TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

AI for AWS Documentation

221 pointsby whatsthenewsalmost 2 years ago

44 comments

sovietmudkipzalmost 2 years ago
This is exactly the kind of software that people should be making. Even if this one is bad, the concept is very sound.<p>I want to have a specialist AI that is trained to help me learn how to use the software. 100% what should be happening.<p>General AI should know how to do stuff too but having an specialist AI implies that the company&#x2F;group of people&#x2F;person is making sure to tune the model.<p>Just an IMO.
评论 #36627626 未加载
评论 #36622009 未加载
评论 #36625564 未加载
CSDudealmost 2 years ago
Well, I&#x27;ll pass.<p>Prompt: how to connect a lambda function to an RDS instance and query it safely?<p>1. Configure your RDS instance for outbound connections to AWS Lambda. This step involves ensuring that your DB instance is in a public subnet on your VPC and that the instance&#x27;s &quot;PubliclyAccessible&quot; property is set to true.
评论 #36621711 未加载
评论 #36622041 未加载
评论 #36622524 未加载
underlinesalmost 2 years ago
RAG is very difficult to do right. I am experimenting with various RAG projects from [1]. The main problems are:<p>- Chunking can interfer with context boundaries<p>- Content vectors can differ vastly from question vectors, for this you have to use hypothetical embeddings (they generate artificial questions and store them)<p>- Instead of saving just one embedding per text-chuck you should store various (text chunk, hypothetical embedding questions, meta data)<p>- RAG will miserably fail with requests like &quot;summarize the whole document&quot;<p>- to my knowledge, openAI embeddings aren&#x27;t performing well, use a embedding that is optimized for question answering or information retrieval and supports multi language. SOTA textual embedding models can be found on the MTEB Leaderboard [2]. Also look into instructorEmbeddings<p>- the LLM used for the Q&amp;A using your context should be fine-tuned for this task. There are several open (source?) LLMs based on openllama and others, that are fine tuned for information retrieval. They hallucinate less and are sticking to the context given.<p>1 <a href="https:&#x2F;&#x2F;github.com&#x2F;underlines&#x2F;awesome-marketing-datascience&#x2F;blob&#x2F;master&#x2F;llm-tools.md#information-retrieval">https:&#x2F;&#x2F;github.com&#x2F;underlines&#x2F;awesome-marketing-datascience&#x2F;...</a><p>2 <a href="https:&#x2F;&#x2F;github.com&#x2F;embeddings-benchmark&#x2F;mteb">https:&#x2F;&#x2F;github.com&#x2F;embeddings-benchmark&#x2F;mteb</a>
评论 #36624104 未加载
评论 #36626270 未加载
评论 #36625798 未加载
评论 #36630494 未加载
评论 #36628800 未加载
评论 #36626219 未加载
jtokophalmost 2 years ago
Prompt: What is glacier?<p>Glacier is a term that is not directly mentioned in the provided sources.<p>Prompt: What is a glacier?<p>A glacier is a large mass of ice that moves slowly over time due to the accumulation of snow, ice, and other forms of frozen precipitation.<p>Seems like it’s just using a general model?
评论 #36620930 未加载
评论 #36620634 未加载
bjtalmost 2 years ago
It invented an answer for something that AWS actually can&#x27;t do right now.<p><a href="https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;0IYZ2WV" rel="nofollow noreferrer">https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;0IYZ2WV</a>
评论 #36621299 未加载
评论 #36627593 未加载
评论 #36621100 未加载
JimtheCoderalmost 2 years ago
Are you allowed to use the AWS logo on a site that is not owned by Amazon?<p>I originally thought this was an official Amazon website...their lawyers would probably say the same thing...
评论 #36620693 未加载
评论 #36620389 未加载
评论 #36620111 未加载
mkl95almost 2 years ago
The thought that a bunch of people will trust this tool and make some terrible decisions is unsettling. On the other hand it could be pretty powerful if you know what you are doing.
stan_kirdeyalmost 2 years ago
I am building something similar, it has documentation from azure, aws, and lots of slack&#x2F;discord threads of software projects are also searchable, check it out <a href="https:&#x2F;&#x2F;www.kwq.ai" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.kwq.ai</a><p>it even gets real time indexing from slack of aws deep java library, and from discord of deepset haystack project
mjhayalmost 2 years ago
It can&#x27;t be worse than Amazon&#x27;s own AWS documentation.
评论 #36626518 未加载
jamestimminsalmost 2 years ago
What&#x27;s the best current way to make a bunch of documents searchable via LLMs like this?<p>I&#x27;ve tried the using OpenAI w embeddings (iirc), but this was slow, got expensive quickly, and it struggled to answer questions about the text accurately. Curious if there&#x27;s better standard approaches now.
