trulens VS dvc

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.

Collaboration and version control are crucial in AI/ML development projects due to the iterative nature of model development and the need for reproducibility. GitHub is the leading platform for source code management, allowing teams to collaborate on code, track issues, and manage project milestones. DVC (Data Version Control) complements Git by handling large data files, data sets, and machine learning models that Git can't manage effectively, enabling version control for the data and model files used in AI projects.

What you’re describing sounds like DVC (at a higher-ish—80%-solution level).

https://dvc.org/

See pachyderm too.

10. DVC by Iterative | Github | tutorial

Platforms such as MLflow monitor the development stages of machine learning models. In parallel, Data Version Control (DVC) brings version control system-like functions to the realm of data sets and models.

I was using DVC (https://dvc.org/) for some time to help solve this but it was getting hard to manage the storage connections and I would run into cache issues a lot, but this solves it using git-lfs itself.

DVC (Data Version Control):

I have been using DVC and MLflow since then DVC had only data tracking and MLflow only model tracking. I can say both are awesome now and maybe the only factor I would like to mention is that IMO, MLflow is a bit harder to learn while DVC is just a git practically.