DevDive_UnleashthFullPotentialofAutomationwithGenAI.pptx

Dev Dives
Go deeper, automate smarter
2
Meet today’s team:
Rohit Radhakrishnan
Marketing
Community Manager
@UiPath
Roxana Ivan
Senior Product
Marketing Manager
@UiPath
3
Meet today’s speakers:
Dhruv Patel
Senior Sales Solution Architect
@UiPath
Russel Alfeche
UiPath MVP
Technology Leader RPA
@qBotica
4
About today’s meeting
• Enjoy the next 50-60 min packed with gen AI powered
automations use cases, demos, and live Q&A.
• Build your own Two Way Match Invoice Processing
with UiPath+GenAI. You’ll receive the recording and
the full pack of instructions to leverage the power of
UiPath Document Understanding and GenAI to
seamlessly process invoices.
• Get answers to your questions and challenges. Please
use the chat box for Qs during the presentation. Live
Q&A session at the end.
• You're encouraged to network and share your
LinkedIn/Twitter in the chat.
Have fun! Feedback is welcome.
Unleash the full
potential of your
automations with
generative AI
UiPath Dev Dives Webinar Series
6
Poll time
We’d love to know more about your experience with
gen AI and automation!
Take a quick poll by scanning the QR code
or access it at
https://www.menti.com/al1eexoy2cdr
7
Agenda
01
02
03
UiPath + generative AI, AI-powered automation
3 patterns for gen AI powered automations
Demo time!
8
Explore Novel Use Cases
Build Better Automations Faster
UiPath Uses Gen AI in 3 Ways
Generative AI Powered
Automations
Incorporating Gen AI directly into
Business Automation Use Cases
Supercharge Developer
Productivity
“Co-Pilot” Like experience bringing a user-
friendly interface to building automations
Product & Model
Augmentation
Add LLM capabilities to improve
design time
1 2 3
9
AI-powered automation
Open | Flexible | Responsible
Supported by UiPath Built with UiPath or BYO
BYO
Docs Screens Tasks Processes
Solutions
AI Infrastructure
Integration Service – Validation Station – Active learning – Fine tuning – Guardrails – Auditing
AI-powered automation
Delivering enterprise automation with Specialized AI
Generative AI Specialized AI
Context
HITL
UI
API
Action
People
Comms
Docs
Data
Processes
10
Advantages of using UiPath with Gen AI for Automation
More than calling a Generative AI Model
Context
Gathering
Specialized
Models
Robots Do Work Human In The Loop
Confidence
in governance
UiPath also has Specialized
models to complement Gen
AI interactions
Gen AI needs context,
UiPath can gather the
context from all sources
Gen AI is just a brain,
Automation is the muscle
that does the work
Gen AI “hallucinates”.
There are times you can
not get things wrong
Your business is governed
with audit logs and
controls while using Gen
AI with UiPath
3 Patterns for Gen AI Powered Automations
A use case may use 1 or multiple patterns
Pattern
1
Reader / Writer
Pattern
2
Pattern
3
Analyst / Doer
Assistant
UiPath can execute
processes as a result of
LLM calls
UiPath can gather context
from multiple sources to
generate and distribute
personalized messages
UiPath can add context and
action to conversational
assistants
UiPath
Advantage
Source 1
Source 2
Source 3
Source 4
LLM
Ingest Analyze
Data Next Best Action
System 1
System 2
System 3
System 4
Do
LLM
System 1
System 2
System 3
System 4
Do
Conversational
Interface
Human
Knowledge
Response
Action
OR
Source 1
Source 2
Source 3
Source 4
LLM
Read Write
Emails Summaries Content
12
Pattern 1 - Reader / Writer
Description:
LLMs are great at taking context and generating personalized text, whether longer or shorter than the original context. UiPath is collecting all the
relevant context and prompting the LLM for text. UiPath can keep a human in the loop to fine tune the output.
Example Use Cases
Cold Call Emails
Gather context about your audience and
generate email
Customer Feedback Response
Gather sentiment and customer history
to generate tailored response
Proposal Writer
Combine multiple answers from your KB
with additional context for a tailored
answer to a proposal question
Applicant Communications
Combine feedback from interviewers,
JD details, and applicant resume for
tailored communications
Customer Summary
Summarize customer history, support
ticket history, etc. for faster consumption
by customer facing agents
Email/PMO Summarizer
Summarize information from PM tools,
emails, other sources for faster
executive overviews
KYC Summarizer
Gather and summarize materials from
multiple sources for faster KYC review
Compliance and ESG Reporting
Monitor data and reports from multiple
systems/source and generate consistent
reporting
Product Documentation
Create and maintain product
documentation summarizing information
from feature tickets and marketing
Fraud Communications
Generate correspondence with
customers collating information multiple
systems
Insurance Claims Communication
Communicate to Customers around
their claims request synthesizing
information from multiple systems
Healthcare Appeals Communication
Tailor communications to customers
about using information about the
customer and the circumstance
Human Input
and Validation
Human in
the loop
Source 1
Source 2
Source 3
Source 4
LLM
Read Write
Emails Summaries Content
System 1
System 2
System 3
System 4
Distribute
13
Pattern 2 – Analyst / Doer
Description:
LLMs can generate structured output (data tables, code, XML/JSON) from multiple unstructured sources when prompted well. UiPath is
collecting the relevant sources and prompting the LLM to generate structured outputs. Critically, UiPath can validate the contents of the
structured outputs vs. systems of record or humans. UiPath can further execute processes based on the output.
Source 1
Source 2
Source 3
Source 4
LLM
Ingest Analyze
Data Next Best Action
System 1
System 2
System 3
System 4
Do/Validate
Human Input
and Validation
Human in
the loop
Example Use Cases
Multi-Source Report Creating
Gather reporting from different systems,
documents, and emails and combine
them into one set
Structuring and Normalizing Data
Normalize data from different sources
into a common schema
2 Way Match (Generic Reconciliation)
Normalize data from multiple systems
and further reconcile the two noting
differences for humans to validate
Contact Center Next Best Action
Gather context from sources,
recommend an action from a list and
execute the action
After Call Work (Action Item Doer)
Extract actions from call scripts for
follow-up. Execute those automatable.
Upsell / Cross-sell Assistant
Gather customer history and needs,
generate a recommendation for what to
sell, and a script to sell it
Contract Extractor
