The battle for RAG, explore the pros and cons of using KnowledgeGraphs and VectorDB in you RAG solution
- 3. AI empowered
List the top 3
contenders for the
data science position?
The top 3 contenders are:
1. Jordan Schlansky
2. Vince Mcmahon
3. Danny Duberstein
- 7. Ingestion
Text Embeddings
1.6, 0.42, 0.8, 1.04, 0.2
0.24, 1.3, 1.1, 0.6, 0.3
0.2, 0.81, 1.01, 0.3, 1.4
unstructured
- 10. Query
1.2, 0.3, 1.2, 0.73, 0.4
User question
Semantic search
K nearest neighbor
Embeddings
Context
- 14. 1. Naive
Q: Fetch the latest 5 published articles
Q: Recommend painkillers
which wouldn’t conflict with
the current meds patient X is taking.
- 15. 2. Unaware of the domain
1. SpO2: 95%
2. PaO2: 80 mmHg
3. PaCO2: 40 mmHg
4. pH: 7.35
5. HCO3: 22
6. HR: 88
7. BP: 100 mmHg
8. RR: 15
Q: Which patient might be at risk ?
- 16. 3. Can’t see the entire dataset
Q: How many employers does company X has?
Q: Which article got the most reviews?
Q: Will a change in module A effect module Z?
- 17. Q: What’s Napoleon’s surname ?
4. Large token overhead
French Empire as
Emperor of the
French from 1804
until 1814, and
briefly again in
1815. His political
and cultural legacy
endures as a
celebrated and
controversial
Napoleon
Bonaparte (born
Napoleone di
Buonaparte;
[1][b]
15 August 1769 –
5 May 1821), later
known by his
regnal name
Napoleon I, was
considered one of
the greatest military
commanders in
history and his wars
and campaigns are
still studied at
military schools
worldwide.
However, historians
still debate the
Bonaparte
- 18. There’s a real problem relaying on this approach
● In the “best” scenario the system will not provide an answer to a question,
saying I don’t know.
● Far worse the system will come up with half truths, providing us with false
information which we might act on.
Vector conclusion
- 26. How to create Knowledge Graph from unstructured data?
How do I maintain knowledge overtime ?
Graph generation
- 28. Q&A
Q: Who fought in the most recent match?
Graph: In the most recent match, Derek Brunson fought against Kevin Holland.
(20 March 2021)
Vector: The most recent match was fought between Markus Perez and Dalcha
Lungiambula.
(20 January 2021)
- 29. Q: Which fighter holds the fastest win?
Graph: The fighter who holds the fastest win is Jorge Masvidal, with a win in just
5 second
Vector:
The fighter with the fastest win, based on the provided context, is Andre Winner,
who won by KO/TKO against Rolando Delgado. The fight was concluded at 202
seconds into the first round.
Q&A
- 30. Q: Which fight had a clear underdog who’ve yet won the match?
Graph: In a fight where the victory was seemingly against the odds, Dan Severn
emerged as the clear underdog yet managed to secure a win against Ken
Shamrock. This was indicated by the comparison of their SLpM and TD_Avg.
Q&A
- 31. Q: Which fight had a clear underdog who’ve yet won the match?
Vector: Based on the information provided, identifying the fight with a clear underdog who then won the match requires assessing disparities in performance metrics or
fight outcomes that might suggest an unexpected victory. However, without explicit pre-fight odds or narratives indicating an underdog status, determining an "underdog"
victory from statistical data alone can be challenging, especially when fights end in decisions that don't necessarily reflect a dominant performance against the odds.
Looking at standout performances against expectations or significant performance turnarounds within the provided context might help, yet the data gives us detailed stats
rather than pre-fight expectations. One classic sign of an underdog victory might be a lower overall statistical expectation ending in a KO/TKO, suggesting a turnaround.
One instance noted is the fight between Belal Muhammad and Vicente Luque, where Luque won by KO/TKO in the first round at 79 seconds despite the fight's short duration
giving limited insight into the performance metrics before the finishing moment. However, labeling Luque as an "underdog" without pre-fight odds or broader fight context is
speculative.
The provided data focuses on fight statistics like significant strikes, control time, and method of victory without explicitly indicating favorites or underdogs. In Mixed Martial Arts
(MMA), unexpected victories often stand out due to knockout power or submission skills that defy statistical trends, but these aspects aren't directly reflected in the metrics
provided.
Without clear indicators of expectations versus outcomes, or a narrative context surrounding each fight, it's difficult to definitively pinpoint a fight featuring a clear underdog
who won.
Q&A
- 32. Q: List fighters who had a trilogy match
Graph: Matt Hughes vs. Georges St-Pierre
Daniel Cormier vs. Stipe Miocic
Junior Dos Santos vs. Cain Velasquez
Q&A
- 33. Q: List fighters who had a trilogy match
Vector: Based on the given context, identifying specific fighters who have had a trilogy match (three matches against the same opponent) within the
dataset provided is not directly possible. The context supplied is a list of fight statistics for various matchups but does not detail multiple matches
between the same pairs of fighters or explicitly label any series of fights as part of a trilogy.
To determine trilogy matches, one would typically look for repeated occurrences where the same pair of `B_fighter` and `R_fighter` appear against
each other across different dates. However, this dataset does not reveal any such repeated pairings from the given entries, or at least, such analysis
would require additional processing to identify any repeating matchups, assuming the data spans all fights in such trilogies. Moreover, the context
provided lists each fight as a separate entry without linking multiple entries to indicate ongoing rivalries or sequential matchups.
In the world of mixed martial arts (MMA), trilogies are often highlighted and marketed due to the evolving nature of the competition between two
fighters. They typically occur after both fighters have one win against each other, leading to a third match to break the tie or due to the competitive and
entertaining nature of their previous encounters that demand a rematch.
Without further data linking fights into series or direct mention of such trilogies in the supplied context, identifying fighters with trilogy matches within
this dataset is not feasible.
Q&A