

Further reading

#reads #nicole choi #github #ai #llm #telemetry