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

LlamaIndex raises $8.5M seed round, led by Greylock Partners

medium.com

Post reply on HN
Print view View original

11–19 of 19 posts

Re: LlamaIndex raises $8.5M seed round, led by Greylock Partners

#16

Post by batou069 »

swyx wrote: post #5

alright HN - langchain and llamaindex - they are not-competitors in that you can use either standalone or you can use both together - who is using which and why?

AFAIK llamaindex is built on langchain to save you a lot of time and lines of code, and also constantly adding new stuff (as does langchain) as dataloaders, different indeces, all kinds of cool stuff like nodes pre and post processing, reranking, query optimization, query decomposition, custom query engines and whatnot. you can still use langchain, for example when using agents or more realistically when going the route of textsplitting by token size. I'd say its complementary, do whatever you can do with llama_index and whatever you cant use langchain.

Re: LlamaIndex raises $8.5M seed round, led by Greylock Partners

#17

Post by towelpluswater »

swyx wrote: post #5

alright HN - langchain and llamaindex - they are not-competitors in that you can use either standalone or you can use both together - who is using which and why?

I'm using LlamaIndex way more these days, mostly because the big use cases from enterprise orgs is around using their own data in novel ways. it makes much more sense for backend tasks.

that said, while there's some clear crossover between the two, i find myself using langchain for things like huggingface embeddings for local models, and other helpers that work well with llamaindex.

somewhat akin to a data warehouse and all the techniques and abstractions that go into modeling it for non-technical end users, llamaindex makes a lot of that much easier to work with as a developer. structured and unstructured data can be indexed side by side, and the auto retriever functions they've recently built out work really well once you've got data indexed in a sensible way. our next step is to put a simple UI on top of it all with filters (like a dashboard) that pass metadata filters to the llamaindex autoretriever.

these patterns may not be exactly right today, but I don't see any others focusing on this area. just throwing all of your docs haphazardly into an index and calling it a day is no different than tossing all your data into a single database schema without any rhyme or reason, and hoping your dashboards can do 'magic' on top of it.

Re: LlamaIndex raises $8.5M seed round, led by Greylock Partners

#18

Post by towelpluswater »

batou069 wrote: post #16
swyx wrote: post #5

alright HN - langchain and llamaindex - they are not-competitors in that you can use either standalone or you can use both together - who is using which and why?

AFAIK llamaindex is built on langchain to save you a lot of time and lines of code, and also constantly adding new stuff (as does langchain) as dataloaders, different indeces, all kinds of cool stuff like nodes pre and post processing, reranking, query optimization, query decomposition, custom query engines and whatnot. you can still use langchain, for example when using agents or more realistically when going the ro…

after using both of them for awhile, i see them as complementary as well. i'm more likely to use langchain for execution of tasks, and llamaindex for backend optimization and building out 'embeddings data pipelines'. if i need something from langchain in llamaindex, i can bring it in, and vice versa.

the more folks experiment with this stuff, i think they'll see where it all comes together, and where some of the crossover is. but given how quickly everything changes in this space, i'm glad there's a clear focus from each team on their core strengths rather than throwing the kitchen sink of new papers at it.

Post reply on HN