We collect cookies to analyze our website traffic and performance; we never collect any personal data. Cookie Policy
Accept
NEW YORK DAWN™NEW YORK DAWN™NEW YORK DAWN™
Notification Show More
Font ResizerAa
  • Home
  • Trending
  • New York
  • World
  • Politics
  • Business
    • Business
    • Economy
    • Real Estate
  • Crypto & NFTs
  • Tech
  • Lifestyle
    • Lifestyle
    • Food
    • Travel
    • Fashion
    • Art
  • Health
  • Sports
  • Entertainment
Reading: AI nonetheless has a hallucination drawback: How MongoDB goals to resolve it with superior rerankers and embedding fashions
Share
Font ResizerAa
NEW YORK DAWN™NEW YORK DAWN™
Search
  • Home
  • Trending
  • New York
  • World
  • Politics
  • Business
    • Business
    • Economy
    • Real Estate
  • Crypto & NFTs
  • Tech
  • Lifestyle
    • Lifestyle
    • Food
    • Travel
    • Fashion
    • Art
  • Health
  • Sports
  • Entertainment
Follow US
NEW YORK DAWN™ > Blog > Technology > AI nonetheless has a hallucination drawback: How MongoDB goals to resolve it with superior rerankers and embedding fashions
AI nonetheless has a hallucination drawback: How MongoDB goals to resolve it with superior rerankers and embedding fashions
Technology

AI nonetheless has a hallucination drawback: How MongoDB goals to resolve it with superior rerankers and embedding fashions

Last updated: February 25, 2025 12:33 am
Editorial Board Published February 25, 2025
Share
SHARE

To get the absolute best outcome from an AI question, organizations want the absolute best information.

The reply that many organizations have needed to overcome that problem is retrieval-augmented era (RAG). With RAG, outcomes are grounded in information from a database. Because it seems, although, not all RAG is similar, and really optimizing a database for the absolute best outcomes will be difficult.

Database vendor MongoDB isn’t any stranger to the world of AI or RAG. The corporate’s namesake database is already getting used for RAG, and MongoDB has additionally launched AI functions improvement initiatives. Whereas the corporate and its customers — such a medical big Novo Nordisk — have had success with gen AI, there may be nonetheless extra to be completed.

Particularly, hallucination and accuracy continues to be a problem holding some organizations again from getting gen AI into manufacturing. To that finish, MongoDB at present introduced the acquisition of privately-held Voyage AI, which develops superior embedding and retrieval fashions. Voyage raised $20 million in funding in Oct. 2024 in a spherical supported by cloud information big Snowflake. The acquisition will carry Voyage AI’s experience in embedding era and reranking — essential elements for AI-powered search and retrieval — instantly into MongoDB’s database platform.

“Over the last year, and especially as organizations have tried to think about how they could build AI powered applications, it became increasingly clear that the quality and trust of the applications they build, or the lack thereof, was becoming one of the barriers for applying AI to mission critical use cases,” MongoDB CPO Sahir Azam advised VentureBeat.

What are the challenges of hallucination? Doesn’t RAG resolve them?

The fundamental concept behind RAG is that, as an alternative of merely counting on a data base from skilled information, the gen AI engine can get grounded information from a database.

Creating extremely correct RAG is sort of complicated, and there may be nonetheless a possible danger for hallucinations — a problem confronted by MongoDB and its customers. Whereas Azam declined to supply any particular instance or incident the place gen AI RAG failed a consumer, he did notice that accuracy is all the time a priority.

Bettering accuracy and decreasing hallucination entails a number of steps. The primary is to enhance the standard of retrieval (the ‘R’ in RAG).

“In many cases, the retrieval quality is not good enough,” Tengyu Ma, founder and CEO of Voyage AI, advised VentureBeat. “In the retrieval step, if they are not retrieving relevant information, then the retrieval is not very useful, and the large language model (LLM) hallucinates because it has to guess some context.”

The Voyage AI fashions now a part of MongoDB assist enhance RAG in just a few key methods:

Area-specific fashions and re-rankers: These are skilled on massive quantities of unstructured information from particular verticals, permitting them to raised perceive the terminology and semantics of these domains.

Customization and fine-tuning:  Customers can superb tune the retrieval mechanism for distinctive datasets and use instances.

MongoDB’s competitors

MongoDB isn’t the primary or solely vendor to acknowledge the necessity for and worth of getting extremely optimized embedding and re-ranker expertise. In spite of everything, that’s one of many causes Snowflake invested in Voyage AI and is utilizing the corporate’s fashions. 

It’s necessary to notice that, even after being acquired by MongoDB, Voyage AI’s fashions will nonetheless be accessible to Snowflake and to Voyage AI’s different customers. The large distinction is that Voyage AI will now be more and more built-in into MongoDB’s database platforms. 

Instantly integrating superior embedding fashions in a database is an method taken by different rival database distributors, as nicely. Again in June 2024, DataStax introduced its personal RAGStack expertise that mixes superior embedding and retrieval fashions.

