langtrace VS self-hosted

+1 to this. Langtrace core maintainer here. We are building a SDK and a client for automatic instrumentation of LLM based applications using OTEL standards. The OpenLLMetry team along with the CNCF OpenTelemetry working group has been doing some great work standardizing semantic naming conventions and we are starting to adopt the same set of standards.

[1] https://github.com/Scale3-Labs/langtrace

Ola and Karthik here. We are working on Langtrace(https://github.com/Scale3-Labs/langtrace), an open source, open telemetry based SDK and monitoring/evaluations client for LLM based applications. The SDK generates OTEL standard spans and traces for popular LLMs like OpenAI, Anthropic and Cohere, popular frameworks like Langchain and LlamaIndex and vectorDBs like ChromaDB and Pinecone.

The LLM monitoring/evaluations space has seen a number of products off late, both open source and closed source ones. But, a couple of things we have observed are: lack of standard spans and traces that creates vendor lock in, different tools are optimized for solving different pain points - Evaluations, Prompt management, Datasets etc.

We believe that adopting open telemetry(OTEL) standard tracing not only lets teams use our SDK without having to switch their observability client, but will also enable developers to develop tooling for any custom needs such as capturing datasets, prompts, evaluations etc.

A quick note on what we have built so far:

[1] We have a Python and a TypeScript SDK and we have broken down the support for the LLM layer into 3 groups, LLMs, Frameworks and VectorDBs. Our SDKs are open telemetry compatible, can be installed and used independently and we also provide an option to pass custom exporters to export the traces and spans to any observability tool of your choice.

[2] An observability client that is hyper optimized for solving the unique pain points and challenges that come with LLM based apps like Evaluations, prompt iteration, datasets etc. We are SOC2 compliant and the client can also be self hosted if you have strict data privacy and protection requirements.

[3] Both the SDK and the client are fully open source. We are leaning on the community to try it out and provide feedback.

A note about Open Telemetry semantic conventions for LLMs - We would like to converge on standard names for trace attributes that follow the OTEL rules and are looking for feedback from experts here - https://github.com/Scale3-Labs/langtrace/discussions/71

We recognize that this project is early and there is a lot of room for improvement. Would love to hear your thoughts and feedback. Thanks!

Links:

[1] https://langtrace.ai/

[2] https://github.com/Scale3-Labs/langtrace

[3] https://docs.langtrace.ai/introduction

[1] We have a Python and a TypeScript SDK and we have broken down the support for the LLM layer into 3 groups, LLMs, Frameworks and VectorDBs. Our SDKs are open telemetry compatible, can be installed and used independently and we also provide an option to pass custom exporters to export the traces and spans to any observability tool of your choice.

[2] An observability client that is hyper optimized for solving the unique pain points and challenges that come with LLM based apps like Evaluations, prompt iteration, datasets etc. We are SOC2 compliant and the client can also be self hosted if you have strict data privacy and protection requirements.

[3] Both the SDK and the client are fully open source. We are leaning on the community to try and provide us with feedback.

A note about Open Telemetry semantic conventions for LLMs. We would like to converge on standard names for trace attributes that follow the OTEL rules and are looking for feedback from experts here - https://github.com/Scale3-Labs/langtrace/discussions/71

We recognize that this project is early and there is a lot of room for improvement. Would love to hear your thoughts and feedback. Thanks!

Links:

[1] https://langtrace.ai/

I was responding to the One of the Sentry inconvenience is self-hosting: it relies on so many services it can be very complicated to maintain part, and also reminding readers that if they, too, hate companies that rug-pull their open source licenses, there is a band-aid for both parts

Compare https://github.com/getsentry/self-hosted/blob/9.1.2/docker-c... with https://github.com/getsentry/self-hosted/blob/24.4.2/docker-... for what life used to be like for running Sentry on-prem. It was awesome

It would take a ton of work to dig up the actual memory and CPU requirements of each one, but rest assured they're not zero, so every one of those services eats ram and requires TLC when, not if, they shit themselves. So, more parts == more headaches with all other things being equal

Then, I deeply appreciate that there are a whole spectrum of reactions to the various licensing schemes in use nowadays, and a bunch of folks don't care. I care, though, because I have gotten immense value from open source projects, and have contributed changes back to quite a few. It has been my life experience that any of those "source available" licenses usually are very hostile toward making local builds and if I can't build it to match how prod goes, then I can't test my fixes in my environment and then I can't contribute the PR with any faith

This is the point where I will point out that you can self-host Sentry free of charge :) https://develop.sentry.dev/self-hosted/

Sentry can be self hosted: https://develop.sentry.dev/self-hosted/

The people we're concerned about are not the hundreds of thousands of Sentry users, including those that self-host.

We're concerned about people who have taken the software for the purposes of competing directly against us, that hinders our ability to monetize the work. Monetizing the work helps us continue improving the software and distribute it for free use, benefitting those aforementioned real users (e.g. https://github.com/getsentry/self-hosted).

> I mean no slander or disrespect to anyone involved, but there was a DataDog alternative posted sometime in the last few weeks that had a docker-compose with like 15 containers in it.

Reminds me of Sentry: https://develop.sentry.dev/self-hosted/

This is their example docker-compose for self-hosting: https://github.com/getsentry/self-hosted/blob/master/docker-...

It has:

  - exim4 (smtp)

> What should people use?

I recall Apache Skywalking being pretty good, especially for smaller/medium scale projects: https://skywalking.apache.org/

The architecture is simple, the performance is adequate, it doesn't make you spend days configuring it and it even supports various different data stores: https://skywalking.apache.org/docs/main/v9.0.0/en/setup/back...

The problems with it are that it isn't super popular (although has agents for most popular stacks), the docs could be slightly better and I recall them also working on a new UI so there is a little bit of churn: https://skywalking.apache.org/downloads/

Still better versus some of the other options when you need something that just works instead of spending a lot of time configuring something (even when that something might be superior in regards to the features): https://github.com/getsentry/self-hosted/blob/master/docker-...

Sentry is just the first thing that comes to mind (OpenTelemetry also isn't simpler due to how much it tries to do), but compare its complexity to Skywalking: https://github.com/apache/skywalking/blob/master/docker/dock...

I wish there was more self-hosted software like that out there, enough to address certain concerns in a simple way on day 1 and leave branching out to more complex options like OpenTelemetry once you have a separate team for that and the cash is rolling in.

Sounds interesting!

Will you compare with qryn? Self-hosted sentry?

qryn.metrico.in/

https://develop.sentry.dev/self-hosted/

I haven't done it in years, but technically sentry is able to be self hosted https://github.com/getsentry/self-hosted