SlideShare a Scribd company logo
29/10/2023
Alessandro Benedetti
When SDMX Meets AI:
Leveraging Open Source LLMs to Make Official
Statistics More Accessible and Discoverable
9th SDMX Global Conference
‣ Born in Tarquinia (ancient Etruscan city in Italy)
‣ R&D Software Engineer
‣ Director
‣ Master degree in Computer Science
‣ PC member for ECIR, SIGIR and Desires
‣ Apache Lucene/Solr PMC member/committer
‣ Elasticsearch/OpenSearch expert
‣ Semantic search, NLP, Machine Learning
technologies passionate
‣ Beach Volleyball player and Snowboarder
ALESSANDRO BENEDETTI
WHO AM I ?
2
‣ Headquarter in London/distributed
‣ Open-source Enthusiasts
‣ Apache Lucene/Solr experts
‣ Elasticsearch/OpenSearch experts
‣ Community Contributors
‣ Active Researchers
‣ Hot Trends : Neural Search,
Natural Language Processing
Learning To Rank,
Document Similarity,
Search Quality Evaluation,
Relevance Tuning
SEArch SErvices
www.sease.io
3
AGENDA
4
LLMs and Open Source
SIS-CC to enable AI applications with SDMX
From Natural Language to structured queries
Findings and future Works
AI, Machine learning and Deep Learning
https://sease.io/2021/07/artificial-intelligence-applied-to-search-introduction.html
WHAT IS A LARGE LANGUAGE MODEL?
● Transformers
● Next-token-prediction and masked-
language-modeling
● estimate the likelihood of each possible
word (in its vocabulary) given the
previous sequence
● learn the statistical structure of
language
● pre-trained on huge quantities of text
https://towardsdatascience.com/how-chatgpt-works-the-models-behind-the-bot-1ce5fca96286
OPEN SOURCE LARGE LANGUAGE MODELS
Search + LLMs KPI’s:
Operational
Search Session
Improve Search-driven
Business Metrics.
What KPI’s specific to
LLMs?
What Data metrics?
Combine Metric for
Business?
Focus on limited KPI’s
that impact business.
Track customers onsite
Behaviors for positive or
negative trends.
https://sease.io/2023/06/how-to-choose-the-right-large-language-model-for-your-domain-open-
source-edition.html
● Generalists
○ Falcon
○ LLaMA
■ alpaca
■ vicuna
… many others!
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
Search + LLMs KPI’s:
Operational
Search Session
Improve Search-driven
Business Metrics.
What KPI’s specific to
LLMs?
What Data metrics?
Combine Metric for
Business?
Focus on limited KPI’s
that impact business.
Track customers onsite
Behaviors for positive or
negative trends.
● OECD lead initiative (The Organisation for
Economic Co-operation and Development)
● The Statistical Information System Collaboration
Community
● .Stat Suite and Apache Solr
https://siscc.org/developers/technology/
SIS-CC TO ENABLE AI APPLICATIONS WITH SDMX
POC
Use case example
Natural language query:
What were the sulfur oxide emissions in
Australia in 2013?
2 Requests to LLM
Search API
GENERATIVE EXTRACTIVE
{ "name":"Emissions of air pollutants",
"id":"ds-siscc-qa:DF_AIR_EMISSIONS"}] },
"Dimensions":[ "Country", "Pollutant", "Unit", "Year"]}, …
Statistic
Filters
{
"Country": ["0|Australia#AUS#"],
"Pollutant": ["0|Sulphur Oxides#SOX#"],
"Unit Of measure": ["0|Total man-made emissions#TOT#"],
"Year": "2013"
}
FROM NATURAL LANGUAGE TO STRUCTURED QUERIES
● How do you update this approach in time?
● New large language models?
● Better prompts?
● How to fit user interactions?
IMPROVING OVER TIME
RESULTS: What were the sulfur oxide emissions in Australia in 2013
GPT Generative answer is:
['Sulfur dioxide emissions', 'Air
pollution', 'Environmental impact', 'Fossil
fuel combustion', 'Acid rain']
GPT Extractive answer is:
{'srQMgwl_en_ss': ['1|Environment#ENV#|Air
and climate#ENV_AC#'], 'dimensions_en_ss':
['Time period', 'Reference area',
'Pollutant', 'Country']}
Dataflow retrieved is:
[{'id': 'ds-siscc-qa:DF_AIR_EMISSIONS', 'name':
'Emissions of air pollutants', 'description':
''}]
4 dimensions are available for the above
dataflow:
['Country', 'Year', 'Pollutant', 'Variable']
{
"dataflow": [
{
"description": "",
"id": "ds-siscc-qa:DF_AIR_EMISSIONS",
"name": "Emissions of air pollutants"
}
],
"filters": {
"Country": "0|Australia#AUS#",
"Pollutant": "0|Sulphur Oxides#SOX#",
"Variable": "0|Total man-made emissions#TOT#",
"Year": "2013"
},
"natural_language_query": "What were the sulfur oxide
emissions in Australia in 2013"
}
● Promising! - LLM are good in query expansion (generative or extractive)
● gpt-3.5-turbo-instruct -> new models can do much better!
● 4k tokens - (for both prompt and response) is not enough
● Mistakes - Some times dimension values are associated to the wrong dimension,
more prompt engineering!
FINDINGS
● [Solr] Fine-tune the dimension retrieval Solr query
● [LLM] Select the best model to date - Explore the State of the Art (both commercially and
Open source)
● [LLM] Refine the prompts according to the model
● [LLM] Implement integration tests with the most common failures -> LLM/prompt
engineering to solve them
● [Solr] Finalising the dataflow retrieval Solr query
● [Performance] Stress test the solution
● [Quality] Set up queries/expected documents
THE ROAD TO PRODUCTION
● StatsBot - More conversation!
● Retrieval Augmented Generation
● Results Summarization
FUTURE WORKS

