Auto-update of schedule

src/content/sessions/HBB3ST.yml

@@ -0,0 +1,24 @@
+title: How to secure, break, and re-secure an encrypted data vault using Python and
+  PostgreSQL
+start: 2024-11-25 13:30:00+11:00
+end: 2024-11-25 15:30:00+11:00
+room: chancellor2
+track:
+abstract: "<p>You’ve got sensitive customer data you need to protect in your Python
+  web service.</p>\n<p>You’ve done all the right things to secure it — using SQLAlchemy
+  to sanitise inputs to your SQL queries, HTTPS with Let’s Encrypt, and Semgrep in
+  your CD pipeline.</p>\n<p>You’ve even gone the extra mile — using cryptography and
+  SQLAlchemy’s StringEncryptedType to encrypt each row of data with AES.</p>\n<p>But
+  you have a lingering feeling that it’s all not quite enough. So how do you shake
+  that feeling?</p>\n<p>One of the best ways to understand a system is to break it
+  and rebuild it. That is what we’re going to do in this session.</p>\n<p>In this
+  workshop you’ll learn:\n * How to secure, break, and then re-secure an encrypted
+  data vault built using Python and PostgreSQL\n * The cryptography fundamentals you
+  need to pay attention to, and the ones you don’t\n * Plus: how quantum safety should
+  affect how you encrypt data today</p>"
+description: ''
+code: HBB3ST
+speakers:
+- PB9BKD
+- KWK79M
+cw:

src/content/sessions/PQAV73.yml

@@ -0,0 +1,26 @@
+title: 'Mastering RAG & Unlocking AI Potential:  Build a RAG system using Python,
+  Open-source LLMs & MongoDB Atlas'
+start: 2024-11-25 09:30:00+11:00
+end: 2024-11-25 12:30:00+11:00
+room: chancellor2
+track:
+abstract: "<p>In this workshop, we will build a ChatBot based on Retrieval Augmented
+  Generation (RAG). The ChatBot will leverage MongoDB Atlas, embedding models, Large
+  Language Models (LLMs) to generate contextualized answers and textual content in
+  accordance to users’ queries based on publicly available sources.</p>\n<p>In this
+  hands-on workshop, attendees will:\n * Learn the foundations of Retrieval Augmented
+  Generation (RAG), such as chunking, embedding, and semantic search\n * Perform semantic
+  search queries against a MongoDB Atlas collection \n * Build a simple RAG system
+  using MongoDB Atlas and open-source LLMs</p>\n<p>Add memory to the RAG application\n
+  * In addition to these goals, the lab also offers more advanced content that covers:\n
+  * Combining pre-filtering with vector search\n * Adding re-ranking to the RAG application\n
+  * Stream responses from the RAG application</p>\n<p>Attendees will be provided with
+  all the resources required to successfully execute the hands-on portions of the
+  workshop, including a GitHub repository consisting of notebook templates with pseudocode.
+  Attendees will replace the pseudocode with their own code during the workshop.</p>"
+description: <p>This workshop will be facilitated by experts from MongoDB</p>
+code: PQAV73
+speakers:
+- PB9BKD
+- KWK79M
+cw: