公式動画ピックアップ
AAPL
ADBE
ADSK
AIG
AMGN
AMZN
BABA
BAC
BL
BOX
C
CHGG
CLDR
COKE
COUP
CRM
CROX
DDOG
DELL
DIS
DOCU
DOMO
ESTC
F
FIVN
GILD
GRUB
GS
GSK
H
HD
HON
HPE
HSBC
IBM
INST
INTC
INTU
IRBT
JCOM
JNJ
JPM
LLY
LMT
M
MA
MCD
MDB
MGM
MMM
MSFT
MSI
NCR
NEM
NEWR
NFLX
NKE
NOW
NTNX
NVDA
NYT
OKTA
ORCL
PD
PG
PLAN
PS
RHT
RNG
SAP
SBUX
SHOP
SMAR
SPLK
SQ
TDOC
TEAM
TSLA
TWOU
TWTR
TXN
UA
UAL
UL
UTX
V
VEEV
VZ
WDAY
WFC
WK
WMT
WORK
YELP
ZEN
ZM
ZS
ZUO
公式動画＆関連する動画 [5 Core Embeddings Choices for Developers | MongoDB.local San Francisco 2026]
Watch more from .local San Francisco → https://www.youtube.com/playlist?list=PL4RCxklHWZ9s7IrElTzddaZ2w5uupd6TQ
Subscribe to MongoDB YouTube→ https://mdb.link/subscribe
Building with embeddings introduces a set of foundational decisions that shape the behavior and performance of AI applications. In this session, Pete Johnson, MongoDB Field CTO for AI, will explore important embedding considerations and how they fit into real-world AI system design. Attendees can expect perspective on how these choices show up in practice, without focusing on a single implementation or approach.
00:00:00 Introduction: Vector Search for Developers
00:02:52 The Evolution of RAG and AI Agents
00:05:20 Moving Beyond Lexical Search to Semantic Vector Search
00:07:44 Choice 1: Selecting the Right Similarity Function
00:10:41 Choice 2: Effective Chunking and Contextualized Embeddings
00:12:54 Choice 3: Optimizing Dimensions with Matryoshka Representation Learning (MRL)
00:14:47 Choice 4: Managing Performance with Scalar and Binary Quantization
00:16:17 Choice 5: Improving Search Accuracy with Re-rankers
00:17:49 Conclusion: Resources for MongoDB and Voyage AI
Visit Mongodb.com → https://mdb.link/MongoDB
Read the MongoDB Blog → https://mdb.link/Blog
Read the Developer Blog → https://mdb.link/developerblog
398
15