Assistants API is promising, but earlier versions have many issues, especially with how it calculates the costs. As per OpenAI docs, you pay for data storage, a fixed price per API call, + token usage. It sounds straightforward until you start using it.<p>Here is how it works. When you upload attachments, in my case a very large PDF, it chunks that PDF into small parts and stores them in a vector database. It seems like the chunking part is not that great, as every time you make a call, the system loads a large chunk or many chunks and sends them to the model along with your prompt, which inflates your per request costs to 10 times more than the prompt + response tokens combined. So, be mindful of the hidden costs and monitor your usage.
I'd be interested in knowing if anyone is seriously using the assistants API, it feels like such a lock in to OpenAIs platform when your can alternatively just use completions that are much more easily interchanged.
I've not seen any of these "agentic" systems be all that useful in practice. Complicated chain of software where a lot can wrong at any step, and the probability of failure explodes when you have many steps.
I stay away from such frameworks because:<p>- Writing what I want in Python/other-lingo gives me much more customizability than these frameworks offer.<p>- No worries about the future plans of the repo and having to deal with abandonware.<p>- No vendor lock in. Currently most repos like this focus on OpenAI's models, but I prefer to work with local models of all kinds and any abstraction above llama.cpp or llama-cpp-python is a no-no for me.<p>The last point means I refuse to build on top of ollama's API as it's yet another wrapper around llama.cpp.
What's the use cases people are using Multi AI Agents to solve problems that deliver real value? Someone has something with your hands on right now?
From the website linked in the readme:<p>“A lot of research has been doing in this are and we can expect a lot more in 2024 in this space. I promise to share some clarity around where I think this industry is headed. In personal talks I have warned that multi-agent systems are complex and hard to get right. I've seen little evidence of real-world use cases too”<p>These assistant systems fascinate me, but I just don’t have the time and energy to set something up. I was going to ask if anyone had a good experience with it, but the above makes it sound like there’s not much hope at the moment. Curious what other people’s experience are.
Anyone recommend the best way to use AI to search all of my documents for a project. I've got specifications, blueprints, emails, forms, etc.<p>Would be great to be able to ask it, 'have we completed the X process with contractor Y yet?'
From their linked main page:<p>> In my opinion, exploration of multi-agent systems is going to require a broader audience of engineers. For AI to become a true commodity, it needs to move out of the Python origins and into more popular languages like JavaScript , a major fact on why I wrote Experts.js.<p>I wholeheartedly agree
I don’t understand the comment about server send events not being async friendly.<p>What is unfriendly about this?<p><pre><code> import OpenAI from 'openai';
const openai = new OpenAI();
async function main() {
const stream = await openai.chat.completions.create({
model: 'gpt-4',
messages: [{ role: 'user', content: 'Say this is a test' }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content || '');
}
}
main();
</code></pre>
It’s easy to collect the streaming output and return it all when the llm’s response is done.
My main conversation “loop” at <a href="https://olympia.chat" rel="nofollow">https://olympia.chat</a> has tool functions connected to “helper AIs” for things such as integrating with email. It lets me minimize functions on the main loop and actually works really well.