From 7aca607940890e6934cd6568e61cb1e5184b93a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cristina=20Gran=C3=A9s?= Date: Wed, 11 Jun 2025 20:12:14 +0200 Subject: [PATCH] Updates README: reformating, adding new links --- ai/ai-document-understanding/README.md | 97 +++++++++++++-------- ai/ai-language/README.md | 69 ++++++++------- ai/ai-speech/README.md | 70 +++++++++------- ai/ai-vision/README.md | 111 ++++++++++++++----------- 4 files changed, 205 insertions(+), 142 deletions(-) diff --git a/ai/ai-document-understanding/README.md b/ai/ai-document-understanding/README.md index 21fdde1c4..9eb3cdd18 100644 --- a/ai/ai-document-understanding/README.md +++ b/ai/ai-document-understanding/README.md @@ -2,34 +2,58 @@ Oracle Cloud Infrastructure (OCI) Document Understanding is an AI service that enables developers to extract text, tables, and other key data from document files through APIs and command-line interface tools. With OCI Document Understanding, you can automate tedious business processing tasks with prebuilt AI models and customize document extraction to fit your industry-specific needs. -Reviewed: 17.10.2024 +Reviewed: 11.06.2025 # Table of Contents -- [Document Understanding](#document-understanding) -- [Table of Contents](#table-of-contents) -- [Team Publications](#team-publications) - - [Reusable Assets Overview](#reusable-assets-overview) -- [Useful Links](#useful-links) - - [LiveLabs and Workshops](#livelabs-and-workshops) - - [Customer Stories](#customer-stories) -- [License](#license) +1. [Team Publications](#team-publications) +2. [Useful Links](#useful-links) +3. [Reusable Assets Overview](#reusable-assets-overview) # Team Publications +## LiveLabs and Workshops + +- [Introduction to OCI Document Understanding](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3585) - [Search Documents stored in Object Storage using Opensearch, Generative AI, Semantic Search, RAG](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3762) +- [Develop with Oracle AI and Database Services: Gen, Vision, Speech, Language, OML, Select AI, RAG and Vector](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3874&clear=RR,180&session=10041712875174) +- [Search Documents and Images stored in Object Storage using OpenSearch, AI Vision, Text Recognition](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3442) + +## GitHub + +- [Invoice Document Processing from Gmail into ERP systems using OCI Document Understanding & Oracle Integration Cloud](https://github.com/oracle-devrel/technology-engineering/tree/main/ai/ai-document-understanding/ai-email-invoice) + +## Architecture Center + +- [Search documents and images stored in Object Storage using OpenSearch, OCI Vision, Text Recognition](https://docs.oracle.com/en/solutions/oci-opensearch-vision/index.html) +- [Enable a Low Code Modular LLM App Engine using Oracle Integration and OCI Generative AI](https://docs.oracle.com/en/solutions/oci-generative-ai-integration/index.html) +- [Use OCI Vision + DU to extract data from images and scanned documents](https://docs.oracle.com/en/solutions/ai-vision-extract-data/index.html) -## Reusable Assets Overview +# Useful Links +- [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/) +- [Document Understanding Oracle.com Page](https://www.oracle.com/artificial-intelligence/document-understanding/) +- [Document Understanding Documentation](https://docs.oracle.com/iaas/document-understanding/document-understanding/using/home.htm) +- [Announcing OCI Document Understanding custom model support (June 14, 2023)](https://blogs.oracle.com/ai-and-datascience/post/oci-document-understanding-custom-model-support) +- [Announcing OCI Document Understanding service (December 8, 2022)](https://blogs.oracle.com/ai-and-datascience/post/announcing-oci-document-understanding-service) +- [Automate with documents using AI](https://blogs.oracle.com/ai-and-datascience/post/automate-documents-using-ai) +- [Oracle Learning YouTube Playlist - OCI Document Understanding Service](https://youtube.com/playlist?list=PLKCk3OyNwIzt1x62El9gGGeNaQr0va58c) +- [GitHub Examples](https://github.com/oracle-samples/oci-data-science-ai-samples/tree/master/labs/ai-document-understanding) + +## Customer