trulens VS n8n

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.

I believe you can achieve that with n8n. Used in past (and still running) for some data transformation and little more. Possibly similar case what are you describing.

https://n8n.io/

A startup, "DevOps Solutions" adopts Helm to streamline their Kubernetes deployments. You're a consultant tasked with creating a basic Helm Chart for n8n. It should be customizable for different environments using values.

n8n.io - a powerful workflow automation tool

N8N - Open Source Alternative to Zapier

N8N - anything that I would have used Zapier or IFTTT for I now use N8N. It is a bit harder to use but more powerful.

I'm using Weweb as my front end and Supabase as my back end. I'm also looking into n8n.io to run some of the backend logic that I'm either unsure how to code myself within Supabase or unsure if Supabase can perform those back-end tasks and workflows. Curious what stack or tools other Supabase users are using?

This is similar to something I saw before: https://n8n.io