More Related Content

Similar to When SDMX meets AI-Leveraging Open Source LLMs To Make Official Statistics More Accessible And Discoverable.pptx

Copenhagen business school drives sustainability at roskilde festival using c...
Copenhagen business school drives sustainability at roskilde festival using c...Copenhagen business school drives sustainability at roskilde festival using c...
Copenhagen business school drives sustainability at roskilde festival using c...
Carlos Tomas
 
DSpace-CRIS: An Open Source Solution for Research - @THETA15
DSpace-CRIS: An Open Source Solution for Research - @THETA15DSpace-CRIS: An Open Source Solution for Research - @THETA15
DSpace-CRIS: An Open Source Solution for Research - @THETA15
Michele Mennielli
 
Osgis2011 edina addy_pope
Osgis2011 edina addy_popeOsgis2011 edina addy_pope
Osgis2011 edina addy_pope
Addy Pope
 
Osgis2011 edina addy_pope
Osgis2011 edina addy_popeOsgis2011 edina addy_pope
Osgis2011 edina addy_popeAddy Pope
 
Introduction to Open Source GIS
Introduction to Open Source GISIntroduction to Open Source GIS
Introduction to Open Source GIS
SANGHEE SHIN
 
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
multimediaeval
 
Internet of manufacturing and Open Source
Internet of manufacturing and Open SourceInternet of manufacturing and Open Source
Internet of manufacturing and Open Source
Ian Skerrett
 
Summer school bz_fp7research_20100708
Summer school bz_fp7research_20100708Summer school bz_fp7research_20100708
Summer school bz_fp7research_20100708
Sandro D'Elia
 
Osgis 10 arnulf-christl
Osgis 10 arnulf-christlOsgis 10 arnulf-christl
Osgis 10 arnulf-christl
Arnulf Christl
 
What is Openness in OGC, OSGeo and OSM
What is Openness in OGC, OSGeo and OSMWhat is Openness in OGC, OSGeo and OSM
What is Openness in OGC, OSGeo and OSM
Arnulf Christl
 
Eclipse Legal Day - Nov 2013
Eclipse Legal Day - Nov 2013Eclipse Legal Day - Nov 2013
Eclipse Legal Day - Nov 2013
Mike Milinkovich
 
Software Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceSoftware Sustainability: Better Software Better Science
Software Sustainability: Better Software Better Science
Carole Goble
 
Will Postgres Live Forever?
Will Postgres Live Forever?Will Postgres Live Forever?
Will Postgres Live Forever?
EDB
 
ITAC 2016 Where Open Source Meets Audit Analytics
ITAC 2016 Where Open Source Meets Audit AnalyticsITAC 2016 Where Open Source Meets Audit Analytics
ITAC 2016 Where Open Source Meets Audit Analytics
Andrew Clark
 
OWF13 - What’s next for Open Source Communities?
OWF13 - What’s next for Open Source  Communities?OWF13 - What’s next for Open Source  Communities?
OWF13 - What’s next for Open Source Communities?
Paris Open Source Summit
 
