Skip to content

Commit 5dce697

Browse files
author
fochan
committed
updates bonus video
1 parent e633b4f commit 5dce697

File tree

2 files changed

+155
-0
lines changed

2 files changed

+155
-0
lines changed

‎docs/bonus/bonus.rst‎

Lines changed: 154 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,154 @@
1+
Bonus: GenAI Demo Videos
2+
========================
3+
4+
F5 AI Gateway
5+
-------------
6+
7+
Identity Aware Model Routing
8+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
9+
10+
Demonstrate the capability of F5 AI Gateway to dynamically apply and steer LLM traffic policy according to user identity based on JSON Web Token (JWT) or header.
11+
12+
13+
.. raw:: html
14+
15+
<iframe width="700" height="410" src="https://www.youtube.com/embed/nl0AmeaXaEY?si=btsimVq7SZFrJFRv" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
16+
17+
18+
|
19+
|
20+
21+
Language and Code Detection Routing
22+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
23+
24+
Demonstrate the capability of F5 AI Gateway to detect type of language input and steer according to the defined language model for better user experience and cost optimization. It also demonstrate code detection and steer the traffic to a local self-hosted model to prevent any unintentional code leakage to a SaaS-Managed model.
25+
26+
27+
.. raw:: html
28+
29+
<iframe width="700" height="410" src="https://www.youtube.com/embed/ySp6EnY89PU?si=0ubsYF7Ov16mMvW2" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
30+
31+
32+
|
33+
|
34+
35+
System Prompt Enforcement (Guardrail)
36+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
37+
38+
Showcase the system prompt capabilities of the F5 AI Gateway (AI GW) to ensure conversations remain contextually relevant. The AI Gateway enforces strict guardrails to prevent users from deviating from the intended purpose of the chatbot. This helps maintain the integrity of the system while preventing the misuse of AI resources
39+
40+
41+
.. raw:: html
42+
43+
<iframe width="700" height="410" src="https://www.youtube.com/embed/ZVzeQKUhs-4?si=euEMuhpkc8VblE4P" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
44+
45+
46+
|
47+
|
48+
49+
50+
OWASP Top 10 LLM01 - Prompt Injection
51+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
52+
53+
Showcase Prompt Injection processor to address few key concern raised in OWASP TOP 10 for LLM apps especially on Prompt Injection concern. (LLM01)
54+
55+
56+
.. raw:: html
57+
58+
<iframe width="700" height="410" src="https://www.youtube.com/embed/fXnu1JmqcgA?si=RWPFX65n-LYLEq4l" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
59+
60+
|
61+
|
62+
63+
OWASP Top 10 LLM02 - Sensitive Information Disclosure (PII)
64+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
65+
66+
Showcase PII Redactor processor to address key concern raise on sensitive information disclosure raise in OWASP TOP 10 for LLM apps (LLM02)
67+
68+
69+
.. raw:: html
70+
71+
<iframe width="700" height="410" src="https://www.youtube.com/embed/1n-du-D-4IQ?si=X_sT7BIL9FVLge8a" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
72+
73+
|
74+
|
75+
76+
77+
OWASP Top 10 LLM07 - System Prompt Leakage
78+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
79+
80+
Showcase System Prompt processor to address key concern raise on system prompt leakage raise in OWASP TOP 10 for LLM apps (LLM07)
81+
82+
.. raw:: html
83+
84+
<iframe width="700" height="410" src="https://www.youtube.com/embed/gfeyP5aTdDc?si=T1uhNtUQ2oADrC7f" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
85+
86+
|
87+
|
88+
89+
90+
91+
Enterprise RAG
92+
--------------
93+
94+
Explores how F5's solutions can help you implement, secure, and optimize your chatbots and other AI applications. This will ensure they perform at their best while protecting sensitive data. One of the AI frameworks showed is Enterprise Retrieval-Augmented Generation (RAG). This demo leverages F5 Distributed Cloud (XC) AppStack, Distributed Cloud WAAP, NGINX Plus as API Gateway, API-Discovery, API-Protection, LangChain, Vector databases, and Flowise AI
95+
96+
.. raw:: html
97+
98+
<iframe width="700" height="410" src="https://www.youtube.com/embed/r4afnSqn-Ns?si=vb5q-5f6BEMvpZZt" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
99+
100+
|
101+
|
102+
103+
104+
105+
Agentic RAG with F5
106+
-------------------
107+
108+
109+
Enhance GenAI Chatbot with power of Agentic RAG and F5 Platform
110+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
111+
112+
Agentic RAG enhances the capabilities of a GenAI chatbot by integrating dynamic knowledge retrieval into its conversational abilities, making it more context-aware and accurate. In this demo, I will demonstrate an autonomous decision-making GenAI chatbot utilizing Agentic RAG. I will explore what Agentic RAG is and why it's crucial in today's AI landscape. I will also discuss how organizations can leverage GPUaaS (GPU as a Service) or AI Factory providers to accelerate their AI strategy. F5 platform provides robust security features that protect sensitive data while ensuring high availability and performance. They optimize the chatbot by streamlining traffic management and reducing latency, ensuring smooth interactions even during high demand. This integration ensures the GenAI chatbot is not only smart but also reliable and secure for enterprise use.
113+
114+
.. raw:: html
115+
116+
<iframe width="700" height="410" src="https://www.youtube.com/embed/crGDvjYCPk0?si=5GK2TdgEEcHQhpSX" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
117+
118+
|
119+
|
120+
121+
122+
Securing Agentic RAG with F5
123+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
124+
125+
In this demo, I will focus on security aspect of the solution. This demonstration will highlight the various security measures implemented and enforced in our AI reference architecture for this Agentic RAG. F5 is a trusted leader in security, with a track record of delivering robust solutions for securing applications and networks. Recognized by many independent evaluations as a Leader in Web Application and API Security from IDC, SC Award, TrustRadius, EMA, and many more, F5 exemplifies excellence and innovation.
126+
127+
.. raw:: html
128+
129+
<iframe width="700" height="410" src="https://www.youtube.com/embed/Pwb8k3LPKgI?si=6_X9p3chMwiq8GVc" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
130+
131+
132+
|
133+
|
134+
135+
136+
Deliver and Optimize Agentic RAG with F5
137+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
138+
139+
Explores delivery and optimization use cases for F5. In this demonstration, we'll showcase three key scenarios that address enterprise concerns around traffic delivery and digital resiliency of an AI Services.
140+
1. GenAI Inference site failure
141+
2. Primary VectorDB failure
142+
3. Edge Inference LLM failure
143+
144+
.. raw:: html
145+
146+
<iframe width="700" height="410" src="https://www.youtube.com/embed/20ciD1b9Bpo?si=X-kjXyl4ih7BQWwr" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen></iframe>
147+
148+
149+
150+
151+
.. toctree::
152+
:maxdepth: 1
153+
:glob:
154+

‎docs/index.rst‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -14,3 +14,4 @@ Welcome to the |classbold|
1414
introduction/introduction*
1515
prerequisite/prerequisite*
1616
class*/class*
17+
bonus*/bonus*

0 commit comments

Comments
 (0)