Extract structured data out of contracts /
amendments, validate against sources,
and input into systems
Company Filing Extractor
Extract key figures out of company
filings, validate with human, and use in
processes
Test Data Creator
Generate test data for application
testing and insert it into the system
using UiPath
Generic Classifier
Take in unstructured sources and
classify against a list of defined options.
Use this data as input for processes
Competition Analysis
Monitor pricing, news, reviews of
competitors and extract structured
findings
Vendor Selection
Analyze proposals from multiple
vendors, extract key differentiations, and
recommend a vendor
14
Pattern 3 - Assistant
Description:
The most common use case enterprises are building is a custom ChatGPT on their own knowledge sources. UiPath can augment and enrich
these chat interfaces with more knowledge sources, either directly in the LLM or in the prompt. For assistant interactions that result in an action,
UiPath be used for last-mile process execution.
LLM
System 1
System 2
System 3
System 4
Do
Conversational
Interface
Human
Knowledge
Response
Action
OR
Human in
the loop
Example Use Cases
Knowledge Base Assistant
Use UiPath to augment the knowledge
accessible to the LLM. Vectorize
databases or embed in the prompt.
Support Escalation Assistant
Variation of a Knowledge Base
Assistant focused on customer support
escalations.
Learning Assistant
UiPath can help find courses from
different learning platforms and
recommend one for a user
Self Service Helpdesk
LLMs will create enhanced assistant
interfaces. Execute common tasks
behind the scenes with UiPath.
Employee Benefits Assistant
Answer employee questions about
benefits and automate benefit selection
/ changing
Employee Travel Concierge
UiPath can bring in context on travel
policy and flight/hotel data to allow
users to book compliant trips faster
Legacy System Augmenter
Legacy systems likely won’t have LLMs
integrated. UiPath can be used to bring
LLM experiences to old systems.
Localization Assistant
LLMs have become decent at localizing
to different languages. UiPath can help
validate the output against other tools
Supply Chain Buyer Assistant
A conversational interface help speed
up inventory management and ordering
across suppliers for buyers
Personalized Assistant
Use a conversational interface to
perform more Reader/Writer and
Analyzer/Doer actions
Guided Form Entry
A conversational interface collects &
validates input from users. UiPath can
input those answers into a system.
Ask GPT (Document)
Gather a specific document with
automation and then allow users to ask
questions about it
Demos
UiPath + gen AI
16
SAMPLE – Web Q&A
Pattern
1
&
3
17
SAMPLE –Video Summarization, Image Generation
Pattern
1
&
3
18
How does it work?
Core Concept in NLP
Embeddings
Numerical Representation of the
meanings of words or a group of words
Used with semantic search to
inject context nearest/relevant to
the query into prompts (Context
Injection)
19
Knowledgebase or data source can be
documents, web pages, video transcripts, etc
Generate most
reliable answers with
LLM completions by
leveraging the primed
prompt
Context Injection
Generate
Answer
Inject
Context
Semantic
Search
Ask
Question
Generate
Embeddings
Fetch
KB, Data
Source
Call embeddings API to calculate the transcript's
embeddings and load into a vector database
Use the question as an input
for semantic search/similarity.
Get only most relevant chunks of tokens
from the embeddings using the query as
an input. The distance between
embeddings carries semantic meaning
Inject the context
gathered from the
search, along with the
specific query, into
the prompt to prime it
Claude
GPT
Vertex AI
…
Pattern
3
20
2 Way Match Invoice Processing
This process matches invoices to purchase orders to ensure accurate payment.
This process ensures that only valid invoices with valid line items are paid,
reducing the risk of fraud and errors; save time and money, and improve their
relationships with business partners.
Generative AI reduces the development complexity and enables developers to
handle complex validation logic with natural language prompts!
Increased Process
Efficiency​
Improved Accuracy,
Clear Compliance &
Audit Trail
Reduced Development
Complexity
Reduced Risk &
Cost Savings
Process: Invoice 2 Way Match
& Gen AI
Leverage the power of UiPath Document Understanding and Generative AI to
seamlessly process invoices
Natural language to prompt GenAI
to handle the validation logic
Automations handle processing,
involving a human when needed
Pattern
2
21
Pharmacovigilance (Adverse Events)
Pharmacovigilance is a crucial process for monitoring the safety of approved drugs by systematically collecting and analyzing data on adverse drug reactions (ADRs) and other drug-related
problems. MedDRA, a standardized medical terminology, plays a vital role in this process. It provides a common language for classifying and coding adverse events and medical conditions,
ensuring consistent reporting.
Automation + GenAI reduce the burden on clinicians, analysts and medical professionals during this process to intake adverse events & encode them in MedDRA, WHO DD, etc.
& Gen AI
Pattern
2
22
Date/Time Topic Status
July 27,
10:30 AM EST /
3:30 PM GMT
Empower your automation with Cloud
Robots
Register AMER
Register EMEA & APAC
August 31,
9:00 AM EST /
2:00 PM GMT
Supercharge testing and RPA with
coded automations
Register AMER
Register EMEA & APAC
Next steps
Download the automation template Two Way Match Invoice Processing: UiPath +
GenAI > https://bit.ly/3JwLAnC
Don't miss the next Dev Dives sessions. Save your seat > https://bit.ly/Dev-Dives_2023
23
CATEGORY 1:
AI POWERED AUTOMATION
SOLUTIONS
CATEGORY 2:
INNOVATE THROUGH CORE
BUSINESS AUTOMATION
SOLUTIONS
AWARDS/CATEGORY:
🥇 1ST place: 4500 $
🥇 2nd place: 3500 $
🥇 3rd place: 1500 $
http://bit.ly/UiPath_Hyper_Hack_2023
24
Live Q&A
Thank you
for your participation!
Join us: community.uipath.com
26
MeetingAI
How it works
20-30 minutes saved
in follow-up per meeting!
& Gen AI
Zoom
Recording
Upload Post-
meeting
Triggers
Automation
Meeting
Gen AI:
Extract action items
Summarize meeting
Microsoft Azure
OpenAI
Gen AI:
Compare action items
to list of existing
automations
Get
Documentation
Microsoft Azure
OpenAI
Get meeting
times
Get recording
link
Compose email
[Meeting Summary]
[Follow-up items]
[Action items]
Less time spent on admin
tasks after meetings
Send email
More time for account strategy,
market research, meeting preparation
List of Automations
supplied by robot
Pattern
1
&
2
1 sur 26