Open AR Cloud One Year Since the Launch
Open AR Cloud One Year Since the LaunchOpen AR Cloud One Year Since the Launch
Open AR Cloud One Year Since the Launch
Open AR Cloud
 
Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...
Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...
Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...
Trivadis
 
E2D3 introduction
E2D3 introductionE2D3 introduction
E2D3 introduction
E2D3
 
Business X Design - People, Planet & Product
Business X Design - People, Planet & ProductBusiness X Design - People, Planet & Product
Business X Design - People, Planet & Product
Cyber-Duck
 

Similar to When SDMX meets AI-Leveraging Open Source LLMs To Make Official Statistics More Accessible And Discoverable.pptx (20)

Copenhagen business school drives sustainability at roskilde festival using c...
Copenhagen business school drives sustainability at roskilde festival using c...Copenhagen business school drives sustainability at roskilde festival using c...
Copenhagen business school drives sustainability at roskilde festival using c...
 
DSpace-CRIS: An Open Source Solution for Research - @THETA15
DSpace-CRIS: An Open Source Solution for Research - @THETA15DSpace-CRIS: An Open Source Solution for Research - @THETA15
DSpace-CRIS: An Open Source Solution for Research - @THETA15
 
Osgis2011 edina addy_pope
Osgis2011 edina addy_popeOsgis2011 edina addy_pope
Osgis2011 edina addy_pope
 
Osgis2011 edina addy_pope
Osgis2011 edina addy_popeOsgis2011 edina addy_pope
Osgis2011 edina addy_pope
 
Introduction to Open Source GIS
Introduction to Open Source GISIntroduction to Open Source GIS
Introduction to Open Source GIS
 
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
 
Internet of manufacturing and Open Source
Internet of manufacturing and Open SourceInternet of manufacturing and Open Source
Internet of manufacturing and Open Source
 
Summer school bz_fp7research_20100708
Summer school bz_fp7research_20100708Summer school bz_fp7research_20100708
Summer school bz_fp7research_20100708
 
Osgis 10 arnulf-christl
Osgis 10 arnulf-christlOsgis 10 arnulf-christl
Osgis 10 arnulf-christl
 
International Forum on E 2.0 - Mota Engil
International Forum on E 2.0 -  Mota EngilInternational Forum on E 2.0 -  Mota Engil
International Forum on E 2.0 - Mota Engil
 
What is Openness in OGC, OSGeo and OSM
What is Openness in OGC, OSGeo and OSMWhat is Openness in OGC, OSGeo and OSM
What is Openness in OGC, OSGeo and OSM
 
Eclipse Legal Day - Nov 2013
Eclipse Legal Day - Nov 2013Eclipse Legal Day - Nov 2013
Eclipse Legal Day - Nov 2013
 
Software Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceSoftware Sustainability: Better Software Better Science
Software Sustainability: Better Software Better Science
 
Will Postgres Live Forever?
Will Postgres Live Forever?Will Postgres Live Forever?
Will Postgres Live Forever?
 
ITAC 2016 Where Open Source Meets Audit Analytics
ITAC 2016 Where Open Source Meets Audit AnalyticsITAC 2016 Where Open Source Meets Audit Analytics
ITAC 2016 Where Open Source Meets Audit Analytics
 
OWF13 - What’s next for Open Source Communities?
OWF13 - What’s next for Open Source  Communities?OWF13 - What’s next for Open Source  Communities?
OWF13 - What’s next for Open Source Communities?
 
Open AR Cloud One Year Since the Launch
Open AR Cloud One Year Since the LaunchOpen AR Cloud One Year Since the Launch
Open AR Cloud One Year Since the Launch
 
Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...
Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...
Azure Days 2019: Azure Chatbot Development for Airline Irregularities (Remco ...
 
E2D3 introduction
E2D3 introductionE2D3 introduction
E2D3 introduction
 
Business X Design - People, Planet & Product
Business X Design - People, Planet & ProductBusiness X Design - People, Planet & Product
Business X Design - People, Planet & Product
 

More from Sease

Multi Valued Vectors Lucene
Multi Valued Vectors LuceneMulti Valued Vectors Lucene
Multi Valued Vectors Lucene
Sease
 
How To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With KibanaHow To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With Kibana
Sease
 
Introducing Multi Valued Vectors Fields in Apache Lucene
Introducing Multi Valued Vectors Fields in Apache LuceneIntroducing Multi Valued Vectors Fields in Apache Lucene
Introducing Multi Valued Vectors Fields in Apache Lucene
Sease
 
Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...
Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...
Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...
Sease
 
How does ChatGPT work: an Information Retrieval perspective
How does ChatGPT work: an Information Retrieval perspectiveHow does ChatGPT work: an Information Retrieval perspective
How does ChatGPT work: an Information Retrieval perspective
Sease
 
How To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With KibanaHow To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With Kibana
Sease
 
Neural Search Comes to Apache Solr
Neural Search Comes to Apache SolrNeural Search Comes to Apache Solr
Neural Search Comes to Apache Solr
Sease
 
Large Scale Indexing
Large Scale IndexingLarge Scale Indexing
Large Scale Indexing
Sease
 
Dense Retrieval with Apache Solr Neural Search.pdf
Dense Retrieval with Apache Solr Neural Search.pdfDense Retrieval with Apache Solr Neural Search.pdf
Dense Retrieval with Apache Solr Neural Search.pdf
Sease
 
Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...
Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...
Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...
Sease
 
Word2Vec model to generate synonyms on the fly in Apache Lucene.pdf
Word2Vec model to generate synonyms on the fly in Apache Lucene.pdfWord2Vec model to generate synonyms on the fly in Apache Lucene.pdf
Word2Vec model to generate synonyms on the fly in Apache Lucene.pdf
Sease
 
How to cache your searches_ an open source implementation.pptx
How to cache your searches_ an open source implementation.pptxHow to cache your searches_ an open source implementation.pptx
How to cache your searches_ an open source implementation.pptx
Sease
 
Online Testing Learning to Rank with Solr Interleaving
Online Testing Learning to Rank with Solr InterleavingOnline Testing Learning to Rank with Solr Interleaving
Online Testing Learning to Rank with Solr Interleaving
Sease
 
Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...
Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...
Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...
Sease
 
Apache Lucene/Solr Document Classification
Apache Lucene/Solr Document ClassificationApache Lucene/Solr Document Classification
Apache Lucene/Solr Document Classification
Sease
 
Advanced Document Similarity with Apache Lucene
Advanced Document Similarity with Apache LuceneAdvanced Document Similarity with Apache Lucene
Advanced Document Similarity with Apache Lucene
Sease
 
Search Quality Evaluation: a Developer Perspective
Search Quality Evaluation: a Developer PerspectiveSearch Quality Evaluation: a Developer Perspective
Search Quality Evaluation: a Developer Perspective
Sease
 
Introduction to Music Information Retrieval
Introduction to Music Information RetrievalIntroduction to Music Information Retrieval
Introduction to Music Information Retrieval
Sease
 
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Sease
 
Explainability for Learning to Rank
Explainability for Learning to RankExplainability for Learning to Rank
Explainability for Learning to Rank
Sease
 

More from Sease (20)

Multi Valued Vectors Lucene
Multi Valued Vectors LuceneMulti Valued Vectors Lucene
Multi Valued Vectors Lucene
 
How To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With KibanaHow To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With Kibana
 
Introducing Multi Valued Vectors Fields in Apache Lucene
Introducing Multi Valued Vectors Fields in Apache LuceneIntroducing Multi Valued Vectors Fields in Apache Lucene
Introducing Multi Valued Vectors Fields in Apache Lucene
 
Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...
Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...
Stat-weight Improving the Estimator of Interleaved Methods Outcomes with Stat...
 
How does ChatGPT work: an Information Retrieval perspective
How does ChatGPT work: an Information Retrieval perspectiveHow does ChatGPT work: an Information Retrieval perspective
How does ChatGPT work: an Information Retrieval perspective
 
How To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With KibanaHow To Implement Your Online Search Quality Evaluation With Kibana
How To Implement Your Online Search Quality Evaluation With Kibana
 
Neural Search Comes to Apache Solr
Neural Search Comes to Apache SolrNeural Search Comes to Apache Solr
Neural Search Comes to Apache Solr
 
Large Scale Indexing
Large Scale IndexingLarge Scale Indexing
Large Scale Indexing
 
Dense Retrieval with Apache Solr Neural Search.pdf
Dense Retrieval with Apache Solr Neural Search.pdfDense Retrieval with Apache Solr Neural Search.pdf
Dense Retrieval with Apache Solr Neural Search.pdf
 
Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...
Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...
Neural Search Comes to Apache Solr_ Approximate Nearest Neighbor, BERT and Mo...
 
