TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Multi AI agent systems using OpenAI's assistants API

227 点作者 metaskills大约 1 年前

14 条评论

yatz大约 1 年前
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.
评论 #40398237 未加载
评论 #40398015 未加载
评论 #40396478 未加载
评论 #40396078 未加载
评论 #40396901 未加载
xrendan大约 1 年前
I&#x27;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.
评论 #40395906 未加载
评论 #40395488 未加载
评论 #40396516 未加载
评论 #40396225 未加载
评论 #40398281 未加载
__loam大约 1 年前
I&#x27;ve not seen any of these &quot;agentic&quot; 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.
behnamoh大约 1 年前
I stay away from such frameworks because:<p>- Writing what I want in Python&#x2F;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&#x27;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&#x27;s API as it&#x27;s yet another wrapper around llama.cpp.
评论 #40397432 未加载
csouzaf大约 1 年前
What&#x27;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?
评论 #40396835 未加载
评论 #40396947 未加载
评论 #40395440 未加载
评论 #40395518 未加载
beoberha大约 1 年前
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&#x27;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.
评论 #40395550 未加载
评论 #40395495 未加载
评论 #40395607 未加载
评论 #40395490 未加载
评论 #40395877 未加载
mentos大约 1 年前
Anyone recommend the best way to use AI to search all of my documents for a project. I&#x27;ve got specifications, blueprints, emails, forms, etc.<p>Would be great to be able to ask it, &#x27;have we completed the X process with contractor Y yet?&#x27;
评论 #40396241 未加载
评论 #40397443 未加载
david_shi大约 1 年前
A bit off topic, but has anyone seen any agent systems focused on improving the agents capabilities with more usage?
jackbravo大约 1 年前
From their linked main page:<p>&gt; 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
ec109685大约 1 年前
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 &#x27;openai&#x27;; const openai = new OpenAI(); async function main() { const stream = await openai.chat.completions.create({ model: &#x27;gpt-4&#x27;, messages: [{ role: &#x27;user&#x27;, content: &#x27;Say this is a test&#x27; }], stream: true, }); for await (const chunk of stream) { process.stdout.write(chunk.choices[0]?.delta?.content || &#x27;&#x27;); } } main(); </code></pre> It’s easy to collect the streaming output and return it all when the llm’s response is done.
评论 #40396273 未加载
评论 #40402387 未加载
评论 #40396266 未加载
tr14大约 1 年前
AI botnet?
spiritplumber大约 1 年前
Ooh, shiny!
moltar大约 1 年前
Bare JS. What is this 2001?
评论 #40400281 未加载
评论 #40395527 未加载
obiefernandez大约 1 年前
My main conversation “loop” at <a href="https:&#x2F;&#x2F;olympia.chat" rel="nofollow">https:&#x2F;&#x2F;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.
评论 #40396398 未加载
评论 #40398744 未加载
评论 #40396335 未加载