langfuse VS trulens

Langfuse is an open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications.

Congrats on the Show! How’s this different from https://github.com/langfuse/langfuse? The exports seems really interesting

Thus, we started working on Langfuse.com (GitHub) to establish an open source LLM engineering platform with tightly integrated features for tracing, prompt management, and evaluation. In the beginning we just solved our own and our friends’ problems. Today we are at over 1000 projects which rely on Langfuse, and 2.3k stars on GitHub. You can either self-host Langfuse or use the cloud instance maintained by us.

- We want to build a tool that is recommended here on HN: you can build a tool you would want to use yourself.

Please see more details here: https://langfuse.com/careers or reach out directly to me: [email protected]

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

[2] https://create.t3.gg/

We struggled with this ourselves while building LLM-based products and then open-sourced our observability/monitoring tool [1]. Many use it to track RAG and agents in production, run custom evals on the production traces (focused on hallucination), and track how metrics are different across releases or customers. Feel free to dm if there is something specific you are looking to solve, happy to help.

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

Visit us on Discord and Github to engage with our project.

Maybe try https://github.com/langfuse/langfuse

It was recently shared on HN

Retrieval using a single vector is called dense passage retrieval (DPR), because an entire passage (dozens to hundreds of tokens) is encoded as a single vector. ColBERT instead encodes a vector-per-token, where each vector is influenced by surrounding context. This leads to meaningfully better results; for example, here’s ColBERT running on Astra DB compared to DPR using openai-v3-small vectors, compared with TruLens for the Braintrust Coda Help Desk data set. ColBERT easily beats DPR at correctness, context relevance, and groundedness.

12. TruLens by TruEra | Github | tutorial

3) Hallucination is probably the biggest problem we solve for. To do evals for hallucination, we typically see our users use a combination of groundedness (does the context support the LLM response) and context relevance (is the retrieved context relevant to the query). There's also a bunch more for the evaluations you mentioned (moderation models, sentiment, usefulness, etc.) and it's pretty easy to add custom evals.

Also - my hot take is that gpt-3.5 is good enough for evals (sometimes better) than gpt-4 if you give the LLM enough instructions on how to do the eval.

website: https://www.trulens.org/

The team at TruEra recently released an open source project for evaluation & tracking of LLM applications called TruLens-Eval. We’ve specifically targeted retrieval-augmented QA as a core use case and so far we’ve seen it used for comparing different models and parameters, prompts, vector-db configurations and query planning strategies. I’d love to get your feedback on it.