From 8638ba0b35ee59091491bcf8ea553b6ce3ddb324 Mon Sep 17 00:00:00 2001
From: Rachel Hu <goldpiggy@berkeley.edu>
Date: Tue, 20 Aug 2024 11:28:51 +0800
Subject: [PATCH 1/3] update website

---
 app/components/Agenda.tsx | 11 ++++++-----
 app/components/Navbar.tsx |  2 +-
 app/page.tsx              | 19 +++++--------------
 3 files changed, 12 insertions(+), 20 deletions(-)

diff --git a/app/components/Agenda.tsx b/app/components/Agenda.tsx
index b845dfd..c05b2a5 100644
--- a/app/components/Agenda.tsx
+++ b/app/components/Agenda.tsx
@@ -2,12 +2,13 @@ import Section from './Section';
 
 const agendaItems = [
   'Section 1: Introduction to RAG and LLM Fine-Tuning (20 mins)',
-  'Section 2: Lab1: RAG pipeline (30 mins)',
-  'Section 3: Lab 2: LLM fine-tuning (30 mins)',
+  'Section 2: Lab setup (10 mins)',
+  'Section 3: Lab 1: Advanced Techniques in RAG (40 mins) - Richard Song',
   'Break (10 mins)',
-  'Section 4: The Pros and Cons of RAG and Fine-tuning (30 mins)',
-  'Section 5: Lab3: RAG + Fine-tuning and Benchmarking (45 mins)',
-  'Section 6: Summary and Q&A (15 mins)',
+  'Section 4: Lab 2: LLM Fine-Tuning (40 mins) - Yunfei Bai, Rachel Hu ',
+  'Break (10 mins)',
+  'Section 5: Lab 3: RAG and Fine-Tuned Model Benchmarking (30 mins) - José Cassio dos Santos Junior',
+  'Section 6: Conclusion and Q&A (20 mins)',
 ];
 
 const Agenda = () => {
diff --git a/app/components/Navbar.tsx b/app/components/Navbar.tsx
index 1fdc38d..cf040ba 100644
--- a/app/components/Navbar.tsx
+++ b/app/components/Navbar.tsx
@@ -36,7 +36,7 @@ const Navbar = () => {
           text-neutral-100
           "
           >
-            KDD Workshop 2024
+            14:00 – 17:00, August 25, 2024
           </div>
         </div>
       </div>
diff --git a/app/page.tsx b/app/page.tsx
index 303d563..c4034e6 100644
--- a/app/page.tsx
+++ b/app/page.tsx
@@ -7,26 +7,17 @@ import TextContainer from './components/TextContainer';
 export default function Home() {
   return (
     <div className="pb-20">
-      <Hero title="The Pros and Cons of RAG and Fine-tuning" subtitle="Workshop time and date - TBD" center />
+      <Hero title="Domain-Driven LLM Development: Insights into RAG and Fine-Tuning Practices" subtitle="Hands On Tutorials at 2024 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Barcelona, Spain" center />
       <Section title="Abstract">
         <TextContainer
-          text="When building Large Language Model (LLM) applications on domain specific data, there are two prominent methods:
-        Retrieval Augmented Generation (RAG) and LLM Fine-Tuning (FT). RAG improves LLM responses by searching external
-        knowledge bases outside of its training data sources. RAG extends the capabilities of LLMs to specific domains
-        or an organization's internal knowledge base, without the need to retrain the model. On the other hand,
-        Fine-tuning approach updates LLM weights with domain-specific data to improve performance on specific tasks. The
-        fine-tuned model is particularly effective to learn new knowledge in a specific domain that is not covered by
-        the LLM pre-training. This tutorial will walk through the RAG and FT techniques, provide the insights of the
-        advantages and limitations, and share best practices of adopting the right methodology for your use cases. All
-        the methods will be introduced in a hands-on lab to demonstrate how the RAG and LLM fine tuning works, and how
-        they perform to handle domain specific LLM tasks. We will use uniflow and pykoi, an open source python library,
-        to implement the RAG and FT techniques in the tutorial."
+          text="To improve Large Language Model (LLM) performance on domain specific applications, ML developers often leverage Retrieval Augmented Generation (RAG) and LLM Fine-Tuning. RAG extends the capabilities of LLMs to specific domains or an organization's internal knowledge base, without the need to retrain the model. On the other hand, Fine-Tuning approach updates LLM weights with domain-specific data to improve performance on specific tasks. The fine-tuned model is particularly effective to systematically learn new comprehensive knowledge in a specific domain that is not covered by the LLM pre-training. This tutorial walks through the RAG and Fine-Tuning techniques, discusses the insights of their advantages and limitations, and provides best practices of adopting the methodologies for the LLM tasks anduse cases. The hands-on labs demonstrate the advanced techniques to optimize the RAG and fine-tuned LLM architecture that handles domain specific LLM tasks. The labs in the tutorial are designed by using a set of open-source python libraries to implement the RAG and fine-tuned LLM architecture."
         />
       </Section>
       <Agenda />
       <Speakers />
-      <Section title="Slides">
-        <TextContainer text="Slides will be available here after the workshop." />
+      <Section title="Contents">
+      <TextContainer text="Slides: Coming Soon" />
+      <TextContainer text="Lab Notebooks: Coming Soon" />
       </Section>
     </div>
   );