Word2Vec model to generate synonyms on the fly in Apache Lucene.pdf
Word2Vec model to generate synonyms on the fly in Apache Lucene.pdfWord2Vec model to generate synonyms on the fly in Apache Lucene.pdf
Word2Vec model to generate synonyms on the fly in Apache Lucene.pdf
 
How to cache your searches_ an open source implementation.pptx
How to cache your searches_ an open source implementation.pptxHow to cache your searches_ an open source implementation.pptx
How to cache your searches_ an open source implementation.pptx
 
Online Testing Learning to Rank with Solr Interleaving
Online Testing Learning to Rank with Solr InterleavingOnline Testing Learning to Rank with Solr Interleaving
Online Testing Learning to Rank with Solr Interleaving
 
Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...
Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...
Rated Ranking Evaluator Enterprise: the next generation of free Search Qualit...
 
Apache Lucene/Solr Document Classification
Apache Lucene/Solr Document ClassificationApache Lucene/Solr Document Classification
Apache Lucene/Solr Document Classification
 
Advanced Document Similarity with Apache Lucene
Advanced Document Similarity with Apache LuceneAdvanced Document Similarity with Apache Lucene
Advanced Document Similarity with Apache Lucene
 
Search Quality Evaluation: a Developer Perspective
Search Quality Evaluation: a Developer PerspectiveSearch Quality Evaluation: a Developer Perspective
Search Quality Evaluation: a Developer Perspective
 
Introduction to Music Information Retrieval
Introduction to Music Information RetrievalIntroduction to Music Information Retrieval
Introduction to Music Information Retrieval
 
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
 
Explainability for Learning to Rank
Explainability for Learning to RankExplainability for Learning to Rank
Explainability for Learning to Rank
 

Recently uploaded

Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Tobias Schneck
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
Cheryl Hung
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
ControlCase
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
Frank van Harmelen
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
Ana-Maria Mihalceanu
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
Kari Kakkonen
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Jeffrey Haguewood
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Inflectra
 

Recently uploaded (20)

Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
Kubernetes & AI - Beauty and the Beast !?! @KCD Istanbul 2024
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Key Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdfKey Trends Shaping the Future of Infrastructure.pdf
Key Trends Shaping the Future of Infrastructure.pdf
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
PCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase TeamPCI PIN Basics Webinar from the Controlcase Team
PCI PIN Basics Webinar from the Controlcase Team
 
Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*Neuro-symbolic is not enough, we need neuro-*semantic*
Neuro-symbolic is not enough, we need neuro-*semantic*
 
Monitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR EventsMonitoring Java Application Security with JDK Tools and JFR Events
Monitoring Java Application Security with JDK Tools and JFR Events
 
DevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA ConnectDevOps and Testing slides at DASA Connect
DevOps and Testing slides at DASA Connect
 
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
Slack (or Teams) Automation for Bonterra Impact Management (fka Social Soluti...
 
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdfFIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
FIDO Alliance Osaka Seminar: The WebAuthn API and Discoverable Credentials.pdf
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered QualitySoftware Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
Software Delivery At the Speed of AI: Inflectra Invests In AI-Powered Quality
 

When SDMX meets AI-Leveraging Open Source LLMs To Make Official Statistics More Accessible And Discoverable.pptx

