MongoDB .local London 2019: Gaining ML insight on Google Cloud with Google Vision API and MongoDB
1 like170 views
The document discusses the integration of Google Vision API with MongoDB on Google Cloud to enhance image management and analysis capabilities across industries. It details a demo for setting up a MongoDB Atlas cluster, configuring a Node.js application, and utilizing machine learning to gain insights from images without prior metadata. Additionally, it emphasizes the security features and ease of use associated with Google Cloud for enterprise customers.
![#MDBloca
l
Gaining ML Insight with
Google Vision API and
MongoDB on Google
Cloud
Sam Weeks [Google Cloud]
https://www.surveymonkey.com/r/K6L52LB](https://image.slidesharecdn.com/gainingmlinsightongcpwithgooglevisionapiandmongodb-swmongo-190928005149-190928122238/85/MongoDB-local-London-2019-Gaining-ML-insight-on-Google-Cloud-with-Google-Vision-API-and-MongoDB-17-320.jpg)
MongoDB .local London 2019: Gaining ML insight on Google Cloud with Google Vision API and MongoDB
- 1. Gaining ML insight with Google Vision API and MongoDB on Google Cloud
- 2. Used across flagship products: Google is an AI company Uniqueprojectdirectories Time
- 3. Three ways to AI&ML on GCP Ease of Use AutoML
- 4. Three ways for AI&ML on GCP Ease of Use AutoML
- 5. Perception APIs Sight Language AutoML Video Intelligence AutoML Translation Conversation Structured Data Vision API Natural Language API Dialogflow AutoML Vision for cloud + edge models AutoML Natural Language Cloud Text-to-Speech Recommendation AI Video Intelligence API Translation API Cloud Speech-to-Text Cloud Inference API
- 6. Vision API Detect popular places and landmarks Classify content with predefined labels OCR support for 50+ languages Detect brands and product logos Identify products from your catalog Identify image properties (colors, etc.) Get hints for best image cropping Detect faces and emotions Moderate explicit content Find similar images on the web Detect objects and retrieve coordinates Extract printed and handwritten text
- 7. Box is using Vision API to help their customers manage and gain insights from their image files, and speed up image-centric processes and workflows. TECHNOLOGY Bringing image recognition and OCR to cloud content management Improved extensive content management for customers in every industry Intelligent structure for 30 billion files managed with powerful capabilities Image source: https://www.box.com/skills
- 8. Gives journalists a new way to search, access, and analyze millions of historic photos NYT digitized more than a century of perishable photographs and other materials. With the Vision API, Times reporters can now easily search millions of high-res scans to enhance their reporting with even more visual storytelling. Bringing historic content to life Preserves a priceless chronicle of more than 100 years of events that have shaped our world MEDIA & ENTERTAINMENT
- 10. ● end to end security defaults that cannot be disabled: ○ always-on authentication ○ network isolation for dedicated clusters ○ TLS / SSL ○ encryption for data at rest ○ granular role-based access controls ○ global VPC peering ○ KMS integration for Enterprise customers ● supports multi-region clusters ● continuous backups and managed snapshots ● Unified billing through Google Marketplace ● Free Tier available on Google Cloud Platform
- 11. Demo quickly build a descriptive metadata MongoDB Atlas DB running on GCP See how easy it is to use Machine Learning to gain additional insights from a batch of photos that have no prior metadata attached.
- 12. 1. Create and configure MongoDB Atlas Free-Tier cluster on GCP 2. Configure our Google Cloud Platform Account 3. Configure a Node JS application on a GCE Debian VM to use Vision API (labels, landmarks and safe search)
- 13. 4. Kick off the batch process from any web-enabled client terminal 5. Verify our new metadata in both the console and in our MongoDB Atlas database
- 14. What just happened there? Let’s review... ● Created a new free, MongoDB Atlas Free-tier cluster from scratch and configured it ● Created a GCE Debian VM and SSH’d into it remotely with ease, thanks to CloudShell ● Configured API access to our VM ● Opened up port 8080 in the firewall for our server ● Made a multi-regional bucket in GCS and modified the permission for our server ● Configured our VM for Node.js, express and Vision API ● Stood up a web server ● Connected to an external VM IP address ● Leveraged machine learning to recourse a bucket and insert metadata into our Atlas database ● Spot checked some of the entries in our database ● Did this with the creation of ONLY 3 FILES
- 15. Can I try this out myself?... Find all code and steps for this demo here: https://cloud.google.com/community/tutorials/mongodb-atlas-visionapi-nodejs Full URL: Google Cloud Community Tutorial Site
- 16. Next steps... 01 Speak to us Chat with our team, learn more about GCP + Atlas 02 Sign up for a new GCP account and get credits Get free trial credits when you sign up for GCP with a new account. 03 Create a new MongoDB Atlas cluster on GCP Create a free MongoDB Atlas database on GCP
- 17. #MDBloca l Gaining ML Insight with Google Vision API and MongoDB on Google Cloud Sam Weeks [Google Cloud] https://www.surveymonkey.com/r/K6L52LB
- 18. 18 Thank you