Stories + +- [Trailcon Leasing: Low-code and AI for Automating Invoice Processing & Approval Workflow](https://www.youtube.com/watch?v=TsbNU6xdQPw) +- [Careem increases efficiency and cuts invoice process time 70% with Oracle AI](https://www.oracle.com/customers/careem-case-study/) + +# Reusable Assets Overview + +## Cloud Coaching - [Cloud Coaching - Boost Your Oracle AI Services](https://youtu.be/VVWTqqlIEhg) - Learn how to Develop a Multi-Chain Document Evaluation Apps with Oracle Generative AI, Document Understanding, and Integration Cloud. -- [Blog: Document Evaluation Tool using OCI Generative AI, Document Understanding & Integration Cloud](https://github.com/oracle-devrel/technology-engineering/tree/main/ai/generative-ai-service/doc-evaluation-genai) - - In this article, we'll explore how to make a handy tool that helps to evaluate documents using Oracle Generative AI, OCI Document Understanding, and Oracle Integration Cloud (OIC). This application combines a low-code approach to orchestrate LLM AI services and applications using Oracle Integration Cloud and Generative AI prompting techniques for tasks like document key criteria extraction, summarization, and evaluation. - - [Cloud Coaching - How to code and develop a Web (or Mobile) Application with Visual Builder that uses and leverages OCI Document Understanding Service](https://youtu.be/0oHixpA9JDc?si=3CWh0d2RpuEzzLKU) - Learn how to create applications that read, modify, and classify documents with a couple of clicks using our low code development platform and some of the OCI AI services offering + - Learn how to create applications that read, modify, and classify documents with a couple of clicks using our low code development platform and some of the OCI AI services offering - [Cloud Coaching - AI Based & Real Time Gmail Invoice Documents Processing into Oracle Fusion ERP Cloud](https://youtu.be/wq7HH-WYslU?si=wBqH5eEkcC0hYKqj) How can you speed up your Account Payable Invoice Processing Cycle? Document Understanding and OCI Intelligent Automation Engine running on top of Oracle Fusion ERP Cloud can help: @@ -42,33 +66,38 @@ Reviewed: 17.10.2024 - [Oracle AI Invoice Handling Solution](https://github.com/oracle-devrel/oci-ai-invoice-handling) -- [Demo: Automate Invoice Handling - Oracle Integration Cloud & AI Document Understanding Service](https://youtu.be/k72CcNhmOjs) -- [Smarter Apps with AI, OIC partner community webcast June 2023](https://videohub.oracle.com/media/Smarter+AI+Apps+with+OIC+partner+community+webcast+June+2023-1080p30/1_m2yjnvf9) - - OCI Language and Document Understanding are cloud-based AI services for performing sophisticated text analysis and extracting data from all kinds of documents e.g. Passport, Driving License, Invoices, Receipts, etc. You can use these services to build intelligent applications by leveraging REST APIs. You can use these services to build intelligent applications by leveraging REST APIs and automating using Oracle Integration Cloud. This allows you to process unstructured text for use cases such as sentiment analysis, service ticket classification, document extraction, and more using pre-trained models or your own custom models leveraging OCI Data Labelling. -- [Document Understanding (Insurance Document) Key Value extraction demo](https://youtu.be/QsFqaRxtV1s) -- [Cloud Customer Connect - How to Train Your Oracle AI Cloud Service Model](https://community.oracle.com/customerconnect/events/604740-oci-how-to-train-your-oracle-ai-cloud-service-model) - - In this session, we demonstrate how you can use OCI AI services, to create custom models using the data labeling, vision, and document understanding service. - [Cloud Coaching - Low Code Modular RAG-based Knowledge Search Engine using Oracle GenAI](https://www.youtube.com/watch?v=KkVomurY_0Q) - In this coaching session, you’ll learn how to use low-code integration with Oracle Integration Cloud to integrate and orchestrate social media channels like WhatsApp, Business channels like a Web Application built in Oracle Visual Builder, productivity channels like OCI Object Storage, local large and small language models (LLMs), and vector databases to ingest live data into the RAG-based