For those building applications with Langfuse and Clickhouse - do you like these products? I get the odd request to do an AI thing, and my previous experience with LLM wrappers convinced me to stay away from them (Langchain, Llamaindex, Autogen, others). In some cases they were poorly written, and in other ways the march of progress rendered their tooling irrelevant fairly quickly. Are these better?
ClickHouse acquires Langfuse
91–99 of 99 posts
Re: ClickHouse acquires Langfuse
#92Earlier quoted context omitted.
Your notes aren't very good. They're not a time series database company, they're a columnar database company. But yeah the LLM bit is weird, database companies _always_ feel like charlatans when it comes to LLMs.
ClickHouse effectively has a number of personas. Time series is one of them, and ClickHouse has steadily absorbed market share from pure play time series databases over the last few years. Other personas include real-time observability backend (the single biggest use case in my experience) as well as real-time data lake engine. Time series support, column storage, and real-time response are key underlying capabilitie…
always nice to see a database ceo be "one of us" and/or "write like a real human being".
Re: ClickHouse acquires Langfuse
#93Earlier quoted context omitted.
It was not a fire sale I'm pretty sure. Langfuse has been consistently growing, they publish some stats about sdk usage etc so you can look that up. They also say in the announcement that they had a term sheet for a good series a. I think the team just took the chance to exit early before the llm hype crashes down. There is also a question of how big this market really is they mostly do observability for chatbots but…
I don’t know about that. I looked at them a couple of months back for prompt management and they were pretty behind in terms of features. Went with PromptLayer
Re: ClickHouse acquires Langfuse
#94For those building applications with Langfuse and Clickhouse - do you like these products? I get the odd request to do an AI thing, and my previous experience with LLM wrappers convinced me to stay away from them (Langchain, Llamaindex, Autogen, others). In some cases they were poorly written, and in other ways the march of progress rendered their tooling irrelevant fairly quickly. Are these better?
We like Langfuse for observability via OpenTelemetry. Prompt management is too basic for our needs.
Re: ClickHouse acquires Langfuse
#95Earlier quoted context omitted.
ClickHouse effectively has a number of personas. Time series is one of them, and ClickHouse has steadily absorbed market share from pure play time series databases over the last few years. Other personas include real-time observability backend (the single biggest use case in my experience) as well as real-time data lake engine. Time series support, column storage, and real-time response are key underlying capabilitie…
Altinity isn't just a vendor, it's THE ClickHouse vendor before ClickHouse became a company. https://altinity.com/blog/big-news-in-the-clickhouse-communi... always nice to see a database ceo be "one of us" and/or "write like a real human being".
Re: ClickHouse acquires Langfuse
#96Earlier quoted context omitted.
Anecdotally, from the AI startup scene in London, I do not know folks who swear by Langfuse. Honestly, evals platforms are still only just starting to catch on. I haven't used any tracing/monitoring tools for LLMs that made me feel like, say, Honeycomb does.
I'd say out of many generative AI observability platforms, Langsmith and Weave (Weights&Biases) are probably the ones most enterprises use, but there's definitely space for Langfuse, Modelmetry, Arize AI, and other players.
Re: ClickHouse acquires Langfuse
#97Earlier quoted context omitted.
We have a SaaS platform (Pydantic Logfire - General and AI observability), and we raised our Series A from Sequoia. For good or bad, I think we're pretty "SaaS/vc/etc." already.
Yeah it seems a bit forced though. Like why go from an open source utility library for typing to take VC money and try to shoe-horn in an observability platform that no one was asking for? My prediction, not going to be a good investment.
I clearly didn't build pydantic "to take VC money" - I maintained Pydantic for 5 years before deciding to take VC money.
I wanted to build logfire and I didn't want to compete with or restrict our open source, we so built logfire.
Let's see on the investment; seems to be going pretty well so far.
Re: ClickHouse acquires Langfuse
#98Earlier quoted context omitted.
I don’t know about that. I looked at them a couple of months back for prompt management and they were pretty behind in terms of features. Went with PromptLayer
say more about what you were looking for that promptlayer had/langfuse didnt?
Re: ClickHouse acquires Langfuse
#99Earlier quoted context omitted.
say more about what you were looking for that promptlayer had/langfuse didnt?
Ohh. Reply from Shawn. I love your work. As far as I recall, we were not looking for a net of features but specifically a git like API that could manage and version the prompts. Meta data tagging, Jinja2, release labels and easy rollback. Add that up with Rest, Typescripts and Python support and it worked pretty well. Langfuse seemed way better at tracing though.