Resolving Memory Leaks in Qdrant Vector Database Connections

Question

Hi guys, hope everything is going well. I'm having this issue where after asking my model a couple of questions, it returns this error and won't run again until I restart the system:

Plain Text

Both client and aclient are provided. If using `:memory:` mode, the data between clients is not synced.

My guess is that there may be a memory leak somewhere within the system, likely within the connection to my Qdrant vector database. The main solution I've been seeing is to try implementing AsyncQdrantClient but I'm not sure where to add it in - is this an issue that's occurring directly within my RAG workflow or does it go deeper and should be applied in a different section? Any advice would be appreciated!

Logan M · Answer

Are you using any local models in your setup? Could be a pytorch issue?

Mitch 🪬 · Answer

No we are using gpt 4o

Mitch 🪬 · Answer

Our stack is Qdrant for vector storage and elastic search for document storage, if that helps

Logan M · Answer

Hmm. Well, the issue is somewhere, but its unrelated to that messageAny other clues? Or if you can share your code at all or link a repo, that would greatly help

Mitch 🪬 · Answer

We kept testing and it looks like Qdrant actually was the issue. We implemented QdrantVectorStore() instead of just running get_vector_store() from app.storage and it seems to now be running with no issues again.

Thanks for your response, will let you know if we run into an issue again!

Find answers from the community

Resolving Memory Leaks in Qdrant Vector Database Connections