Knowledge Search Engine store. -# Useful Links +## Blogs -- [Automate with documents using AI](https://blogs.oracle.com/ai-and-datascience/post/automate-documents-using-ai) -- [Oracle Learning YouTube Playlist - OCI Document Understanding Service](https://youtube.com/playlist?list=PLKCk3OyNwIzt1x62El9gGGeNaQr0va58c) -- [GitHub Examples](https://github.com/oracle-samples/oci-data-science-ai-samples/tree/master/labs/ai-document-understanding) -- [Announcing OCI Document Understanding custom model support (June 14, 2023)](https://blogs.oracle.com/ai-and-datascience/post/oci-document-understanding-custom-model-support) -- [Announcing OCI Document Understanding service (December 8, 2022)](https://blogs.oracle.com/ai-and-datascience/post/announcing-oci-document-understanding-service) +- [Document Evaluation Tool using OCI Generative AI, Document Understanding & Integration Cloud](https://github.com/oracle-devrel/technology-engineering/tree/main/ai/generative-ai-service/doc-evaluation-genai) + - In this article, we'll explore how to make a handy tool that helps to evaluate documents using Oracle Generative AI, OCI Document Understanding, and Oracle Integration Cloud (OIC). This application combines a low-code approach to orchestrate LLM AI services and applications using Oracle Integration Cloud and Generative AI prompting techniques for tasks like document key criteria extraction, summarization, and evaluation. -- [Document Understanding Oracle.com Page](https://www.oracle.com/artificial-intelligence/document-understanding/) -- [Document Understanding Documentation](https://docs.oracle.com/iaas/document-understanding/document-understanding/using/home.htm) +- [Create a Custom Document Understanding Model in OCI](https://blogs.oracle.com/analytics/post/create-a-custom-document-understanding-model-in-oci) + - Explore which are the steps to create custom models in Document Understanding and which models can be customized. Custom models are useful for specific business requirements, when pretrained models are not enough to solve those needs. -## LiveLabs and Workshops - -- [Introduction to OCI Document Understanding](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3585) +- [Register and Invoke Custom Document Understanding Models in Oracle Analytics Cloud](https://blogs.oracle.com/analytics/post/register-and-invoke-custom-document-understanding-models-in-oac) + - Learn about custom Document Understanding models and how to register and invoke a custom key value extraction model from OAC. + +- [OCI Document Understanding: Using OJET apps with TypeScript](https://blogs.oracle.com/developers/post/oci-document-understanding-using-ojet-apps-with-typescript) + +- [Extract key values with Oracle Analytics and OCI Document Understanding](https://blogs.oracle.com/analytics/post/innovate-with-oracle-analytics-and-ai-document-understanding) + + +## Demos & Events + +- [Demo: Automate Invoice Handling - Oracle Integration Cloud & AI Document Understanding Service](https://youtu.be/k72CcNhmOjs) +- [Smarter Apps with AI, OIC partner community webcast June 2023](https://videohub.oracle.com/media/Smarter+AI+Apps+with+OIC+partner+community+webcast+June+2023-1080p30/1_m2yjnvf9) + - OCI Language and Document Understanding are cloud-based AI services for performing sophisticated text analysis and extracting data from all kinds of documents e.g. Passport, Driving License, Invoices, Receipts, etc. You can use these services to build intelligent applications by leveraging REST APIs. You can use these services to build intelligent applications by leveraging REST APIs and automating using Oracle Integration Cloud. This allows you to process unstructured text for use cases such as sentiment analysis, service ticket classification, document extraction, and more using pre-trained models or your own custom models leveraging OCI Data Labelling. +- [Document Understanding (Insurance Document) Key Value extraction demo](https://youtu.be/QsFqaRxtV1s) +- [Cloud Customer Connect - How to Train Your Oracle AI Cloud Service Model](https://community.oracle.com/customerconnect/events/604740-oci-how-to-train-your-oracle-ai-cloud-service-model) + - In this session, we demonstrate how you