  • 1. 29/10/2023 Alessandro Benedetti When SDMX Meets AI: Leveraging Open Source LLMs to Make Official Statistics More Accessible and Discoverable 9th SDMX Global Conference
  • 2. ‣ Born in Tarquinia (ancient Etruscan city in Italy) ‣ R&D Software Engineer ‣ Director ‣ Master degree in Computer Science ‣ PC member for ECIR, SIGIR and Desires ‣ Apache Lucene/Solr PMC member/committer ‣ Elasticsearch/OpenSearch expert ‣ Semantic search, NLP, Machine Learning technologies passionate ‣ Beach Volleyball player and Snowboarder ALESSANDRO BENEDETTI WHO AM I ? 2
  • 3. ‣ Headquarter in London/distributed ‣ Open-source Enthusiasts ‣ Apache Lucene/Solr experts ‣ Elasticsearch/OpenSearch experts ‣ Community Contributors ‣ Active Researchers ‣ Hot Trends : Neural Search, Natural Language Processing Learning To Rank, Document Similarity, Search Quality Evaluation, Relevance Tuning SEArch SErvices www.sease.io 3
  • 4. AGENDA 4 LLMs and Open Source SIS-CC to enable AI applications with SDMX From Natural Language to structured queries Findings and future Works
  • 5. AI, Machine learning and Deep Learning https://sease.io/2021/07/artificial-intelligence-applied-to-search-introduction.html
  • 6. WHAT IS A LARGE LANGUAGE MODEL? ● Transformers ● Next-token-prediction and masked- language-modeling ● estimate the likelihood of each possible word (in its vocabulary) given the previous sequence ● learn the statistical structure of language ● pre-trained on huge quantities of text https://towardsdatascience.com/how-chatgpt-works-the-models-behind-the-bot-1ce5fca96286
  • 7. OPEN SOURCE LARGE LANGUAGE MODELS Search + LLMs KPI’s: Operational Search Session Improve Search-driven Business Metrics. What KPI’s specific to LLMs? What Data metrics? Combine Metric for Business? Focus on limited KPI’s that impact business. Track customers onsite Behaviors for positive or negative trends. https://sease.io/2023/06/how-to-choose-the-right-large-language-model-for-your-domain-open- source-edition.html ● Generalists ○ Falcon ○ LLaMA ■ alpaca ■ vicuna … many others! https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
  • 8. Search + LLMs KPI’s: Operational Search Session Improve Search-driven Business Metrics. What KPI’s specific to LLMs? What Data metrics? Combine Metric for Business? Focus on limited KPI’s that impact business. Track customers onsite Behaviors for positive or negative trends. ● OECD lead initiative (The Organisation for Economic Co-operation and Development) ● The Statistical Information System Collaboration Community ● .Stat Suite and Apache Solr https://siscc.org/developers/technology/ SIS-CC TO ENABLE AI APPLICATIONS WITH SDMX
  • 9. POC
  • 10. Use case example Natural language query: What were the sulfur oxide emissions in Australia in 2013? 2 Requests to LLM Search API GENERATIVE EXTRACTIVE { "name":"Emissions of air pollutants", "id":"ds-siscc-qa:DF_AIR_EMISSIONS"}] }, "Dimensions":[ "Country", "Pollutant", "Unit", "Year"]}, … Statistic Filters { "Country": ["0|Australia#AUS#"], "Pollutant": ["0|Sulphur Oxides#SOX#"], "Unit Of measure": ["0|Total man-made emissions#TOT#"], "Year": "2013" } FROM NATURAL LANGUAGE TO STRUCTURED QUERIES
  • 11. ● How do you update this approach in time? ● New large language models? ● Better prompts? ● How to fit user interactions? IMPROVING OVER TIME
  • 12. RESULTS: What were the sulfur oxide emissions in Australia in 2013 GPT Generative answer is: ['Sulfur dioxide emissions', 'Air pollution', 'Environmental impact', 'Fossil fuel combustion', 'Acid rain'] GPT Extractive answer is: {'srQMgwl_en_ss': ['1|Environment#ENV#|Air and climate#ENV_AC#'], 'dimensions_en_ss': ['Time period', 'Reference area', 'Pollutant', 'Country']} Dataflow retrieved is: [{'id': 'ds-siscc-qa:DF_AIR_EMISSIONS', 'name': 'Emissions of air pollutants', 'description': ''}] 4 dimensions are available for the above dataflow: ['Country', 'Year', 'Pollutant', 'Variable'] { "dataflow": [ { "description": "", "id": "ds-siscc-qa:DF_AIR_EMISSIONS", "name": "Emissions of air pollutants" } ], "filters": { "Country": "0|Australia#AUS#", "Pollutant": "0|Sulphur Oxides#SOX#", "Variable": "0|Total man-made emissions#TOT#", "Year": "2013" }, "natural_language_query": "What were the sulfur oxide emissions in Australia in 2013" }
  • 13. ● Promising! - LLM are good in query expansion (generative or extractive) ● gpt-3.5-turbo-instruct -> new models can do much better! ● 4k tokens - (for both prompt and response) is not enough ● Mistakes - Some times dimension values are associated to the wrong dimension, more prompt engineering! FINDINGS
  • 14. ● [Solr] Fine-tune the dimension retrieval Solr query ● [LLM] Select the best model to date - Explore the State of the Art (both commercially and Open source) ● [LLM] Refine the prompts according to the model ● [LLM] Implement integration tests with the most common failures -> LLM/prompt engineering to solve them ● [Solr] Finalising the dataflow retrieval Solr query ● [Performance] Stress test the solution ● [Quality] Set up queries/expected documents THE ROAD TO PRODUCTION
  • 15. ● StatsBot - More conversation! ● Retrieval Augmented Generation ● Results Summarization FUTURE WORKS