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

1–10 of 61 posts

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

#1

Post by mtricot »

Hi HN,

A few of our team members at Airbyte (and Joe, who killed it!) recently played with building our own internal support chat bot, using Airbyte, Langchain, Pinecone and OpenAI, that would answer any questions we ask when developing a new connector on Airbyte.

As we prototyped it, we realized that it could be applied for many other use cases and sources of data, so... we created a tutorial that other community members can leverage [http://airbyte.com/tutorials/chat-with-your-data-using-opena...] and the Github repo to run it [https://github.com/airbytehq/tutorial-connector-dev-bot]

The tutorial shows: - How to extract unstructured data from a variety of sources using Airbyte Open Source - How to load data into a vector database (here Pinecone), preparing the data for LLM usage along the way - How to integrate a vector database into ChatGPT to ask questions about your proprietary data

I hope some of it is useful, and would love your feedback!

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

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

#2

Post by bnchrch »

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 magnitude easier to ingest from traditionally malformated sources.

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

#3

Post by mtricot »

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…

Let me know how that works out for you and if you would add anything to this tutorial!

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

#4

Post by jmorgan »

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:

https://python.langchain.com/docs/integrations/llms/ollama

This can be a great option if you'd like to keep your data local versus submitting it to a cloud LLM, with the added benefit of saving costs if you're submitting many questions in a row (e.g. in batches)

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

#5

Post by swyx »

congrats team!

what was the thinking behind choosing to support "Vector Database (powered by LangChain)" instead of directly supporting Pinecone Chroma et al directly as you do in the other destinations? when is direct integration the right approach vs when is it better to have an (possibly brittle, but faster time to market) integration of an integration?

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

#7

Post by mtricot »

swyx wrote: post #5

congrats team! what was the thinking behind choosing to support "Vector Database (powered by LangChain)" instead of directly supporting Pinecone Chroma et al directly as you do in the other destinations? when is direct integration the right approach vs when is it better to have an (possibly brittle, but faster time to market) integration of an integration?

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.

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

#9

Post by mtricot »

jmorgan wrote: post #4

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: https://python.langchain.com/docs/integrations/llms/ollama This can be a great option if you'd like to keep your data local versus submitting it to a cloud LLM, with the added benefit of saving costs if you're submitting many questions in a row (e.g. in batch…

I am sure we can build something around that. Going to take a look at it. Thanks for mentioning it.

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

#10

Post by mritchie712 »

mtricot wrote: post #7
swyx wrote: post #5

congrats team! what was the thinking behind choosing to support "Vector Database (powered by LangChain)" instead of directly supporting Pinecone Chroma et al directly as you do in the other destinations? when is direct integration the right approach vs when is it better to have an (possibly brittle, but faster time to market) integration of an integration?

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.
Post reply on HN