can use OCI AI services, to create custom models using the data labeling, vision, and document understanding service. +- [Low-Code Modular RAG-Based Knowledge Search Engine](https://www.oracle.com/artificial-intelligence/low-code-modular-rag/) +- [Automate Invoice Handling with OCI Document Understanding](https://www.oracle.com/artificial-intelligence/automate-invoice-processing/) +- [Processing Invoices in Email Using OCI Document Understanding and Oracle Integration Cloud](https://www.oracle.com/artificial-intelligence/processing-invoices-in-email/) +- [Evaluating Documents using OCI Generative AI and OCI Document Understanding](https://www.oracle.com/artificial-intelligence/evaluating-document/) -## Customer Stories - -- [Trailcon Leasing: Low-code and AI for Automating Invoice Processing & Approval Workflow](https://www.youtube.com/watch?v=TsbNU6xdQPw) # License diff --git a/ai/ai-language/README.md b/ai/ai-language/README.md index 0036ef2ed..0f41c69e5 100644 --- a/ai/ai-language/README.md +++ b/ai/ai-language/README.md @@ -2,58 +2,63 @@ OCI Language is a cloud-based AI service for performing sophisticated text analysis at scale. Use this service to build intelligent applications by leveraging REST APIs and SDKs to process unstructured text for sentiment analysis, entity recognition, translation, and more. -Reviewed: 25.10.2024 +Reviewed: 11.06.2025 # Table of Contents -- [AI Language](#ai-language) -- [Table of Contents](#table-of-contents) -- [Team Publications](#team-publications) - - [Architecture Center](#architecture-center) -- [Useful Links](#useful-links) - - [LiveLabs and Workshops](#livelabs-and-workshops) - - [Customer Stories](#customer-stories) -- [Reusable Assets](#reusable-assets) -- [License](#license) +1. [Team Publications](#team-publications) +2. [Useful Links](#useful-links) +3. [Reusable Assets Overview](#reusable-assets-overview) # Team Publications - [Saving the Bees using AI: One Positive Entity at a Time](https://www.linkedin.com/pulse/saving-bees-using-ai-one-positive-entity-time-ismail-syed/) -- [AI Meetings: Sentiment analysis & Name Entity Recognition](https://www.oracle.com/artificial-intelligence/automate-meeting-transcriptions/) -- [Cloud Coaching - Unlock the potential of enterprise Oracle GenAI](https://www.youtube.com/watch?v=dtvP0DU7Mdg) - - During this cloud coaching session, we demonstrate how to leverage AI to revolutionize meeting interactions. Experience real-time transcription, summary generation, a chat interface and more that enhances collaboration and productivity. -- [Cloud Coaching - Oracle Integration (OIC3) and AI Language Service](https://www.youtube.com/watch?v=9gDHVjwKDR8) - - The aim of this video is to show practical examples when and how to use AI Language Service - Named Entity Recognition method. -- [Getting Started with Oracle Cloud Infrastructure AI Language Service](https://www.youtube.com/watch?v=-t6jje8SRXU) -- [Enabling a WhatsApp Customer HelpMate using OCI Generative AI, AI Language & Integration](https://www.youtube.com/watch?v=ryo3wVB_69E) + + +## LiveLabs and Workshops + +- [Get started with Oracle Cloud Infrastructure Language](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=887&clear=RR,180&session=5298742340912) +- [Perform Sentiment Analysis with OCI AI Language Service and OAC](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3214&clear=RR,180&session=5298742340912) +- [Deliver Immersive Conversational User Experiences with OCI AI Services](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3452&clear=RR,180&session=5298742340912) +- [Develop with Oracle AI and Database Services: Gen, Vision, Speech, Language, OML, Select AI, RAG and Vector](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3874&clear=RR,180&session=10041712875174) + ## Architecture Center -- [Use OCI Language for customer feedback analysis](https://docs.oracle.com/en/solutions/oci-ai-language/index.html#GUID-33D63770-1F4D-4AAE-BC6D-D42C62D10CC2) +- [Use OCI Language for customer feedback analysis](https://docs.oracle.com/en/solutions/oci-ai-language/index.html) +- [Enhance and automate review replies with OCI Generative AI, OCI Language, and OCI