-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
24 additions
and
8 deletions.
There are no files selected for viewing
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,24 @@ | ||
--- | ||
title: "ODSC East 2024: RAG, the bad parts (and the good!)" | ||
date: 2024-04-25 | ||
author: "ZanSara" | ||
tags: [LLM, NLP, Python, AI, RAG, "ODSC East", ODSC, Retrieval, Generation, Evaluation, Haystack] | ||
featuredImage: "/talks/2024-04-25-odsc-east-rag.png" | ||
--- | ||
|
||
[Announcement](https://odsc.com/speakers/rag-the-bad-parts-and-the-good-building-a-deeper-understanding-of-this-hot-llm-paradigms-weaknesses-strengths-and-limitations/), [slides](https://drive.google.com/file/d/19EDFCqOiAo9Cvx5fxx6Wq1Z-EoMKwxbs/view?usp=sharing) | ||
|
||
--- | ||
|
||
In this talk at [ODSC East 2024](https://odsc.com/boston/) I talk about RAG: how it works, how it fails, and how to evaluate its performance objectively. I give an overview of some useful open-source tools for RAG evalution and how to use them with [Haystack](https://haystack.deepset.ai/?utm_campaign=odsc-east), and then give you some ideas on how to expand your RAG architecture further than a simple two-step process. | ||
|
||
Some resources mentioned in the talk: | ||
|
||
- Haystack: open-source LLM framework for RAG and beyond: [https://haystack.deepset.ai/](https://haystack.deepset.ai/?utm_campaign=odsc-east) | ||
- Build and evaluate RAG with Haystack: [https://haystack.deepset.ai/tutorials/35_model_based_evaluation_of_rag_pipelines](https://haystack.deepset.ai/tutorials/35_model_based_evaluation_of_rag_pipelines/?utm_campaign=odsc-east) | ||
- Evaluating LLMs with UpTrain: https://docs.uptrain.ai/getting-started/introduction | ||
- Evaluating RAG end-to-end with RAGAS: https://docs.ragas.io/en/latest/ | ||
- Semantic Answer Similarity (SAS) metric: https://docs.ragas.io/en/latest/concepts/metrics/semantic_similarity.html | ||
- Answer Correctness metric: https://docs.ragas.io/en/latest/concepts/metrics/answer_correctness.html | ||
|
||
Plus, shout-out to a very interesting LLM evaluation library I discovered at ODSC: [continuous-eval](https://docs.relari.ai/v0.3). Worth checking out especially if SAS or answer correctness are too vague and high level for your domain. |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.