Recommandé

An Introduction to Generative AI - May 18, 2023 par
An Introduction  to Generative AI - May 18, 2023An Introduction  to Generative AI - May 18, 2023
An Introduction to Generative AI - May 18, 2023CoriFaklaris1
904 vues28 diapositives
The Future is in Responsible Generative AI par
The Future is in Responsible Generative AIThe Future is in Responsible Generative AI
The Future is in Responsible Generative AISaeed Al Dhaheri
663 vues16 diapositives
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74) par
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Naoki (Neo) SATO
1.2K vues47 diapositives
Unlocking the Power of Generative AI An Executive's Guide.pdf par
Unlocking the Power of Generative AI An Executive's Guide.pdfUnlocking the Power of Generative AI An Executive's Guide.pdf
Unlocking the Power of Generative AI An Executive's Guide.pdfPremNaraindas1
2.2K vues29 diapositives
Conversational AI and Chatbot Integrations par
Conversational AI and Chatbot IntegrationsConversational AI and Chatbot Integrations
Conversational AI and Chatbot IntegrationsCristina Vidu
423 vues24 diapositives
AI FOR BUSINESS LEADERS par
AI FOR BUSINESS LEADERSAI FOR BUSINESS LEADERS
AI FOR BUSINESS LEADERSAndre Muscat
914 vues25 diapositives

Contenu connexe

Tendances

GENERATIVE AI, THE FUTURE OF PRODUCTIVITY par
GENERATIVE AI, THE FUTURE OF PRODUCTIVITYGENERATIVE AI, THE FUTURE OF PRODUCTIVITY
GENERATIVE AI, THE FUTURE OF PRODUCTIVITYAndre Muscat
6.5K vues19 diapositives
The Creative Ai storm par
The Creative Ai stormThe Creative Ai storm
The Creative Ai stormLeandro Righini
647 vues26 diapositives
Generative AI: Past, Present, and Future – A Practitioner's Perspective par
Generative AI: Past, Present, and Future – A Practitioner's PerspectiveGenerative AI: Past, Present, and Future – A Practitioner's Perspective
Generative AI: Past, Present, and Future – A Practitioner's PerspectiveHuahai Yang
549 vues48 diapositives
A Framework for Navigating Generative Artificial Intelligence for Enterprise par
A Framework for Navigating Generative Artificial Intelligence for EnterpriseA Framework for Navigating Generative Artificial Intelligence for Enterprise
A Framework for Navigating Generative Artificial Intelligence for EnterpriseRocketSource
187 vues30 diapositives
Using the power of Generative AI at scale par
Using the power of Generative AI at scaleUsing the power of Generative AI at scale
Using the power of Generative AI at scaleMaxim Salnikov
901 vues31 diapositives
Generative-AI-in-enterprise-20230615.pdf par
Generative-AI-in-enterprise-20230615.pdfGenerative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdfLiming Zhu
815 vues7 diapositives

Tendances(20)

GENERATIVE AI, THE FUTURE OF PRODUCTIVITY par Andre Muscat
GENERATIVE AI, THE FUTURE OF PRODUCTIVITYGENERATIVE AI, THE FUTURE OF PRODUCTIVITY
GENERATIVE AI, THE FUTURE OF PRODUCTIVITY
Andre Muscat6.5K vues
Generative AI: Past, Present, and Future – A Practitioner's Perspective par Huahai Yang
Generative AI: Past, Present, and Future – A Practitioner's PerspectiveGenerative AI: Past, Present, and Future – A Practitioner's Perspective
Generative AI: Past, Present, and Future – A Practitioner's Perspective
Huahai Yang549 vues
A Framework for Navigating Generative Artificial Intelligence for Enterprise par RocketSource
A Framework for Navigating Generative Artificial Intelligence for EnterpriseA Framework for Navigating Generative Artificial Intelligence for Enterprise
A Framework for Navigating Generative Artificial Intelligence for Enterprise
RocketSource187 vues
Using the power of Generative AI at scale par Maxim Salnikov
Using the power of Generative AI at scaleUsing the power of Generative AI at scale
Using the power of Generative AI at scale
Maxim Salnikov901 vues
Generative-AI-in-enterprise-20230615.pdf par Liming Zhu
Generative-AI-in-enterprise-20230615.pdfGenerative-AI-in-enterprise-20230615.pdf
Generative-AI-in-enterprise-20230615.pdf
Liming Zhu815 vues
Leveraging Generative AI & Best practices par DianaGray10
Leveraging Generative AI & Best practicesLeveraging Generative AI & Best practices
Leveraging Generative AI & Best practices
DianaGray101.7K vues
Generative AI Use-cases for Enterprise - First Session par Gene Leybzon
Generative AI Use-cases for Enterprise - First SessionGenerative AI Use-cases for Enterprise - First Session
Generative AI Use-cases for Enterprise - First Session
Gene Leybzon173 vues
The Five Levels of Generative AI for Games par Jon Radoff
The Five Levels of Generative AI for GamesThe Five Levels of Generative AI for Games
The Five Levels of Generative AI for Games
Jon Radoff2.8K vues
Generative AI Risks & Concerns par Ajitesh Kumar
Generative AI Risks & ConcernsGenerative AI Risks & Concerns
Generative AI Risks & Concerns
Ajitesh Kumar2.6K vues
AI and ML Series - Leveraging Generative AI and LLMs Using the UiPath Platfor... par DianaGray10
AI and ML Series - Leveraging Generative AI and LLMs Using the UiPath Platfor...AI and ML Series - Leveraging Generative AI and LLMs Using the UiPath Platfor...
AI and ML Series - Leveraging Generative AI and LLMs Using the UiPath Platfor...
DianaGray10305 vues
UNLEASHING INNOVATION Exploring Generative AI in the Enterprise.pdf par Hermes Romero
UNLEASHING INNOVATION Exploring Generative AI in the Enterprise.pdfUNLEASHING INNOVATION Exploring Generative AI in the Enterprise.pdf
UNLEASHING INNOVATION Exploring Generative AI in the Enterprise.pdf
Hermes Romero461 vues
Future of AI - 2023 07 25.pptx par Greg Makowski
Future of AI - 2023 07 25.pptxFuture of AI - 2023 07 25.pptx
Future of AI - 2023 07 25.pptx
Greg Makowski3.4K vues
AI and ML Series - Introduction to Generative AI and LLMs - Session 1 par DianaGray10
AI and ML Series - Introduction to Generative AI and LLMs - Session 1AI and ML Series - Introduction to Generative AI and LLMs - Session 1
AI and ML Series - Introduction to Generative AI and LLMs - Session 1
DianaGray101.2K vues
The Future of AI is Generative not Discriminative 5/26/2021 par Steve Omohundro
The Future of AI is Generative not Discriminative 5/26/2021The Future of AI is Generative not Discriminative 5/26/2021
The Future of AI is Generative not Discriminative 5/26/2021
Steve Omohundro960 vues
Nasscom AI top 50 use cases par ADDI AI 2050
Nasscom AI top 50 use casesNasscom AI top 50 use cases
Nasscom AI top 50 use cases
ADDI AI 20501.6K vues

