Top LLM frameworks may not be as reliable as you think
Nearly a month ago, I decided to add Gemini support to Feeds Fun and did some research on top LLM frameworks — I didn't want to write my own bicycle.
As a result, I found an embarrassing bug (in my opinion, of course) in the integration with Gemini in LLamaIndex. Judging by the code, it is also present in Haystack and in the plugin for LangChain. And the root of the problem is in the Google SDK for Python.
When initializing a new client for Gemini, the framework code overwrites/replaces API keys in all clients created before. Because the API key, by default, is stored in a singleton.
It is death-like, if you have a multi-tenant application, and unnoticeable in all other cases. Multi-tenant means that your application works with multiple users.
For example, in my case, in Feeds Fun, a user can enter their API key to improve the quality of the service. Imagine what a funny situation could happen: a user entered an API key to process their news but spent tokens (paid for) for all service users.
I reported this bug only in LLamaIndex as a security issue, and there has been no reaction for 3 weeks. I'm too lazy to reproduce and report for Haystack and LangChain. So this is your chance to report a bug to a top repository. All the info will be below, reproducing is not difficult.
This error is notable for many reasons:
- The assessment of the criticality of the error depends a lot on taste, experience, and context. For me, in the projects I worked on, this is a critical security issue. However, it seems that this is not critical at all for most current projects that use LLMs. Which leads to some thoughts about mainstream near-LLM development.
- This is a good indicator of a low level of code quality control: code reviews, tests, all processes. After all, this is an integration with one of the major API providers. The problem could have been found in many different ways, but none worked.
- This is a good illustration of the vicious approach to development: "copy-paste from a tutorial and push to prod". To make such a mistake, you had to ignore both the basic architecture of your project and the logic of calling the code you are copying.
Ultimately, I gave up on these frameworks and implemented my own client over HTTP API.
My conclusion from this mess is: you can't trust the code under the hood of modern LLM frameworks. You need to double-check and proofread it. Just because they state that they are "production-ready" doesn't mean they are really production-ready.
Let me tell you more about the bug.
Grainau: hiking and beer at 3000 meters
How it all looks from the ground.
For her vacation, Yuliya decided to show me the beautiful German mountains and took me for a couple of days to Grainau — it's a piece of Bavaria that's almost like Switzerland. At least, it is similar to the pictures of Switzerland that I've seen :-D
In short, it's a lovely place with a measured pace of life. If you need to catch your breath, calm your nerves, and enjoy nature, then this is the place for you. But if you can't live without parties, you'll get bored quickly.
What's there:
- The highest mountain in Germany plus a couple of glaciers.
- There's skiing in winter. If you really need it, you can find a place to ski in summer, but the descent is short, and the lifts are turned off.
- A large clean lake and a couple of smaller ones.
- A huge number of trails for hiking.
- A huge number of waterfalls, streams, and a couple of mountain rivers.
- Restaurants with beer.
- Beautiful fallen trees in the forests, private property, fences, cows with bells, and "racing tractors" (I don't know how to name this phenomenon better, but tractors are moving fast there :-D).
This is briefly, and now in detail.
Migrating from GPT-3.5-turbo to GPT-4o-mini
Guess when I switched models.
Recently OpenAI released GPT-4o-mini — a new flagship model for the cheap segment, as it were.
- They say it works "almost like" GPT-4o, sometimes even better than GPT-4.
- It is almost three times cheaper than GPT-3.5-turbo.
- Context size 128k tokens, against 16k for GPT-3.5-turbo.
Of course, I immediately started migrating my news reader to this model.
In short, it's a cool replacement for GPT-3.5-turbo. I immediately replaced two LLM agents with one without changing prompts, reducing costs by a factor of 5 without losing quality.
However, then I started tuning the prompt to make it even cooler and began to encounter nuances. Let me tell you about them.
My GPTs and prompt engineering
Ponies are doing prompt engineering (c) DALL-E
I've been using ChatGPT almost since the release of the fourth version (so for over a year now). Over this time, I've gotten pretty good at writing queries to this thing.
At some point, OpenAI allowed customizing chats with your text instructions (look for Customize ChatGPT in the menu). With time, I added more and more commands there, and recently, the size of the instructions exceeded the allowed maximum :-)
Also, it turned out that a universal instruction set is not such a good idea — you need to adjust instructions for different kinds of tasks, otherwise, they won't be as useful as they could be.
Therefore, I moved the instructions to GPT bots instead of customizing my chat. OpenAI calls them GPTs. They are the same chats but with a higher limit on the size of the customized instructions and the ability to upload additional texts as a knowledge base.
Someday, I'll make a GPT for this blog, but for now, I'll tell you about two GPTs I use daily:
- Expert — answers to questions.
- Abstractor — makes abstracts of texts.
For each, I'll provide the basic prompt with my comments.
By the way, OpenAI recently opened a GPT store, I'd be grateful if you liked mine GPTs. Of course, only if they are useful to you.
Hello, World!
Nice to meet you, friends!
My name is Aliaksei, but feel free to call me Tiendil — it is my nickname for the last 20 years or so :-)
A few words about me:
- By occupation, I am a software developer, mostly backend, mainly in Python.
- For most of my career, I've been working in game development on big projects and own indie games.
- I like playing games, reading books, and writing long-reads about partially complex topics.
You can find more about me:
- In the about page
- In my GitHub profile: github.com/tiendil
- In the LinkedIn profile: linkedin.com/in/tiendil
This is my first blog post in English, but not the first one in general. I have blogged in Russian for a long time and have always wanted to share my thoughts with the English-speaking world. At last, I found some time to adapt my blog, and here we are!
Most of the future posts will be bilingual (English & Russian). Also, with time, I'll translate my most interesting old posts.
Once again, nice to meet you! Feel free to contact me by any means.