Integration](https://docs.oracle.com/en/solutions/enhance-auto-replies-oci/index.html) +- [Enable a Low Code Modular LLM App Engine using Oracle Integration and OCI Generative AI](https://docs.oracle.com/en/solutions/oci-generative-ai-integration/index.html) # Useful Links - [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/) - [Oracle AI Language on oracle.com](https://www.oracle.com/uk/artificial-intelligence/language/) - [Oracle AI Language documentation](https://docs.oracle.com/en-us/iaas/language/using/language.htm) +- [Oracle AI Language v4.1: Enhanced accuracy, control and performance](https://blogs.oracle.com/ai-and-datascience/post/oci-language-v41) +- [Oracle AI Language v4 announcement blog 2024](https://blogs.oracle.com/ai-and-datascience/post/oci-ai-language-4-0) - [Oracle AI Language v3 announcement blog](https://blogs.oracle.com/ai-and-datascience/post/announcing-the-general-availability-of-oci-language-30) -- [Oracle AI Language announcement blog](https://blogs.oracle.com/ai-and-datascience/post/announcing-oci-language) - - -## LiveLabs and Workshops - -- [Get started with Oracle Cloud Infrastructure Language](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=887&clear=RR,180&session=5298742340912) -- [Perform Sentiment Analysis with OCI AI Language Service and OAC](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3214&clear=RR,180&session=5298742340912) -- [Deliver Immersive Conversational User Experiences with OCI AI Services](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3452&clear=RR,180&session=5298742340912) -- [Build applications with Oracle’s AI services](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3674&clear=RR,180&session=5298742340912) +- [Oracle AI Language announcement blog 2021](https://blogs.oracle.com/ai-and-datascience/post/announcing-oci-language) +- [Getting Started with Oracle Cloud Infrastructure AI Language Service](https://www.youtube.com/watch?v=-t6jje8SRXU) +- [OCI AI Language Service introduction video](https://www.youtube.com/watch?v=-t6jje8SRXU) ## Customer Stories - [Aon improves customer experience with OCI Language service](https://www.oracle.com/customers/aon-case-study/) -# Reusable Assets - -- [OCI AI Language Service introduction video](https://www.youtube.com/watch?v=-t6jje8SRXU) +# Reusable Assets Overview +## Cloud Coaching +- [Cloud Coaching - Unlock the potential of enterprise Oracle GenAI](https://www.youtube.com/watch?v=dtvP0DU7Mdg) + - During this cloud coaching session, we demonstrate how to leverage AI to revolutionize meeting interactions. Experience real-time transcription, summary generation, a chat interface and more that enhances collaboration and productivity. +- [Cloud Coaching - Oracle Integration (OIC3) and AI Language Service](https://www.youtube.com/watch?v=9gDHVjwKDR8) + - The aim of this video is to show practical examples when and how to use AI Language Service - Named Entity Recognition method. +## Blogs +- [Customer sentiment analysis with OCI AI Language](https://blogs.oracle.com/cloud-infrastructure/post/oci-ai-language-nonenglish-language-use-case) +- [Speech-to-speech translation using Oracle AI services](https://blogs.oracle.com/ai-and-datascience/post/speech-to-speech-using-ai-services) +- [How to call the OCI AI Language Service from the Oracle Integration Cloud](https://blogs.oracle.com/integration/post/how-to-call-the-oci-ai-language-service-from-oic) +- [Oracle B2C Service Built-in Thread Translation](https://blogs.oracle.com/cx/post/thread-translation) + +## Demos & Events +- [AI Meetings: Sentiment analysis & Name Entity Recognition](https://www.oracle.com/artificial-intelligence/automate-meeting-transcriptions/) - [Real-Time Outlook Email Analysis with Oracle Integration & OCI AI Language](https://youtu.be/qzyzdAZjUU0?si=moC-O47m7L1nrhqx) - Through a Live Demo you will see how Oracle Integration Cloud work seamlessly with Oracle Cloud Streaming & API Gateway for instant Outlook Messages capture via Microsoft Graph Webhooks @@ -68,11 +73,13 @@ Reviewed: 25.10.2024 - Use OCI Generative AI (in pre-availability) for "Customer Service Quick Replies" Generation for Whatsapp Neutral Messages (customer questions, queries, etc.), sentence-level sentiment analysis from