Tag: Qdrant

I check the new path from worker to search so that a long capture is not only processed, but also appears cleanly as one result.

I rebuilt the worker so that one capture produces multiple token chunks, each chunk is embedded individually, and storage in Qdrant remains completely isolated.

The migration to bge-m3 brought an 8192-token limit. Nevertheless, I deliberately set the chunk limit to 1500 tokens to preserve semantic focus.

I had already implemented text splitting, but the context error kept appearing. Only when I accounted for the token budget and special tokens did the cause become clear.

I wanted to inspect Qdrant data in the browser without making the database public. Locally I use Traefik; in production I open only an SSH tunnel and keep Qdrant internal.

Before launch, I reviewed my architecture for more than scaling. I also examined implicit security assumptions and found two small gaps that could quickly become costly in production.