Find answers from the community

Updated last year

Hi all I ve got a qdrant db where i

Hi all!.. I've got a qdrant db, where i stored some docs using Langchain. Im trying to load and use them with Llama, without much luck. Both seems to save content in the db in a different way. Llama seems to use the 'text' payload property to store the text, and langchain 'page_content'. How could one query langchain's way of storing the text with llama?

12 comments

kkittenkill

If i kinda change this: https://github.com/jerryjliu/llama_index/blob/main/llama_index/vector_stores/qdrant.py#L197

kkittenkill

To .get('page_content') it kinda works. 😛

LLogan M

You could definitely subclass to adjust which fields it works with

LLogan M

there's not really an easy cross-compatible solution here I guess 🤔

LLogan M

besides subclassing and writing your own query method

kkittenkill

What do you mean by subclass?

kkittenkill

inherit the thing, and re-write the function i need?

kkittenkill

Just saw you comment here: https://github.com/jerryjliu/llama_index/issues/6567

kkittenkill

Not sure if its the same thing i was loooking, but your suggestion looks to be quite similar. 🙂

LLogan M

Yea, by subclass I mean inherit

Plain Text

class KittenKillVectorStore(QdrantVectorStore):
  def query(..):
     # custom query code

LLogan M

something like that haha

kkittenkill

👍

Add a reply