From 0d6c07ba631378133c2c8fc3b10e1e912baca119 Mon Sep 17 00:00:00 2001
From: Rachel Hu <goldpiggy@berkeley.edu>
Date: Tue, 20 Aug 2024 11:53:18 +0800
Subject: [PATCH 2/3] fix linter

---
 .vscode/settings.json |  6 ++++++
 app/page.tsx          | 18 ++++++++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/.vscode/settings.json b/.vscode/settings.json
index 85ebb19..608a190 100644
--- a/.vscode/settings.json
+++ b/.vscode/settings.json
@@ -8,4 +8,10 @@
     "editor.codeActionsOnSave": {
         "source.fixAll.eslint": "explicit"
     },
+    "flake8.interpreter": [
+	    "/Users/goldpiggy/anaconda3/envs/uniflow/bin/python"
+	],
+    "pylint.interpreter": [
+	    "/Users/goldpiggy/anaconda3/envs/uniflow/bin/python"
+	],
 }
\ No newline at end of file
diff --git a/app/page.tsx b/app/page.tsx
index c4034e6..d2ec348 100644
--- a/app/page.tsx
+++ b/app/page.tsx
@@ -7,10 +7,24 @@ import TextContainer from './components/TextContainer';
 export default function Home() {
   return (
     <div className="pb-20">
-      <Hero title="Domain-Driven LLM Development: Insights into RAG and Fine-Tuning Practices" subtitle="Hands On Tutorials at 2024 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Barcelona, Spain" center />
+      <Hero title="Domain-Driven LLM Development: Insights into RAG and Fine-Tuning Practices" 
+      subtitle="Hands On Tutorials at 2024 ACM SIGKDD International Conference on Knowledge 
+      Discovery and Data Mining, Barcelona, Spain" center />
       <Section title="Abstract">
         <TextContainer
-          text="To improve Large Language Model (LLM) performance on domain specific applications, ML developers often leverage Retrieval Augmented Generation (RAG) and LLM Fine-Tuning. RAG extends the capabilities of LLMs to specific domains or an organization's internal knowledge base, without the need to retrain the model. On the other hand, Fine-Tuning approach updates LLM weights with domain-specific data to improve performance on specific tasks. The fine-tuned model is particularly effective to systematically learn new comprehensive knowledge in a specific domain that is not covered by the LLM pre-training. This tutorial walks through the RAG and Fine-Tuning techniques, discusses the insights of their advantages and limitations, and provides best practices of adopting the methodologies for the LLM tasks anduse cases. The hands-on labs demonstrate the advanced techniques to optimize the RAG and fine-tuned LLM architecture that handles domain specific LLM tasks. The labs in the tutorial are designed by using a set of open-source python libraries to implement the RAG and fine-tuned LLM architecture."
+          text="To improve Large Language Model (LLM) performance on domain specific applications, 
+          ML developers often leverage Retrieval Augmented Generation (RAG) and LLM Fine-Tuning. 
+          RAG extends the capabilities of LLMs to specific domains or an organization's internal 
+          knowledge base, without the need to retrain the model. On the other hand, Fine-Tuning 
+          approach updates LLM weights with domain-specific data to improve performance on specific 
+          tasks. The fine-tuned model is particularly effective to systematically learn new 
+          comprehensive knowledge in a specific domain that is not covered by the LLM pre-training. 
+          This tutorial walks through the RAG and Fine-Tuning techniques, discusses the insights of 
+          their advantages and limitations, and provides best practices of adopting the methodologies 
+          for the LLM tasks anduse cases. The hands-on labs demonstrate the advanced techniques to 
+          optimize the RAG and fine-tuned LLM architecture that handles domain specific LLM tasks. 
+          The labs in the tutorial are designed by using a set of open-source python libraries to 
+          implement the RAG and fine-tuned LLM architecture."
         />
       </Section>
       <Agenda />

