Airbyte
AI
retrieval chatbot tutorial
SHOW HN2023
How HN took it
3 positive, 16 neutral or asking, 1 mixed, 3 critical, out of 23 comments about the project. Thread score 0.00.
Docs: 2 for, 0 againstPrivacy: 1 for, 1 againstExecution: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Well written, practical tutorial with substance
From 3 comments
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…
bnchrch on HNVery 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…
gz5 on HNnice to see a tutorial that recognizes the case where the underlying data can change and the embedding needs to be updated. Any plans to write a tutorial for fine-tuning local…
everythingmeta on HN
Objections
Sending data to Pinecone and OpenAI raises privacy and PII concerns
From 2 comments
I don't know what datasets you guys are working with that have no issues being shared in plain text across three separate proprietary paid services, but this is a nonstarter for…
ramesh31 on HNHow are you thinking about preventing customer PII making it to OpenAI?
r_thambapillai on HN
Pinecone is not open source
From 1 comment
When there are so many awesome FOSS vector databases available, I wonder what motivated the airbyte team to use Pinecone, the one database that is anti-FOSS?
wanderingmind on HN
Too many moving parts for prototyping
From 1 comment
I feel that there are too many moving pieces here especially for prototyping. There was a much more simpler app recently I took a look at on a recent hackernews post :…
anupsurendran on HN
Requests
Support for pgvector as a destination
From 2 comments
have you considered supporting pgvector? I'd imagine that'd be easier since you already have pg as a destination.
mritchie712 on HNhi folks, when will you have pgvector as a destination ? we (https://github.com/arakoodev/edgechains) work with a lot of enterprises and they would not move away from using redis…
sandGorgon on HN
Support for non-OpenAI embedding models
From 2 comments
hi folks, when will you have pgvector as a destination ? we (https://github.com/arakoodev/edgechains) work with a lot of enterprises and they would not move away from using redis…
sandGorgon on HNWhat about the embedding?
zarazas on HN
Direct Pinecone destination support
From 1 comment
A version supporting Pinecone directly is coming soon!
rschwabco on HN
Questions
Can local LLMs like Llama 2 be used instead of OpenAI
From 3 comments
LangChain supports local LLMs like Llama 2 with Ollama (https://github.com/jmorganca/ollama) as of this morning, in both their Python and Javascript versions:…
jmorgan on HN> - OpenAI: you can host an OSS model if you want to Just to confirm: you mean models like Facebook's Llama 2 and variants right? Since OpenAI hasn't released any OSS models.
samspenc on HNcorrect
mtricot on HN
How large a dataset can be submitted
From 2 comments
How large of a dataset can I submit? I have hundreds of thousands of words of text.
johndhi on HNShouldn't have any limits here. Can you let us know how it goes?
mtricot on HN
Alternatives named
Weaviate and other vector databases
From 1 comment
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…
_pdp_ on HN
Ollama for local LLMs
From 1 comment
LangChain supports local LLMs like Llama 2 with Ollama (https://github.com/jmorganca/ollama) as of this morning, in both their Python and Javascript versions:…
jmorgan on HN
Kadoa for data extraction
From 1 comment
You're right, LLMs are really good at extracting and structuring data from third party sources. I've been working on a "Zapier for data extraction" for this reason:…
hubraumhugo on HN