Configuring FB Dataset with Metadata & Vector Setting with Real World Data Using Text2SQL Dataset

Starting with the review of Text2SQL dataset released by GretelAI and deciding which columns can be used as metadata, and which as fields the video dives into creating 4 different version of Argilla's FB Datasets.

Chapter Navigation:
0:00 Intro
0:35 Explanation of Steps Covered
2:30 Demo of Final Dataset
4:22 Code Walkthrough: Connecting to Server
5:10 Introducing Text2SQL Dataset
6:12 Reviewing Text2SQL Dataset columns
7:55 Deciding Columns to be Fields & Metadata
11:10 Creating TextQuestion Object
11:45 Configuring v1.0 Feedbackdataset Object
14:00 Reviewing v1.0 DS Settings in Argilla UI
15:30 Creating records for v1.0 FBDS
17:30 Pushing 15 records to Argilla Server
18:20 Reviewing the Datapoints on UI
19:45 Creating Metadata Settings
22:00 Creating & Reviewing v2.0 DS with Single Metadata
23:15 Pushing records with Metadata to v2.0 DS
25:35 Reviewing Metadata Filter in UI
26:35 Creating & Reviewing V3.0 DS with Multi Metadata
27:30 Pushing Data to v3.0 DS
29:00 Discussing Benefits of Metadata
29:30 Introducing Vector Settings
30:00 Using SentenceTransformerExtractor Object to update vectors
32:30 Reviewing Find Similar option in UI
33:40 Reviewing the Vector Settings in UI
34:30 Creating Vector Settings From Scratch
35:30 Creating Sentence Transformer models
37:00 Pushing Records with Vectors to Argilla server
37:30 Reviewing the FindSimilar in the UI
38:33 Recap of various FB Datasets created
39:33 Pushing final dataset to Hugging Face
40:20 Reviewing the Pushed Datasets in HuggingFace
42:00 Re-using HF datasets in Argilla
42:30 How to Drill Deeper into Argilla
43:50 Outro

The data and the code is located at

I believe you will like this video, and subscribe to the channel. Further uploads related to Big Data, Large Language models and Artificial Intelligence will be shared to your Youtube Dashboard Directly.

The supporting playlists are
The bard Project
Practical Projects Playlist
Huggingface Playlist
Python Data Engineering Playlist
Python Ecosystem of Libraries
ChatGPT and AI Playlist
AWS and Python AWS Wrangler
Exploring the Realm of Generative AI: Hardware and Software Discussions

PS: Got a question or have a feedback on my content. Get in touch
By leaving a Comment in the video
@twitter Handle is @KQrios