From a8e295a4ce902fbddf31b0e2219c6acf4c709d7f Mon Sep 17 00:00:00 2001
From: Jojo Ortiz <ortiz.jroman@gmail.com>
Date: Tue, 20 Aug 2024 08:37:58 -0700
Subject: [PATCH 3/3] fix linting

---
 app/page.tsx | 37 ++++++++++++++++++++-----------------
 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/app/page.tsx b/app/page.tsx
index d2ec348..4fd102e 100644
--- a/app/page.tsx
+++ b/app/page.tsx
@@ -7,31 +7,34 @@ import TextContainer from './components/TextContainer';
 export default function Home() {
   return (
     <div className="pb-20">
-      <Hero title="Domain-Driven LLM Development: Insights into RAG and Fine-Tuning Practices" 
-      subtitle="Hands On Tutorials at 2024 ACM SIGKDD International Conference on Knowledge 
-      Discovery and Data Mining, Barcelona, Spain" center />
+      <Hero
+        title="Domain-Driven LLM Development: Insights into RAG and Fine-Tuning Practices"
+        subtitle="Hands On Tutorials at 2024 ACM SIGKDD International Conference on Knowledge
+      Discovery and Data Mining, Barcelona, Spain"
+        center
+      />
       <Section title="Abstract">
         <TextContainer
-          text="To improve Large Language Model (LLM) performance on domain specific applications, 
-          ML developers often leverage Retrieval Augmented Generation (RAG) and LLM Fine-Tuning. 
-          RAG extends the capabilities of LLMs to specific domains or an organization's internal 
-          knowledge base, without the need to retrain the model. On the other hand, Fine-Tuning 
-          approach updates LLM weights with domain-specific data to improve performance on specific 
-          tasks. The fine-tuned model is particularly effective to systematically learn new 
-          comprehensive knowledge in a specific domain that is not covered by the LLM pre-training. 
-          This tutorial walks through the RAG and Fine-Tuning techniques, discusses the insights of 
-          their advantages and limitations, and provides best practices of adopting the methodologies 
-          for the LLM tasks anduse cases. The hands-on labs demonstrate the advanced techniques to 
-          optimize the RAG and fine-tuned LLM architecture that handles domain specific LLM tasks. 
-          The labs in the tutorial are designed by using a set of open-source python libraries to 
+          text="To improve Large Language Model (LLM) performance on domain specific applications,
+          ML developers often leverage Retrieval Augmented Generation (RAG) and LLM Fine-Tuning.
+          RAG extends the capabilities of LLMs to specific domains or an organization's internal
+          knowledge base, without the need to retrain the model. On the other hand, Fine-Tuning
+          approach updates LLM weights with domain-specific data to improve performance on specific
+          tasks. The fine-tuned model is particularly effective to systematically learn new
+          comprehensive knowledge in a specific domain that is not covered by the LLM pre-training.
+          This tutorial walks through the RAG and Fine-Tuning techniques, discusses the insights of
+          their advantages and limitations, and provides best practices of adopting the methodologies
+          for the LLM tasks anduse cases. The hands-on labs demonstrate the advanced techniques to
+          optimize the RAG and fine-tuned LLM architecture that handles domain specific LLM tasks.
+          The labs in the tutorial are designed by using a set of open-source python libraries to
           implement the RAG and fine-tuned LLM architecture."
         />
       </Section>
       <Agenda />
       <Speakers />
       <Section title="Contents">
-      <TextContainer text="Slides: Coming Soon" />
-      <TextContainer text="Lab Notebooks: Coming Soon" />
+        <TextContainer text="Slides: Coming Soon" />
+        <TextContainer text="Lab Notebooks: Coming Soon" />
       </Section>
     </div>
   );