OCI AI Language to uncover overall sentiment and set service ticket severity for negative Whatsapp messages, automatically classify Customer Service tickets through OCI AI Language custom text classification and aspect-based sentiment analysis (ABSA) services. - Learn how Oracle Integration Cloud and Oracle Cloud Infrastructure (OCI) Streaming allow real-time capture of WhatsApp messages. - All this automation using OCI AI Services APIs orchestrated by Oracle Integration Cloud (using no-code integration approach) -- [Enabling an Event-Driven, Real-Time Twitter Sentiment Analysis Dashboard Demo ](https://www.youtube.com/watch?v=9hvUxLSE3Vg) +- [Enabling an Event-Driven, Real-Time Twitter Sentiment Analysis Dashboard Demo](https://www.youtube.com/watch?v=9hvUxLSE3Vg) - [Smarter Apps with AI, OIC partner community webcast June 2023](https://videohub.oracle.com/media/Smarter+AI+Apps+with+OIC+partner+community+webcast+June+2023-1080p30/1_m2yjnvf9) - OCI Language and Document Understanding are cloud-based AI services for performing sophisticated text analysis and extracting data from all kinds of documents e.g. Passport, Driving License, Invoices, Receipt etc. You can use these services to build intelligent applications by leveraging REST APIs. You can use these services to build intelligent applications by leveraging REST APIs and automate using Oracle Integration Cloud. This allows you to process unstructured text for use cases such as sentiment analysis, service ticket classification, document extraction, and more using pretrained models or your own custom models leveraging OCI Data Labelling. - [AI Language demo](https://youtu.be/w8vFTKp4JME) - [AI Language - Hotel Reviews (AI Language, OAC)](https://youtu.be/pmf90oUZGH4) +- [Text Translation Using OCI Language](https://www.oracle.com/artificial-intelligence/text-translation/) +- [Translating CSV and JSON Files with OCI Language](https://www.oracle.com/artificial-intelligence/translating-csv-and-json-files-with-oci/) # License diff --git a/ai/ai-speech/README.md b/ai/ai-speech/README.md index 8b09f1267..9d29c039b 100644 --- a/ai/ai-speech/README.md +++ b/ai/ai-speech/README.md @@ -2,29 +2,45 @@ OCI Speech is an AI service that applies automatic speech recognition technology to transform audio-based content into text. Developers can easily make API calls to integrate OCI Speech’s pre-trained models into their applications. OCI Speech can be used for accurate, text-normalized, time-stamped transcription via the console and REST APIs as well as command-line interfaces or SDKs. You can also use OCI Speech in an OCI Data Science notebook session. With OCI Speech, you can filter profanities, get confidence scores for both single words and complete transcriptions, and more. -Reviewed: 12.05.2025 +Reviewed: 11.06.2026 # Table of Contents -- [AI Speech](#ai-speech) -- [Table of Contents](#table-of-contents) -- [Team Publications](#team-publications) - - [Reusable Assets Overview](#reusable-assets-overview) - - [Architecture Center](#architecture-center) - - [LiveLabs and Workshops](#livelabs-and-workshops) -- [Useful Links](#useful-links) -- [License](#license) +1. [Team Publications](#team-publications) +2. [Useful Links](#useful-links) +3. [Reusable Assets Overview](#reusable-assets-overview) # Team Publications -- [AI Meetings: Meetings transcription](https://www.oracle.com/artificial-intelligence/automate-meeting-transcriptions/) -- [Create Podcasts with Generative AI](https://www.oracle.com/artificial-intelligence/create-podcasts-with-generative-ai/) -## Reusable Assets Overview +## LiveLabs and Workshops + +- [Introduction to OCI Speech](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3135&clear=RR,180&session=106771425893627) +- [Search Documents stored in Object Storage using Opensearch, Generative AI, Semantic Search, RAG](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3762) +- [Detect and manage offensive behavior in YouTube videos using OCI Data Science, OCI Language, and OCI Speech integrated with APEX](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3867&clear=RR,180&session=110244305190461) +- [Develop with Oracle AI and Database Services: Gen, Vision, Speech, Language, OML, Select