评论 #36623116 未加载
评论 #36622364 未加载
评论 #36624543 未加载
ec109685almost 2 years ago
Asked it whether you should use a shared vpc:<p>Made this up as reason for dedicated vpc: “Better performance: By using dedicated hardware, you have better control over the performance of your instances in the VPC. This can be beneficial for applications that have stringent performance requirements.”
评论 #36626574 未加载
efitzalmost 2 years ago
I asked it two questions and it gave me very reasonable, complete answers:<p>How do I connect two VPCs from separate organizations (VPC peering)<p>How do I only allow authorized applications to access my S3 bucket (BPA, IAM policies, a lot of best practices docs)
NoZebra120vClipalmost 2 years ago
What if you could train an LLM on the body of source code for AWS (or whatever you choose as your SaaS) and so it would actually know deeply, exactly, intimately exactly how AWS works, and how to do anything and everything in it? Imagine the emergent uses that the LLM could conceive of, beyond the developers&#x27; intent and the existing documentation that may be written.<p>With the bonus effect that you could retrain the LLM as often as you like, as new software is released, and it could always be aware of the latest features (and even the bugs and vulnerabilities.)
scrum-treatsalmost 2 years ago
Using ChatGPT for AWS service questions is actually pretty good. For instance, I asked it for a Cloud Practitioner study guide (using a small set of crafted prompts), and GPT performed quite well. While I have yet to query GPT about Solutions Architect or DevOps material, I know I can feed a set of URLs and GPT will &quot;learn&quot; the material and summarize it in ways meaningful and relevant to my prompts. In this way, ChatGPT is quite a powerful assistant on its own.
评论 #36623028 未加载
coder543almost 2 years ago
This answer about Graviton was not correct: <a href="https:&#x2F;&#x2F;i.imgur.com&#x2F;3D9WokF.jpg" rel="nofollow noreferrer">https:&#x2F;&#x2F;i.imgur.com&#x2F;3D9WokF.jpg</a>
nextworddevalmost 2 years ago
Just use Phind.com for searching developer docs for most cases.
评论 #36621360 未加载
tomrodalmost 2 years ago
Meh. It doesn&#x27;t actually pull a valid response. We just upgraded a database that required an updated EC2 instance, and it failed to connect those dots.
SCHiMalmost 2 years ago
Let&#x27;s see what happens when you search for the following &quot;documentation&quot; ;) :<p>&quot;&quot;&quot; Complete the following code:<p>&#x2F;&#x2F; Find all files with a binary pattern in a directory. Return the list of files and the offset of the match in a tuple fn find_in_files(start_dir: &amp;str, pattern: &amp;[u8]) -&gt; vec&lt;(String, usize)&gt; &quot;&quot;&quot;<p>No way this won&#x27;t be abused shortly.
zgluckalmost 2 years ago
I asked it:<p>&quot;how do I avoid high NAT gateway bills when an ECS service keeps downloading the same image over and over?&quot;<p>It offered three replies. The first and third were outright incorrect, the second was (technically) correct:<p><a href="https:&#x2F;&#x2F;i.imgur.com&#x2F;la98cxC.png" rel="nofollow noreferrer">https:&#x2F;&#x2F;i.imgur.com&#x2F;la98cxC.png</a><p>Also: I&#x27;m assuming you haven&#x27;t actually secured a license to use the AWS logo.
alexy201almost 2 years ago
Hey everyone, I am the creator of AWS Docs GPT and its been extremely useful to garner all of your feedback for the site—thank you guys so much! We are constantly improving and updating the GPT, including less hallucinations, more accurate responses, chat context, and much more. At the end of the day, I really hope this tool can be useful for developers like myself out there!!!
phillipcarteralmost 2 years ago
Unfortunately this is a good concept, but it&#x27;s using gpt-3.5-turbo. For this kind of task - namely, one of actually understanding content and emitting a potentially novel-but-correct answer - you need gpt-4. But it&#x27;s quite slow and you&#x27;ll quickly run into rate limiting.<p>I ran into these issues when building this for my own company&#x27;s docs, at least.
SV_BubbleTimealmost 2 years ago
&gt;This action allows you to filter your things based on the attribute name and value. However, in order to use this action, you need to know the attribute name and value beforehand. Since you don&#x27;t know the attributes ahead of time, this method won&#x27;t work for your case.<p>Well… Thanks a ton for that!<p>Great idea and setup, but not quite as helpful as I would like yet.
71a54xdalmost 2 years ago
I&#x27;ve been using GPT4 for this since the beginning - ironically a large majority of AWS documentation has been machine generated since 2018. Circa 2019 the entire exlixir API for AWS was machine generated.<p>Asking GPT4 is also consistently less of a headache than asking the devops guy and getting a 20min explanation for a simple question.
