[Day 190] Learning about evaluating vector search engines for RAG apps

 Hello :)
Today is Day 190!


A quick summary of today:
  • covered Module 3: vector search from the LLM zoomcamp


All the code from today is on my repo.

The first part of the module was related to doing semantic search using dense vectors in Elasticsearch

1. Loaded Q&A documents from a json file

2. Created dense vectors for each document using a pre-trained model

3. Created an index in Elasticsearch

4. Indexed the documents in Elasticsearch

5. Performed a semantic search using the dense vectors

6. Filtered the results using a specific section

(picture is from the course)


Next I learned about evaluating the retrieval mechanism

1. Generate unique IDs for each document to distinguish each other

2. Generate 5 sample questions for each document using the GPT API

3. Save the results to a file to use for evaluation

first 10 rows from the created dataset:

The ID is needed to connect the sample created questions to the documenta they are related to.


Next, I learned about two evaluation metrics for evaluating the used search mechanism

Recall

  • Measures the number of relevant documents retrieved out of the total number of relevant documents available.
  • Formula: Recall = (Number of relevant documents retrieved) / (Total number of relevant documents)

Mean Reciprocal Rank

  • Evaluates the rank position of the first relevant document.
  • Formula: MRR = (1 / |Q|) * Σ (1 / rank_i) for i = 1 to |Q|

To do evaluation, a few different engines were created and compared based on recall and MRR

  • base elastic search based on word similarity: recall: 0.74, mrr: 0.60
  • KNN using embedded question body: recall: 0.77, mrr: 0.66
  • KNN using embedded text body: recall: 0.83, mrr: 0.71
  • KNN using embedded question and text boxy: recall: 0.92, mrr: 0.82
All ran with different times, so it is about evaluating what do we care more, speed vs a set % improvement

At the end, I completed the homework which covered similar questions like the above learned content.


That is all for today!

See you tomorrow :)

Popular posts from this blog

[Day 198] Transactions Data Streaming Pipeline Porject [v1 completed]

Image
 Hello :) Today is Day 198! A quick summary of today: data streaming pipeline project [v1 done] Here is a link to the project's repo. Well ... I did not know I can do it in a day (~14 hours) after yesterday's issues but here we are. Turns out in order to insert the full (~70 variables with nested/list structure), I need the proper pyspark schema. And yesterday I did not have that and that is why when I was reading data in the kafka producer I was getting NULL in the columns - my schema was wrong. Well today I not only fixed the schema for the 4 variables I had yesterday, but included *all* the variables that come from the Stripe API ~ 70 (for completeness).  When I run docker-compose, the data streams and is input into the postgres db (and is still running). Unfortunately, the free Stripe API for creating realistic transactions has a limit of 25, so every 3 seconds, 25 new transactions are sent to the db. It has been running half the day (since I got that set up) and as I am wr
Read more

[Day 107] Transforming natural language to charts

Image
 Hello :) Today is Day 107! A quick summary of today: created text2chart - transforming natural language to charts [ github ] [ webapp ] I am super sick, but in the around 3 hours of my fever not being high, I managed to study a bit. I was again thinking about creating some nlp project but was stuck on the idea of how to host a model. After looking around I found this article where they create a similar app called chat2vis  and they use codellama. I know codellama is an open source model that I can get from huggingface and I wondered, how did they host it. Turns out - they ask the user to input a huggingface api key, which then allows for querying and generating content. (AWESOME! this is applicable to some of the other PDF chat apps that I have, but I will look to make an app of them later).  My fever eased a bit, and I sat on my chair to do some work ^^ Here is a breakdown of the app. I used streamlit. Also, 2 default datasets during dev: Financial Statements of Major Companies(2009-
Read more

[Day 54] I became a backprop ninja! (woohoo)

Image
 Hello :) Today is Day 54! A quick summary of today: Read through cs231n's neural network lectures [1] [2] [3] Spent 8 hours going over Andrej Karpathy's backprop ninja tutorial After yesterday's confidence boost in doing backprop, I came in today with the intention of becoming of, as Andrej Karpathy calls it, a backprop ninja.  The cs231n NN lectures were the usual about how NN became to be, param initialization, activation functions, loss functions, regularization and optimizers. Nothing out of the ordinary, but still was good to reassure myself of that knowledge. But that was definitely not the main even of today. As I mentioned, I wanted to become (or at least attempt to become) a backprop ninja today. I have watched that particular tutorial twice, the 1st time I had no idea what is going on, the 2nd time I could follow, and now it was the 3rd time - and now, I wanted to participate and actually see the why and the how of the things we have to do, when we do manual back
Read more