AI, RAG and Vector](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3874&clear=RR,180&session=10041712875174) + +## GitHub +- [Podcast Generator](https://github.com/oracle-devrel/technology-engineering/tree/main/ai/ai-speech/podcast-generator) + +## Architecture Center +- [Implement a web-based user interface for interacting with Oracle Cloud Infrastructure Generative AI Agents](https://docs.oracle.com/en/solutions/oci-genai-speech/index.html) +- [Use OCI Speech to transcribe natural language](https://docs.oracle.com/en/solutions/ai-speech/index.html) + +# Useful Links + +- [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/) +- [Oracle AI Speech on oracle.com](https://www.oracle.com/artificial-intelligence/speech/) +- [Oracle AI Speech documentation](https://docs.oracle.com/en-us/iaas/Content/speech/home.htm) +- [Oracle Speech AI service now supports diarization](https://blogs.oracle.com/ai-and-datascience/post/oracle-speech-ai-service-now-supports-diarization) +- [OCI Speech supports the Whisper model](https://blogs.oracle.com/ai-and-datascience/post/oci-speech-supports-the-whisper-model) +- [OCI Speech supports text-to-speech and real-time transcription with customized vocabulary](https://blogs.oracle.com/ai-and-datascience/post/oci-speech-texttospeech-realtime-transcription-custom-vocab) + +# Reusable Assets Overview + +## Cloud Coaching - [Cloud Coaching - Boost Your Oracle AI Services](https://youtu.be/VVWTqqlIEhg) - Integrate OCI AI Speech Service and Generative AI Summarization with Oracle Integration Cloud and Visual Builder -- [Demos built using OCI Python SDK](https://github.com/luigisaetta/oci-speech-demos) -- [AI Speech console demo](https://youtu.be/EWBSoSLNph8) - [Cloud Coaching - Unlock the potential of enterprise Oracle GenAI](https://www.youtube.com/watch?v=dtvP0DU7Mdg) - During this cloud coaching session, we demonstrate how to leverage AI to revolutionize meeting interactions. Experience real-time transcription, summary generation, a chat interface and more that enhances collaboration and productivity. - [Cloud Coaching - Build an OCI AI Speech-to-Text App Using Visual Builder and Functions](https://www.youtube.com/watch?v=9-KiORugqGc) @@ -33,24 +49,20 @@ Reviewed: 12.05.2025 - Integrate Python and Oracle Functions for backend processing. - Build a user-friendly interface with Oracle Visual Builder Cloud Service. -Download, and preview transcribed text. -- [Podcast Generator](https://github.com/oracle-devrel/technology-engineering/tree/main/ai/ai-speech/podcast-generator) -## Architecture Center -- [Implement a web-based user interface for interacting with Oracle Cloud Infrastructure Generative AI Agents](https://docs.oracle.com/en/solutions/oci-genai-speech/index.html) -- [Use OCI Speech to transcribe natural language](https://docs.oracle.com/en/solutions/ai-speech/index.html) +## Blogs +- [Speech-to-speech translation using Oracle AI services](https://blogs.oracle.com/ai-and-datascience/post/speech-to-speech-using-ai-services) +- [Enabling the notification feature for OCI Speech service](https://blogs.oracle.com/ai-and-datascience/post/notification-and-events-oci-speech-service) +- [Interactive AI Holograms: Develop a Digital Double Assistant with Oracle Database 23ai Select AI, Vector RAG, OCI Speech AI, and Audio2Face MetaHumans](https://blogs.oracle.com/developers/post/interactive-ai-holograms-develop-a-digital-double-assistant-with-oracle-database-23ai-select-ai-vector-rag-oci-speech-ai-and-audio2face-metahumans) -## LiveLabs and Workshops - -- [Introduction to OCI Speech](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3135&clear=RR,180&session=106771425893627) -- [Search Documents stored in Object Storage using Opensearch, Generative AI, Semantic Search, RAG](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3762) -- [Detect and manage offensive behavior in YouTube videos using OCI Data Science, OCI Language, and OCI Speech integrated with APEX](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3867&clear=RR,180&session=110244305190461) +## Demos & Events -# Useful Links - -- [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/) -- [Oracle AI Speech on