Help with Vector Databases: worth it?

[amberhall]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about small local stacks.

I'm especially interested in mistakes worth avoiding.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[tinycontext]

following this because I'm in the same boat.

If you post your exact settings, people here can probably narrow it down pretty fast.

[batchwire]

A couple questions before I guess too hard. What model, what runtime, and roughly what context size?

[southspark]

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.

[amberhall]

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

[dockridge]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost.

[orbitbench6]

My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost.

worth checking the driver first.

[fastfield4]

that fixed it for me too.

If you post your exact settings, people here can probably narrow it down pretty fast.

[amberhall]

A couple things I'd check first. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[orbitbench6]

Thanks, that helps. I ended up in about the same place using MLX. The biggest change for me was simplifying the stack instead of adding one more optimization layer.