loki VS Typesense

I also needed to make a small patch to Promtail to make this work: https://github.com/grafana/loki/pull/10256

We don't pull logs, we forward logs to a centralized logging service.

Over the past few months, I've been spending a lot of time creating dashboards on Grafana using Loki for MyUnisoft (the company I work for).

For log systems you generally don't migrate data. Logs lose value over time. What you want to do is to go ahead and start ingesting data into the new system (OpenObserve in this case) and slowly, the data in the old system will become stale and then you can retire it. However if you need to export logs anyhow, there is no straightforward way in loki to do this. You could run a script to query loki and export it to a file. If found this thread with a sample script - https://github.com/grafana/loki/issues/409

That snap is woefully out of date. The upstream repo was recently updated to 2.8.2, but the snap stable channel has 2.4.1 from 18 months ago. https://github.com/grafana/loki/releases/tag/v2.8.2

Loki

I installed promtail a few weeks back and I ran into this bug, that has been outstanding for months: https://github.com/grafana/loki/issues/8663 (e.g. a fix had been written but had not been released):

Due to a buffering issue, Loki would exit in case of configuration error without printing any error message or anything at all

There is definitely something weird about how the project is run.

There are actually plenty of non-ES products that are way easier to integrate and tune (and get better results with less effort).

- Typesense (https://github.com/typesense/typesense)

- Algolia

- Google Programmable Search Engine (https://programmablesearchengine.google.com/about/)

Typesense - Open Source Alternative to Algolia

If you like your penny take a look at Typesense https://typesense.org/ - nothing to complain here. Especially nothing complain about pricing.

I work on Typesense [1] (historically considered an open source alternative to Algolia).

We then launched vector search in Jan 2023, and just last week we launched the ability to generate embeddings from within Typesense.

You'd just need to send JSON data, and Typesense can generate embeddings for your data using OpenAI, PaLM API, or built-in models like S-BERT, E-5, etc (running on a GPU if you prefer) [2]

You can then do a hybrid (keyword + semantic) search by just sending the search keywords to Typesense, and Typesense will automatically generate embeddings for you internally and return a ranked list of keyword results weaved with semantic results (using Rank Fusion).

You can also combine filtering, faceting, typo tolerance, etc - the things Typesense already had.

[1] https://github.com/typesense/typesense

[2] https://typesense.org/docs/0.25.0/api/vector-search.html

For something small with a minimal footprint, I'd recommend Typesense. https://github.com/typesense/typesense

I haven’t used Publish, but I’d assume you could use something like https://typesense.org/ to index and search the vault.

A cheaper option would be to use https://typesense.org. You can use DynamoDb streams to automatically load records. It has worked well for me.

Try tigris | typesense for faster search

I’m also checking out Typesense as a possibility for replacing Elastic: https://typesense.org/