Similaire à DevDive_UnleashthFullPotentialofAutomationwithGenAI.pptx

Hackaton Moonshots - 06222023.pdf par
Hackaton Moonshots - 06222023.pdfHackaton Moonshots - 06222023.pdf
Hackaton Moonshots - 06222023.pdfRohit Radhakrishnan
272 vues16 diapositives
HyperHack 2023 Global Presentation - AMER Enablement_070623.pdf par
HyperHack 2023 Global Presentation - AMER Enablement_070623.pdfHyperHack 2023 Global Presentation - AMER Enablement_070623.pdf
HyperHack 2023 Global Presentation - AMER Enablement_070623.pdfDianaGray10
190 vues33 diapositives
DU PPT (1).pptx par
DU PPT (1).pptxDU PPT (1).pptx
DU PPT (1).pptxRohit Radhakrishnan
156 vues47 diapositives
Intelligent Automation in Accounting and Finance with IMA Queens College Stud... par
Intelligent Automation in Accounting and Finance with IMA Queens College Stud...Intelligent Automation in Accounting and Finance with IMA Queens College Stud...
Intelligent Automation in Accounting and Finance with IMA Queens College Stud...Diana Gray, MBA
199 vues29 diapositives
Dev Dives: Unlock AI-driven automation with semantic automation & communicati... par
Dev Dives: Unlock AI-driven automation with semantic automation & communicati...Dev Dives: Unlock AI-driven automation with semantic automation & communicati...
Dev Dives: Unlock AI-driven automation with semantic automation & communicati...Cristina Vidu
638 vues27 diapositives
Entering the Conversational Era with Chatbots for the Enterprise par
Entering the Conversational Era with Chatbots for the EnterpriseEntering the Conversational Era with Chatbots for the Enterprise
Entering the Conversational Era with Chatbots for the EnterpriseAleisha McKeeby
480 vues39 diapositives

Similaire à DevDive_UnleashthFullPotentialofAutomationwithGenAI.pptx(20)

HyperHack 2023 Global Presentation - AMER Enablement_070623.pdf par DianaGray10
HyperHack 2023 Global Presentation - AMER Enablement_070623.pdfHyperHack 2023 Global Presentation - AMER Enablement_070623.pdf
HyperHack 2023 Global Presentation - AMER Enablement_070623.pdf
DianaGray10190 vues
Intelligent Automation in Accounting and Finance with IMA Queens College Stud... par Diana Gray, MBA
Intelligent Automation in Accounting and Finance with IMA Queens College Stud...Intelligent Automation in Accounting and Finance with IMA Queens College Stud...
Intelligent Automation in Accounting and Finance with IMA Queens College Stud...
Diana Gray, MBA199 vues
Dev Dives: Unlock AI-driven automation with semantic automation & communicati... par Cristina Vidu
Dev Dives: Unlock AI-driven automation with semantic automation & communicati...Dev Dives: Unlock AI-driven automation with semantic automation & communicati...
Dev Dives: Unlock AI-driven automation with semantic automation & communicati...
Cristina Vidu638 vues
Entering the Conversational Era with Chatbots for the Enterprise par Aleisha McKeeby
Entering the Conversational Era with Chatbots for the EnterpriseEntering the Conversational Era with Chatbots for the Enterprise
Entering the Conversational Era with Chatbots for the Enterprise
Aleisha McKeeby480 vues
UiPath Document Understanding_Day 3.pptx par UiPathCommunity
UiPath Document Understanding_Day 3.pptxUiPath Document Understanding_Day 3.pptx
UiPath Document Understanding_Day 3.pptx
UiPathCommunity101 vues
Introduction to RPA and Document Understanding par DianaGray10
Introduction to RPA and Document UnderstandingIntroduction to RPA and Document Understanding
Introduction to RPA and Document Understanding
DianaGray1064 vues
Systems Analysis And Role Of The Systems Analyst par Ashley Lovato
Systems Analysis And Role Of The Systems AnalystSystems Analysis And Role Of The Systems Analyst
Systems Analysis And Role Of The Systems Analyst
Ashley Lovato3 vues
Introduction to RPA and Document Understanding par Diana Gray, MBA
Introduction to RPA and Document UnderstandingIntroduction to RPA and Document Understanding
Introduction to RPA and Document Understanding
Diana Gray, MBA604 vues
Improve Employee Self Service With Bolt On Applications par LBi Software
Improve Employee Self Service With Bolt On Applications Improve Employee Self Service With Bolt On Applications
Improve Employee Self Service With Bolt On Applications
LBi Software1.9K vues
FATE_Foundation_it-strategy-oct2013-part1 par Aide Ojigbede
FATE_Foundation_it-strategy-oct2013-part1FATE_Foundation_it-strategy-oct2013-part1
FATE_Foundation_it-strategy-oct2013-part1
Aide Ojigbede317 vues
Workshop on requirements and modeling at HAE 2015 par Olivier Béghain
Workshop on requirements and modeling at HAE 2015Workshop on requirements and modeling at HAE 2015
Workshop on requirements and modeling at HAE 2015
Olivier Béghain533 vues
Black Friday - MuleSoft Automation.pdf par Amir Khan
Black Friday - MuleSoft Automation.pdfBlack Friday - MuleSoft Automation.pdf
Black Friday - MuleSoft Automation.pdf
Amir Khan249 vues
Real time insights for better products, customer experience and resilient pla... par Balvinder Hira
Real time insights for better products, customer experience and resilient pla...Real time insights for better products, customer experience and resilient pla...
Real time insights for better products, customer experience and resilient pla...
Balvinder Hira107 vues
Secure Your Environment with UiPath and CyberArk Technologies par DianaGray10
Secure Your Environment with UiPath and CyberArk TechnologiesSecure Your Environment with UiPath and CyberArk Technologies
Secure Your Environment with UiPath and CyberArk Technologies
DianaGray1037 vues
Digital Transformation Services and Solutions - Chatbot Development par PrajaktaKulkarni55
Digital Transformation Services and Solutions - Chatbot DevelopmentDigital Transformation Services and Solutions - Chatbot Development
Digital Transformation Services and Solutions - Chatbot Development
IO Journey All Up par baselsss
IO Journey All UpIO Journey All Up
IO Journey All Up
baselsss121 vues
Biz Nova It Project Bonus Slides par TyHowardPMP
Biz Nova It Project Bonus SlidesBiz Nova It Project Bonus Slides
Biz Nova It Project Bonus Slides
TyHowardPMP317 vues

