Brett England

Well this server was setup a long time ago and as it still working and doing everything that is required of it I see no reason to upgrade just because...

I think this solves your problem https://github.com/zylon-ai/private-gpt/pull/1800 the default is 5m. Increase it. ``` ollama: keep_alive: 30m ```

What ingest_mode are you using? That has a significant impact on the timing. `pipeline` is the fastest https://github.com/zylon-ai/private-gpt/pull/1750. Also there is a problem with ollama fixed in version 0.1.29 ref...

@paul-asvb Index writing will always be a bottleneck. With `pipeline` mode the index will update in the background whilst still ingesting (doing embed work). Depending on how long the index...

/usr/share/perl5/PVE/QemuServer.pm ``` if ($winversion >= 6) { push @$globalFlags, 'kvm-pit.lost_tick_policy=discard'; push @$cmd, '-no-hpet'; } ``` -no-hpet is added as the ostype has a version >= 6 the version becomes the...

I too, ran into this problem - these changes worked for me. https://github.com/dbzoo/ollama/commit/45eb1048496780a78ed07cf39b3ce6b62b5a72e3

Embedding model changes: * ```BAAI/bge-small-en-v1.5``` has a vector size of 384 * ```nomic-embed-text``` has a vector size of 768 If you are using ollama with the default configuration you are...

Its using SQLLite as its using simple (filesystem based) indexes and doc stores. Once this https://github.com/imartinez/privateGPT/pull/1706 is pulled, those things can be moved into Postgres.

I ran into this. This is what worked for me. These commands are executed from the private_gpt clone dir. **Delete the virtual env.** $ poetry env list private-gpt-XXXXX $ poetry...

The act of `poetry install` will [create a virtual environment](https://python-poetry.org/docs/configuration/#:~:text=If%20not%20set%20explicitly%2C%20poetry,root%20directory%20of%20the%20project) Alternatively, you can clear the poetry cache. I ran into poetry problems doing this. After the virtenv is gone go...