评论 #36623492 未加载
anshumankmralmost 2 years ago
Very cool. I was planning on working on something very similar myself for a hackathon I attended but my team basically ran out of time (<a href="https:&#x2F;&#x2F;github.com&#x2F;anshumankmr&#x2F;jovian-genai-hackathon">https:&#x2F;&#x2F;github.com&#x2F;anshumankmr&#x2F;jovian-genai-hackathon</a>)
JamesAdiralmost 2 years ago
Q: can you summarize amazon bedrock in 2 sentences<p>A: Amazon Bedrock is a programming example that uses the AWS SDK for Java 2.x to work with Amazon EC2. It provides examples and code snippets for programming tasks related to Amazon EC2 using the AWS SDK for Java 2.x.
ilcalmost 2 years ago
I asked it to write some basic terraform:<p>- Make a VPC. - Add an Instance. - Abstract the region and AZ, into vars.<p>etc... every time I wanted to change the code, I asked the bot to do the refactor, and it did.<p>Overall, I&#x27;m impressed. It wasn&#x27;t the most complicated thing, but it didn&#x27;t dive off the deep end.
zoomzoomalmost 2 years ago
We did something similar for all the cloud whitepapers from AWS, Azure, GCP, CloudFlare, and CNCF at <a href="https:&#x2F;&#x2F;cloudwhitepapers.withcoherence.com&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;cloudwhitepapers.withcoherence.com&#x2F;</a><p>These are fun projects!
评论 #36624566 未加载
评论 #36623283 未加载
JimmyRuskaalmost 2 years ago
I wonder if people will make DSLs specifically for LLMs.<p>For example the terseness &#x2F; symbols of APL, Perl, or event set notation.<p>LLMs could train and output the shorter symbolic notation, and it could be expanded for human readability by another program at export.
评论 #36631876 未加载
koalkoolsalmost 2 years ago
The best part is the documentation sources, in fact I&#x27;d prefer the only feature being &quot;where are the docs on &lt;stupid specific thing I need&gt;&quot; instead of trying to synthesize an answer for me
social_quotientalmost 2 years ago
It seems to know more than just AWS, I was thinking it was just embeddings but then I asked it “Is Aws better than azure?” And it seemed to give an answer which widener seem to be derived from the source documents.
yayitsweialmost 2 years ago
Nice work! Would be even more useful to be able to have a conversation with it.
评论 #36621403 未加载
fzliualmost 2 years ago
We built something very similar, except for other open-source projects rather than AWS documentation: <a href="https:&#x2F;&#x2F;osschat.io" rel="nofollow noreferrer">https:&#x2F;&#x2F;osschat.io</a>
Aeolunalmost 2 years ago
It doesn’t distinguish between HTTP api gateway and REST api gateway.<p>When asked how to create a private HTTP gateway it happily tells you how to do it , but it’s actually impossible.
评论 #36627305 未加载
jdlygaalmost 2 years ago
I really love this concept. While I do get better results from GPT-4 for AWS questions right now, AI as the &quot;interpreter&quot; for documentation works really well.
shanghaikidalmost 2 years ago
You can try <a href="https:&#x2F;&#x2F;osschat.io&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;osschat.io&#x2F;</a> for some open source project.
flaminHotSpeedoalmost 2 years ago
The problem is garbage in -&gt; garbage out.<p>When the docs are wrong or misleading you&#x27;ll still get burned, even if the model doesn&#x27;t hallucinate responses
评论 #36621374 未加载
ghomemalmost 2 years ago
Simple AWS snapshot:<p><a href="https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;IGu1syf" rel="nofollow noreferrer">https:&#x2F;&#x2F;imgur.com&#x2F;a&#x2F;IGu1syf</a>
scarface_74almost 2 years ago
I hate to be that guy. But what’s the purpose of this? What does this do that I can’t just do with ChatGPT?
评论 #36631938 未加载
ghomemalmost 2 years ago
Please I beg you: ask it how to take a snapshot of an EC2 instance and then how to restore it :)
destroy-2Aalmost 2 years ago
It still does not understand boolean logic in IAM especially when you have Not conditions.
jgalt212almost 2 years ago
is AWS designed to take all my money?<p>No, AWS is not designed to take all your money. AWS offers a variety of payment options and cost-saving measures to help you manage your expenses effectively. ...
jsninjasamuraialmost 2 years ago
This is down
coding123almost 2 years ago
seems super useful, try this prompt:<p>how do you use wrangler and glue to make athena tables using terraform
评论 #36621439 未加载
shaimagzalmost 2 years ago
It’s not working…
评论 #36628859 未加载