Plus de Rohit Radhakrishnan

UiPath Devops.pptx par
UiPath Devops.pptxUiPath Devops.pptx
UiPath Devops.pptxRohit Radhakrishnan
344 vues12 diapositives
UiPath Test Suite_final.pptx par
UiPath Test Suite_final.pptxUiPath Test Suite_final.pptx
UiPath Test Suite_final.pptxRohit Radhakrishnan
104 vues16 diapositives
UiPath Test Manager Connect Webinar UiPath Planview.pptx par
UiPath Test Manager Connect Webinar UiPath Planview.pptxUiPath Test Manager Connect Webinar UiPath Planview.pptx
UiPath Test Manager Connect Webinar UiPath Planview.pptxRohit Radhakrishnan
122 vues25 diapositives
uipath_insights_upgrade.pptx par
uipath_insights_upgrade.pptxuipath_insights_upgrade.pptx
uipath_insights_upgrade.pptxRohit Radhakrishnan
135 vues15 diapositives
UiPath Marketplace - HyperHack 2023.pptx par
UiPath Marketplace - HyperHack 2023.pptxUiPath Marketplace - HyperHack 2023.pptx
UiPath Marketplace - HyperHack 2023.pptxRohit Radhakrishnan
103 vues34 diapositives
UiPath_Orchestrtor_Upgrade_IAAS_PAAS.pptx par
UiPath_Orchestrtor_Upgrade_IAAS_PAAS.pptxUiPath_Orchestrtor_Upgrade_IAAS_PAAS.pptx
UiPath_Orchestrtor_Upgrade_IAAS_PAAS.pptxRohit Radhakrishnan
199 vues17 diapositives

Plus de Rohit Radhakrishnan(20)

UiPath Test Manager Connect Webinar UiPath Planview.pptx par Rohit Radhakrishnan
UiPath Test Manager Connect Webinar UiPath Planview.pptxUiPath Test Manager Connect Webinar UiPath Planview.pptx
UiPath Test Manager Connect Webinar UiPath Planview.pptx
Automation Cloud Series - Mastering the Automation Cloud Admin experience_Ses... par Rohit Radhakrishnan
Automation Cloud Series - Mastering the Automation Cloud Admin experience_Ses...Automation Cloud Series - Mastering the Automation Cloud Admin experience_Ses...
Automation Cloud Series - Mastering the Automation Cloud Admin experience_Ses...
Maximizing efficiency and security in large-scale automation rollouts with Au... par Rohit Radhakrishnan
Maximizing efficiency and security in large-scale automation rollouts with Au...Maximizing efficiency and security in large-scale automation rollouts with Au...
Maximizing efficiency and security in large-scale automation rollouts with Au...
UiPath Automation Cloud Robots - Best Practises session 2.pptx par Rohit Radhakrishnan
UiPath Automation Cloud Robots - Best Practises session 2.pptxUiPath Automation Cloud Robots - Best Practises session 2.pptx
UiPath Automation Cloud Robots - Best Practises session 2.pptx
UiPath Automation Cloud - Best Practises session1.pptx par Rohit Radhakrishnan
UiPath Automation Cloud - Best Practises session1.pptxUiPath Automation Cloud - Best Practises session1.pptx
UiPath Automation Cloud - Best Practises session1.pptx
UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant... par Rohit Radhakrishnan
UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant...UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant...
UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant...
UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant... par Rohit Radhakrishnan
UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant...UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant...
UiPath 2022.10 Release – Updates with StudioX, Activities and Robot Assistant...

Dernier

Roadmap to Become Experts.pptx par
Roadmap to Become Experts.pptxRoadmap to Become Experts.pptx
Roadmap to Become Experts.pptxdscwidyatamanew
11 vues45 diapositives
Five Things You SHOULD Know About Postman par
Five Things You SHOULD Know About PostmanFive Things You SHOULD Know About Postman
Five Things You SHOULD Know About PostmanPostman
27 vues43 diapositives
The Research Portal of Catalonia: Growing more (information) & more (services) par
The Research Portal of Catalonia: Growing more (information) & more (services)The Research Portal of Catalonia: Growing more (information) & more (services)
The Research Portal of Catalonia: Growing more (information) & more (services)CSUC - Consorci de Serveis Universitaris de Catalunya
73 vues25 diapositives
Combining Orchestration and Choreography for a Clean Architecture par
Combining Orchestration and Choreography for a Clean ArchitectureCombining Orchestration and Choreography for a Clean Architecture
Combining Orchestration and Choreography for a Clean ArchitectureThomasHeinrichs1
69 vues24 diapositives
.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV par
.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV
.conf Go 2023 - How KPN drives Customer Satisfaction on IPTVSplunk
88 vues20 diapositives
Uni Systems for Power Platform.pptx par
Uni Systems for Power Platform.pptxUni Systems for Power Platform.pptx
Uni Systems for Power Platform.pptxUni Systems S.M.S.A.
50 vues21 diapositives

Dernier(20)

