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)

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.

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?

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 me.

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 options like Weaviate, or even delve into the world of sparse indexes for an added layer of complexity. The models themselves have their own quirks too. For example, GPT3.5 Turbo tends to respond well when given clear instructions at the beginning of the context, while GPT4, although more flexible, still comes with its own set of challenges. Despite this, I'm genuinely excited about the push to highlight the potential of LLM applications (more of that, please!). Just remember, while tutorials like this are a great step, achieving seamless results might require some hands-on experience and learning along the way.

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 or pgvector even as their vector store. Is there a way where we can leverage that ?

Second, for a LOT of enterprises, they want to use non-openai embedding models (minilm, GTE, BGE), will you support that. For e.g. in Edgechains we natively support BGE and minilm. Would you be able to support that ?

This is cool, I would like access to the code contents as well, not just the issue. Is that possible with airbyte? If so, how?

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 : https://news.ycombinator.com/item?id=36894142

They still have work to do with different connectors (e.g. PDF etc) but the realtime simple document pipeline is what helps a lot.

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?

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

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?

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.

How large of a dataset can I submit? I have hundreds of thousands of words of text.

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

nice 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 models?

Why is the OpenAI from the article title missing?