Azam argued that MongoDB is a bit totally different, although. For one, it’s an operational database, versus an analytical database. Additionally, versus simply offering insights and evaluation, MongoDB helps energy transactions and real-world operations. MongoDB can also be what is named a “document model database,” which has a unique construction than a standard relational database. That construction doesn’t depend on columns and tables, which aren’t notably good at representing details about unstructured information (a essential component for AI functions).

“We’re the only database technology that combines the management of metadata about a customer’s information, the operations and transactions, which is the heartbeat of what’s happening in the business, as well as the foundation for retrieval — all with a single system,” mentioned Azam.

Why Voyage AI issues for agentic AI workflows

The necessity for extremely correct embedding and retrieval fashions is being additional accelerated by agentic AI.

“Agentic AI still needs retrieval methods, because an agent cannot make decisions out of context,” mentioned Ma. “Sometimes, actually multiple retrieval components are used in even one decision.”

Ma famous that Voyage AI is presently engaged on particular fashions which are extremely custom-made for agentic AI use instances. He defined that agentic AI can use several types of queries that may nonetheless profit from extra optimization.

As gen AI more and more strikes into operational use instances, the necessity to take away the chance of hallucinations is clearly paramount. Whereas MongoDB has had success with gen AI, Azam expects the mixing of Voyage AI to open new mission essential use instances.

“If we can now say, ‘Hey, we can give you well north of 90% accuracy for your applications that today may only, in some cases, get to 30 or 60% accuracy for the results,’ the aperture widens in terms of the types of opportunities people can apply AI to in their software applications,” mentioned Azam.

Each day insights on enterprise use instances with VB Each day

If you wish to impress your boss, VB Each day has you coated. We provide the inside scoop on what corporations are doing with generative AI, from regulatory shifts to sensible deployments, so you’ll be able to share insights for max ROI.

An error occured.

Cut back mannequin integration prices whereas scaling AI: LangChain’s open ecosystem delivers the place closed distributors can’t

You Might Also Like

OpenAI launches analysis preview of Codex AI software program engineering agent for builders — with parallel tasking

Acer unveils AI-powered wearables at Computex 2025

Elon Musk’s xAI tries to elucidate Grok’s South African race relations freakout the opposite day

The $1 Billion database wager: What Databricks’ Neon acquisition means on your AI technique

Software program engineering-native AI fashions have arrived: What Windsurf’s SWE-1 means for technical decision-makers

TAGGED:advancedaimsembeddinghallucinationmodelsMongoDBproblemrerankerssolve
Share This Article
Facebook Twitter Email Print

Follow US

Find US on Social Medias
FacebookLike
TwitterFollow
YoutubeSubscribe
TelegramFollow
Popular News
From Burnout to Stability: 6 Self-Care Habits That’ll Change Your Life in 2025
Lifestyle

From Burnout to Stability: 6 Self-Care Habits That’ll Change Your Life in 2025

Editorial Board December 28, 2024
Echoing Conservative Grievances, Blackburn Miscasts Jackson’s Views
Trip Residence Safety: A Full Guidelines for Peace of Thoughts Whereas You are Away
Potential epigenetic biomarker discovered for preeclampsia in being pregnant
Is CBD use throughout being pregnant as secure as individuals suppose? New examine uncovers potential dangers to infants

You Might Also Like

Cut back mannequin integration prices whereas scaling AI: LangChain’s open ecosystem delivers the place closed distributors can’t
Technology

Cut back mannequin integration prices whereas scaling AI: LangChain’s open ecosystem delivers the place closed distributors can’t

May 16, 2025
Cut back mannequin integration prices whereas scaling AI: LangChain’s open ecosystem delivers the place closed distributors can’t
Technology

From OAuth bottleneck to AI acceleration: How CIAM options are eradicating the highest integration barrier in enterprise AI agent deployment

May 15, 2025
Take-Two studies stable earnings and explains GTA VI delay
Technology

Take-Two studies stable earnings and explains GTA VI delay

May 15, 2025
Nintendo opens a San Francisco retailer that may imply lots to followers | The DeanBeat
Technology

Nintendo opens a San Francisco retailer that may imply lots to followers | The DeanBeat

May 15, 2025

Categories

  • Health
  • Sports
  • Politics
  • Entertainment
  • Technology
  • World
  • Art

About US

New York Dawn is a proud and integral publication of the Enspirers News Group, embodying the values of journalistic integrity and excellence.
Company
  • About Us
  • Newsroom Policies & Standards
  • Diversity & Inclusion
  • Careers
  • Media & Community Relations
  • Accessibility Statement
Contact Us
  • Contact Us
  • Contact Customer Care
  • Advertise
  • Licensing & Syndication
  • Request a Correction
  • Contact the Newsroom
  • Send a News Tip
  • Report a Vulnerability
Term of Use
  • Digital Products Terms of Sale
  • Terms of Service
  • Privacy Policy
  • Cookie Settings
  • Submissions & Discussion Policy
  • RSS Terms of Service
  • Ad Choices
© 2024 New York Dawn. All Rights Reserved.
Welcome Back!

Sign in to your account

Lost your password?