Five Things You SHOULD Know About Postman par Postman
Five Things You SHOULD Know About PostmanFive Things You SHOULD Know About Postman
Five Things You SHOULD Know About Postman
Postman27 vues
Combining Orchestration and Choreography for a Clean Architecture par ThomasHeinrichs1
Combining Orchestration and Choreography for a Clean ArchitectureCombining Orchestration and Choreography for a Clean Architecture
Combining Orchestration and Choreography for a Clean Architecture
.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV par Splunk
.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV
.conf Go 2023 - How KPN drives Customer Satisfaction on IPTV
Splunk88 vues
AI: mind, matter, meaning, metaphors, being, becoming, life values par Twain Liu 刘秋艳
AI: mind, matter, meaning, metaphors, being, becoming, life valuesAI: mind, matter, meaning, metaphors, being, becoming, life values
AI: mind, matter, meaning, metaphors, being, becoming, life values
The details of description: Techniques, tips, and tangents on alternative tex... par BookNet Canada
The details of description: Techniques, tips, and tangents on alternative tex...The details of description: Techniques, tips, and tangents on alternative tex...
The details of description: Techniques, tips, and tangents on alternative tex...
BookNet Canada121 vues
Future of Learning - Yap Aye Wee.pdf par NUS-ISS
Future of Learning - Yap Aye Wee.pdfFuture of Learning - Yap Aye Wee.pdf
Future of Learning - Yap Aye Wee.pdf
NUS-ISS41 vues
handbook for web 3 adoption.pdf par Liveplex
handbook for web 3 adoption.pdfhandbook for web 3 adoption.pdf
handbook for web 3 adoption.pdf
Liveplex19 vues
.conf Go 2023 - Data analysis as a routine par Splunk
.conf Go 2023 - Data analysis as a routine.conf Go 2023 - Data analysis as a routine
.conf Go 2023 - Data analysis as a routine
Splunk93 vues
Understanding GenAI/LLM and What is Google Offering - Felix Goh par NUS-ISS
Understanding GenAI/LLM and What is Google Offering - Felix GohUnderstanding GenAI/LLM and What is Google Offering - Felix Goh
Understanding GenAI/LLM and What is Google Offering - Felix Goh
NUS-ISS41 vues
Business Analyst Series 2023 - Week 3 Session 5 par DianaGray10
Business Analyst Series 2023 -  Week 3 Session 5Business Analyst Series 2023 -  Week 3 Session 5
Business Analyst Series 2023 - Week 3 Session 5
DianaGray10209 vues
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze par NUS-ISS
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng TszeDigital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze
Digital Product-Centric Enterprise and Enterprise Architecture - Tan Eng Tsze
NUS-ISS19 vues
Igniting Next Level Productivity with AI-Infused Data Integration Workflows par Safe Software
Igniting Next Level Productivity with AI-Infused Data Integration Workflows Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Safe Software225 vues
Black and White Modern Science Presentation.pptx par maryamkhalid2916
Black and White Modern Science Presentation.pptxBlack and White Modern Science Presentation.pptx
Black and White Modern Science Presentation.pptx

