trulens VS sqlglot

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.

This is probably referring to "zero changes to your driver code" and not "zero changes to the SQL you send over this driver".

Translating between SQL dialects is notoriously hard and attempts to translate [1] are working in 95% of cases. But the last 5% would require 5x amount of work. That's because "SQL dialect" also includes weird edge cases of type inference of things like COALESCE(5, FALSE) and emulation of system catalogs (pg_catalog, information_schema).

[1] https://github.com/tobymao/sqlglot

Recommend checking out https://github.com/tobymao/sqlglot if you are interested in this capability for other SQL dialects

Tools like this are helpful for:

- Rendering SQL in a consistent way, eg for snapshot testing

sqlglot – Python SQL Parser and Transpiler

In the project we used Python lib networkx and a DiGraph object (Direct Graph). To detect a table reference in a Query, we use sqlglot, a SQL parser (among other things) that works well with Bigquery.

Cool! Is this built with sqlglot[1] on the back end?

[1] https://github.com/tobymao/sqlglot

Wanted to give sqlglot a shoutout as it saved me a ton of time.