Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update: Vector database from pgvector to qdrant #59

Closed
1 of 6 tasks
amindadgar opened this issue May 13, 2024 · 0 comments · Fixed by #60
Closed
1 of 6 tasks

Update: Vector database from pgvector to qdrant #59

amindadgar opened this issue May 13, 2024 · 0 comments · Fixed by #60
Assignees
@amindadgar

Comments

@amindadgar
Copy link
Member

amindadgar commented May 13, 2024 •
edited
Loading

As we faced the problem on our ETL pipelines for hivemind, we were required to change the database to qdrant

The details of the issue is described here: TogetherCrew/airflow-dags#151

The tasks on hivemind-bot side would be the following

  • Update PGVectorAccess to be QDrantVectorAcess
  • Remove the save_documents of PGVectorAccess since we would be now using another pipeline on ETLs
  • Update the load_index of PGVectorAccess to load index for qdrant database
  • Update BaseSummarySearch to use qdrant vector database index
  • Do manual merging of discord summary data on qdrant database
  • Update the initial and secondary search of discord and discourse to use the qdrant database (rewrite if required)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@amindadgar amindadgar

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

feat: Added qdrant support for BaseEngine and added MediaWiki RAG! TogetherCrew/hivemind-bot
1 participant
@amindadgar