Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

airbyte.com

Post reply on HN
Print view View original

21–30 of 61 posts

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#21

Post by BoorishBears »

bnchrch wrote: post #2

Always so happy to see a tutorial with actual substance. So much on LLMs lately is mostly blog spam for SEO but this actually is information dense and practical. Definitely bookmarking this for tonight. Also really happy to see a bonus section on pulling in data from third party websites. I think this is where LLMs get really interesting. Not only is data much easier to query with these new models, its also orders of…

It's a little weird writing a comment worded like this if you work at Airbyte isn't it?

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#22

Post by BoorishBears »

zby wrote: post #20

So I guess after all those discussions we are still stuck with LangChain for everything to do with LLMs.

I spend all day talking to people shipping AI products and approximately zero of them actually use LangChain.

LangChain doesn't make sense for a ton of reasons, but the top few are the code quality being horrid, the scope being ill defined, and the fact that most of the tasks it does are better done with a prompt that was designed for your exact use case.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#23

Post by kaveet »

BoorishBears wrote: post #21
bnchrch wrote: post #2

Always so happy to see a tutorial with actual substance. So much on LLMs lately is mostly blog spam for SEO but this actually is information dense and practical. Definitely bookmarking this for tonight. Also really happy to see a bonus section on pulling in data from third party websites. I think this is where LLMs get really interesting. Not only is data much easier to query with these new models, its also orders of…

It's a little weird writing a comment worded like this if you work at Airbyte isn't it?

That's disappointing to see, and posted within 10 minutes no less.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#24

Post by mtricot »

_pdp_ wrote: post #17

A fantastic starting point for beginners! Personally, I believe this tutorial provides a solid foundation, but there's so much more to explore. Building something truly effective involves tackling various nuanced situations and special cases. While querying records in Pinecone can sometimes give you the right results, it can also be a bit unpredictable, depending on what and how you query. You might want to check out…

Thanks! I agree with your point. There is a lot of tuning that needs to happen, including context aware splitting and any other kind of transformation before the unstructured data gets indexed. This is one of the big challenge of productionizing LLM apps with external data. So far we are using internally since the team as experience dealing with building these connectors and that becomes a great co-pilot.

The great thing we get by plugging this whole stack together is that we get all the refreshed data as more issues/connectors get created.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#26

Post by mtricot »

mritchie712 wrote: post #10
mtricot wrote: post #7

Earlier quoted context omitted.

Great question :) We want to get to value as fast as possible. I am certain that at some point we will need to go deeper with those integrations and they will likely require to be separate destinations. It will also depend on how they differentiate from each others, we will need more granularity with configurations.

have you considered supporting pgvector? I'd imagine that'd be easier since you already have pg as a destination.

On the roadmap! We want to get more clarity on how to fit the Embedding part in the ELT model. Once we figure it out we will add it to PG.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#27

Post by mtricot »

r_thambapillai wrote: post #18

How are you thinking about preventing customer PII making it to OpenAI?

For the purpose of the tutorial that we built, it really comes down to the type of data that you're using.

If you have data with PII:

One option would be to use Airbyte and bring the data into files/local db rather than directly to the vector store, add an extra step that strips the data from all PII and then configure Airbyte to move the clean file/record to the vector store.

The option that jmorgan mention is relevant here, using a "self-hosted" model.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#28

Post by mtricot »

gz5 wrote: post #15

Very well written and illustrated, thank you. When using a local vector db, what is the security model between my data and Airbyte? For example, do I need to permit Airbyte IPs into my enviro, and is there a VPN type option for private connectivity?

It depends.

Airbyte comes in 3 flavors: OSS, Cloud, Enterprise.

For OSS & Enterprise, data doesn't leave your infra since Airbyte is running in your infrastructure. For Cloud, you would have to allow some IPs to allow us to access your local db.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#29

Post by kingforaday »

amelius wrote: post #25

I like to keep my tools simple so just give me a single AI that can do everything, browse through my data, generate pictures and give me suggestions in my code editor, etc. etc., instead of a different AI for every tool out there.

The next great debate. MonolithicAI vs Micro-serviceAI.

Re: Show HN: Chat with your data using LangChain, Pinecone, and Airbyte

#30

Post by mtricot »

amelius wrote: post #25

I like to keep my tools simple so just give me a single AI that can do everything, browse through my data, generate pictures and give me suggestions in my code editor, etc. etc., instead of a different AI for every tool out there.

Isn't it the dream? Today there is a lot of stack that needs to be built to enable what you're describing. This is actually what we are doing with that post. What foundations do we need to build so that the UX for the end user is what you're describing. Will take some time to get there :)
Post reply on HN