DevDive_UnleashthFullPotentialofAutomationwithGenAI.pptx

  • 1. Dev Dives Go deeper, automate smarter
  • 2. 2 Meet today’s team: Rohit Radhakrishnan Marketing Community Manager @UiPath Roxana Ivan Senior Product Marketing Manager @UiPath
  • 3. 3 Meet today’s speakers: Dhruv Patel Senior Sales Solution Architect @UiPath Russel Alfeche UiPath MVP Technology Leader RPA @qBotica
  • 4. 4 About today’s meeting • Enjoy the next 50-60 min packed with gen AI powered automations use cases, demos, and live Q&A. • Build your own Two Way Match Invoice Processing with UiPath+GenAI. You’ll receive the recording and the full pack of instructions to leverage the power of UiPath Document Understanding and GenAI to seamlessly process invoices. • Get answers to your questions and challenges. Please use the chat box for Qs during the presentation. Live Q&A session at the end. • You're encouraged to network and share your LinkedIn/Twitter in the chat. Have fun! Feedback is welcome.
  • 5. Unleash the full potential of your automations with generative AI UiPath Dev Dives Webinar Series
  • 6. 6 Poll time We’d love to know more about your experience with gen AI and automation! Take a quick poll by scanning the QR code or access it at https://www.menti.com/al1eexoy2cdr
  • 7. 7 Agenda 01 02 03 UiPath + generative AI, AI-powered automation 3 patterns for gen AI powered automations Demo time!
  • 8. 8 Explore Novel Use Cases Build Better Automations Faster UiPath Uses Gen AI in 3 Ways Generative AI Powered Automations Incorporating Gen AI directly into Business Automation Use Cases Supercharge Developer Productivity “Co-Pilot” Like experience bringing a user- friendly interface to building automations Product & Model Augmentation Add LLM capabilities to improve design time 1 2 3
  • 9. 9 AI-powered automation Open | Flexible | Responsible Supported by UiPath Built with UiPath or BYO BYO Docs Screens Tasks Processes Solutions AI Infrastructure Integration Service – Validation Station – Active learning – Fine tuning – Guardrails – Auditing AI-powered automation Delivering enterprise automation with Specialized AI Generative AI Specialized AI Context HITL UI API Action People Comms Docs Data Processes
  • 10. 10 Advantages of using UiPath with Gen AI for Automation More than calling a Generative AI Model Context Gathering Specialized Models Robots Do Work Human In The Loop Confidence in governance UiPath also has Specialized models to complement Gen AI interactions Gen AI needs context, UiPath can gather the context from all sources Gen AI is just a brain, Automation is the muscle that does the work Gen AI “hallucinates”. There are times you can not get things wrong Your business is governed with audit logs and controls while using Gen AI with UiPath
  • 11. 3 Patterns for Gen AI Powered Automations A use case may use 1 or multiple patterns Pattern 1 Reader / Writer Pattern 2 Pattern 3 Analyst / Doer Assistant UiPath can execute processes as a result of LLM calls UiPath can gather context from multiple sources to generate and distribute personalized messages UiPath can add context and action to conversational assistants UiPath Advantage Source 1 Source 2 Source 3 Source 4 LLM Ingest Analyze Data Next Best Action System 1 System 2 System 3 System 4 Do LLM System 1 System 2 System 3 System 4 Do Conversational Interface Human Knowledge Response Action OR Source 1 Source 2 Source 3 Source 4 LLM Read Write Emails Summaries Content
  • 12. 12 Pattern 1 - Reader / Writer Description: LLMs are great at taking context and generating personalized text, whether longer or shorter than the original context. UiPath is collecting all the relevant context and prompting the LLM for text. UiPath can keep a human in the loop to fine tune the output. Example Use Cases Cold Call Emails Gather context about your audience and generate email Customer Feedback Response Gather sentiment and customer history to generate tailored response Proposal Writer Combine multiple answers from your KB with additional context for a tailored answer to a proposal question Applicant Communications Combine feedback from interviewers, JD details, and applicant resume for tailored communications Customer Summary Summarize customer history, support ticket history, etc. for faster consumption by customer facing agents Email/PMO Summarizer Summarize information from PM tools, emails, other sources for faster executive overviews KYC Summarizer Gather and summarize materials from multiple sources for faster KYC review Compliance and ESG Reporting Monitor data and reports from multiple systems/source and generate consistent reporting Product Documentation Create and maintain product documentation summarizing information from feature tickets and marketing Fraud Communications Generate correspondence with customers collating information multiple systems Insurance Claims Communication Communicate to Customers around their claims request synthesizing information from multiple systems Healthcare Appeals Communication Tailor communications to customers about using information about the customer and the circumstance Human Input and Validation Human in the loop Source 1 Source 2 Source 3 Source 4 LLM Read Write Emails Summaries Content System 1 System 2 System 3 System 4 Distribute
  • 13. 13 Pattern 2 – Analyst / Doer Description: LLMs can generate structured output (data tables, code, XML/JSON) from multiple unstructured sources when prompted well. UiPath is collecting the relevant sources and prompting the LLM to generate structured outputs. Critically, UiPath can validate the contents of the structured outputs vs. systems of record or humans. UiPath can further execute processes based on the output. Source 1 Source 2 Source 3 Source 4 LLM Ingest Analyze Data Next Best Action System 1 System 2 System 3 System 4 Do/Validate Human Input and Validation Human in the loop Example Use Cases Multi-Source Report Creating Gather reporting from different systems, documents, and emails and combine them into one set Structuring and Normalizing Data Normalize data from different sources into a common schema 2 Way Match (Generic Reconciliation) Normalize data from multiple systems and further reconcile the two noting differences for humans to validate Contact Center Next Best Action Gather context from sources, recommend an action from a list and execute the action After Call Work (Action Item Doer) Extract actions from call scripts for follow-up. Execute those automatable. Upsell / Cross-sell Assistant Gather customer history and needs, generate a recommendation for what to sell, and a script to sell it Contract Extractor Extract structured data out of contracts / amendments, validate against sources, and input into systems Company Filing Extractor Extract key figures out of company filings, validate with human, and use in processes Test Data Creator Generate test data for application testing and insert it into the system using UiPath Generic Classifier Take in unstructured sources and classify against a list of defined options. Use this data as input for processes Competition Analysis Monitor pricing, news, reviews of competitors and extract structured findings Vendor Selection Analyze proposals from multiple vendors, extract key differentiations, and recommend a vendor
  • 14. 14 Pattern 3 - Assistant Description: The most common use case enterprises are building is a custom ChatGPT on their own knowledge sources. UiPath can augment and enrich these chat interfaces with more knowledge sources, either directly in the LLM or in the prompt. For assistant interactions that result in an action, UiPath be used for last-mile process execution. LLM System 1 System 2 System 3 System 4 Do Conversational Interface Human Knowledge Response Action OR Human in the loop Example Use Cases Knowledge Base Assistant Use UiPath to augment the knowledge accessible to the LLM. Vectorize databases or embed in the prompt. Support Escalation Assistant Variation of a Knowledge Base Assistant focused on customer support escalations. Learning Assistant UiPath can help find courses from different learning platforms and recommend one for a user Self Service Helpdesk LLMs will create enhanced assistant interfaces. Execute common tasks behind the scenes with UiPath. Employee Benefits Assistant Answer employee questions about benefits and automate benefit selection / changing Employee Travel Concierge UiPath can bring in context on travel policy and flight/hotel data to allow users to book compliant trips faster Legacy System Augmenter Legacy systems likely won’t have LLMs integrated. UiPath can be used to bring LLM experiences to old systems. Localization Assistant LLMs have become decent at localizing to different languages. UiPath can help validate the output against other tools Supply Chain Buyer Assistant A conversational interface help speed up inventory management and ordering across suppliers for buyers Personalized Assistant Use a conversational interface to perform more Reader/Writer and Analyzer/Doer actions Guided Form Entry A conversational interface collects & validates input from users. UiPath can input those answers into a system. Ask GPT (Document) Gather a specific document with automation and then allow users to ask questions about it
  • 16. 16 SAMPLE – Web Q&A Pattern 1 & 3
  • 17. 17 SAMPLE –Video Summarization, Image Generation Pattern 1 & 3
  • 18. 18 How does it work? Core Concept in NLP Embeddings Numerical Representation of the meanings of words or a group of words Used with semantic search to inject context nearest/relevant to the query into prompts (Context Injection)
  • 19. 19 Knowledgebase or data source can be documents, web pages, video transcripts, etc Generate most reliable answers with LLM completions by leveraging the primed prompt Context Injection Generate Answer Inject Context Semantic Search Ask Question Generate Embeddings Fetch KB, Data Source Call embeddings API to calculate the transcript's embeddings and load into a vector database Use the question as an input for semantic search/similarity. Get only most relevant chunks of tokens from the embeddings using the query as an input. The distance between embeddings carries semantic meaning Inject the context gathered from the search, along with the specific query, into the prompt to prime it Claude GPT Vertex AI … Pattern 3
  • 20. 20 2 Way Match Invoice Processing This process matches invoices to purchase orders to ensure accurate payment. This process ensures that only valid invoices with valid line items are paid, reducing the risk of fraud and errors; save time and money, and improve their relationships with business partners. Generative AI reduces the development complexity and enables developers to handle complex validation logic with natural language prompts! Increased Process Efficiency​ Improved Accuracy, Clear Compliance & Audit Trail Reduced Development Complexity Reduced Risk & Cost Savings Process: Invoice 2 Way Match & Gen AI Leverage the power of UiPath Document Understanding and Generative AI to seamlessly process invoices Natural language to prompt GenAI to handle the validation logic Automations handle processing, involving a human when needed Pattern 2
  • 21. 21 Pharmacovigilance (Adverse Events) Pharmacovigilance is a crucial process for monitoring the safety of approved drugs by systematically collecting and analyzing data on adverse drug reactions (ADRs) and other drug-related problems. MedDRA, a standardized medical terminology, plays a vital role in this process. It provides a common language for classifying and coding adverse events and medical conditions, ensuring consistent reporting. Automation + GenAI reduce the burden on clinicians, analysts and medical professionals during this process to intake adverse events & encode them in MedDRA, WHO DD, etc. & Gen AI Pattern 2
  • 22. 22 Date/Time Topic Status July 27, 10:30 AM EST / 3:30 PM GMT Empower your automation with Cloud Robots Register AMER Register EMEA & APAC August 31, 9:00 AM EST / 2:00 PM GMT Supercharge testing and RPA with coded automations Register AMER Register EMEA & APAC Next steps Download the automation template Two Way Match Invoice Processing: UiPath + GenAI > https://bit.ly/3JwLAnC Don't miss the next Dev Dives sessions. Save your seat > https://bit.ly/Dev-Dives_2023
  • 23. 23 CATEGORY 1: AI POWERED AUTOMATION SOLUTIONS CATEGORY 2: INNOVATE THROUGH CORE BUSINESS AUTOMATION SOLUTIONS AWARDS/CATEGORY: 🥇 1ST place: 4500 $ 🥇 2nd place: 3500 $ 🥇 3rd place: 1500 $ http://bit.ly/UiPath_Hyper_Hack_2023
  • 25. Thank you for your participation! Join us: community.uipath.com
  • 26. 26 MeetingAI How it works 20-30 minutes saved in follow-up per meeting! & Gen AI Zoom Recording Upload Post- meeting Triggers Automation Meeting Gen AI: Extract action items Summarize meeting Microsoft Azure OpenAI Gen AI: Compare action items to list of existing automations Get Documentation Microsoft Azure OpenAI Get meeting times Get recording link Compose email [Meeting Summary] [Follow-up items] [Action items] Less time spent on admin tasks after meetings Send email More time for account strategy, market research, meeting preparation List of Automations supplied by robot Pattern 1 & 2

Notes de l'éditeur

  1. Left - you can do now Productivity / product augmentation – what we’re working on / on the roadmap Classify – GPT Labeling – 50/50 both specialized / gpt comparing results Extraction – specialized model, much higher accuracy level, Validation – higher confidence level – have two models working together
  2. Have the platform that combines the power of AI and Automation – In order to maximize the value of AI, need robots and be able to set the context – need to show a specific example…! Secure AI – UiPath Value Prop Context for Prompt HITL Brains and Muscle Specialized Models like DU and Comms Mining Orchestrating all of this together If you could make your average X as good as your best X – human doing something awesome and they are reading or writing Person to another Person
  3. Generating text-based responses
  4. How can you extend the generative capabilities of large language models through UiPath. Although chat plugins as well as multi-modal capabilities of ChatGPT are within the horizon, what if we can achieve these features now with UiPath? Because Unless you’re subscribed to chatgpt plus, you won’t have access to early preview of plugins which lets the model browse the web But essentially how does these work, it turns out it’s a pretty simple flow leveraging one of the core concept in NLP which is embeddings using embeddings Web QnA: Question about the linked url (url docloader + embeddings api + chat completion)
  5. ChatGPT and even ChatGPTPlus doesn’t support image generation yet but there are available APIs that can do that which you can easily integrate UiPath with. Image Generation: Image generation (chat completion to create prompt + stable diffusion api to generate image from prompt) Image Interpretation: Image interpreter (visual qna transformer models + chat completion) Another example is youtube summrizer, even if you’re subscribed to chatGPT plus, I don’t think there’s a plugin already yet, at least that I know of. But with UiPath you can do these by integrating with native youtube doc loaders, along with embeddings YT Vid Summary: Summarize youtube vid using URL (yt docloader + embeddings api + chat completion)
  6. What is the common denominator for these samples? Embeddings, vector database, semantic search or similarity, context injection 1 Let’s talk about embeddings which is a core concept in NLP   2 Words such as beautiful, pretty, awesome, they have meanings, and consequently, synonyms and if you put words together to make up sentences, it will create a thought which may or may not represent a whole new meaning. 3 Basically, embeddings are numerical representations of the meanings of words or a group of words or thoughts, which are also called vectors 4 So essentially if you plot the embeddings of words in a graph… words that have close meanings generate nearby vectors if you plot them in a multidimensional graph. 5 these can then be used for semantic search or similarity, so that given a question… A large language model is a type of artificial intelligence model that is designed to understand and generate human language. It is trained on vast amounts of text data, such as books, articles, and websites, and uses statistical techniques to learn the patterns and structures of language. The goal of a large language model is to be able to generate new, coherent sentences that are similar in style and content to those found in the training data. Embeddings are a key component of large language models. They are a way of representing words as numerical vectors that capture their meaning and context. Each word in the model's vocabulary is assigned a unique vector, and these vectors are learned during the training process. The vectors are designed to be similar for words that have similar meanings or are used in similar contexts, and dissimilar for words that are unrelated.Embeddings are used in large language models to help the model understand the meaning and context of words in a sentence. When the model is given a sentence to generate, it uses the embeddings of the words in the sentence to predict the most likely next word. By using embeddings, the model is able to capture the nuances of language and generate sentences that are both grammatically correct and semantically meaningful. A large language model is a type of neural network that is designed to process and understand natural language. These models are trained on massive amounts of text data, such as books, articles, and websites, in order to learn the patterns and relationships between words and phrases.One important aspect of large language models is the use of word embeddings. Word embeddings are a way of representing words as numerical vectors, which can be used as input to the neural network. The idea behind word embeddings is to map semantically similar words to vectors that are close together in the vector space, so that the neural network can better understand the meaning of the words.For example, the words "cat" and "dog" might be mapped to vectors that are close together, since they are both animals that are often kept as pets. On the other hand, the word "car" might be mapped to a vector that is farther away, since it is not semantically related to "cat" or "dog".By using word embeddings, large language models are able to better understand the meaning of natural language text, and can perform tasks such as language translation, question answering, and text generation. ===
  7. What is one of the things rpa is best at? Data gathering and consolidation How automation can help LLMs generate more relevant information and prevent hallucination through embeddings Generate Embeddings from knowledgebase > Ask a question > Use semantic similarity for the question asked vs the embeddings > Get most relevant chunks of tokens from the embeddings > Use the relevant information gathered along with the question into the prompt > Generate answer Context Injection The benefit of context injection is it primes the prompt with very specific information to use for the answer and always use up to date answer, you don’t have to retrain the entire model in case there are new information from the database Essentially the model doesn't have to be fine-tuned since the prompt is fed with very specific context based on the question, to generate the most appropriate answer.
  8. Created by Dhruv Patel