oracle.com](https://www.oracle.com/artificial-intelligence/speech/) -- [Oracle AI Speech documentation](https://docs.oracle.com/en-us/iaas/Content/speech/home.htm) -- [Oracle Speech AI service now supports diarization](https://blogs.oracle.com/ai-and-datascience/post/oracle-speech-ai-service-now-supports-diarization) +- [Demos built using OCI Python SDK](https://github.com/luigisaetta/oci-speech-demos) +- [AI Speech console demo](https://youtu.be/EWBSoSLNph8) +- [AI Meetings: Meetings transcription](https://www.oracle.com/artificial-intelligence/automate-meeting-transcriptions/) +- [Create Podcasts with Generative AI](https://www.oracle.com/artificial-intelligence/create-podcasts-with-generative-ai/) +- [Streamlining Medical Transcription Processes using OCI Speech](https://www.oracle.com/artificial-intelligence/enhancing-medical-transcription-with-oci-speech/) +- [Transcribing voice messages for service requests in Siebel CRM using OCI Speech](https://www.oracle.com/artificial-intelligence/transcribe-calls-oci-speech-siebel/) # License diff --git a/ai/ai-vision/README.md b/ai/ai-vision/README.md index ffcd19736..90ff0b0f0 100644 --- a/ai/ai-vision/README.md +++ b/ai/ai-vision/README.md @@ -2,81 +2,96 @@ OCI Vision is an AI service for performing deep-learning–based image analysis at scale. With prebuilt models available out of the box, developers can easily build image recognition and text recognition into their applications without machine learning (ML) expertise. For industry-specific use cases, developers can automatically train custom vision models with their own data. These models can be used to detect visual anomalies in manufacturing, organize digital media assets, and tag items in images to count products or shipments. -Reviewed: 13.11.2024 +Reviewed: 11.06.2025 # Table of Contents -- [AI Vision](#ai-vision) -- [Table of Contents](#table-of-contents) -- [Team Publications](#team-publications) -- [Useful Links](#useful-links) - - [Architecture Center](#architecture-center) - - [LiveLabs and Workshops](#livelabs-and-workshops) -- [Reusable Assets Overview](#reusable-assets-overview) -- [License](#license) +1. [Team Publications](#team-publications) +2. [Useful Links](#useful-links) +3. [Reusable Assets Overview](#reusable-assets-overview) # Team Publications - [OCI Vision Saving Bees using Object Detection](https://www.linkedin.com/pulse/saving-bees-using-ai-one-object-time-ismail-syed/) -- [OCI Vision Healthcare Image Analysis](https://blogs.oracle.com/ai-and-datascience/post/advancing-healthcare-image-analysis-on-oci) -- [Build a real-time object identifier using OCI Vision and Oracle Autonomous Database](https://docs.oracle.com/en/solutions/realtime-ocivision-object-identification/index.html#GUID-A875FB7D-29E3-4FBF-AED5-C0CF43F71469) - - The reference architecture describes how you can integrate an OCI Vision-trained model with a front-end web app to perform real-time object identification with a mobile phone camera. -- [Build a meal recommmendation Engine with OCI Vision & Generative AI](https://www.oracle.com/artificial-intelligence/build-a-meal-recommendation-engine-with-ai/) -- [Cloud Coaching - Unlock Culinary Creativity: AI Powered Cooking Adventure from Fridge to Fork!](https://www.youtube.com/watch?v=tRVwTLKS4rE&t) - - You are in the mood of cooking an exotic dish. You open the refrigerator, and using the mobile phone, access your favourite retail app to scan the items you have and submit. - - This triggers a series of actions: - - OCI AI Vision identifies the items (specific vegetables, egg, chicken etc). - - On choosing your favourite cuisine, OCI Generative AI suggests a list of dishes based on identified items. - - On selecting your favourite dish, OCI Generative AI provides the detailed recipe. Also, the missing ingredients are listed, with an option to order the same. -- [Cloud Coaching - Discover OCI Vision for Object Detection in Manufacturing, Retail, & More](https://www.youtube.com/watch?v=lHH_1MXGOc0) - - In this session you learn how OCI Vision can identify, classify, and quantify visual data in powerful ways. Watch as the service identifies objects (people, cars, trees, and so forth) and categorizes them. See how it can even detect faces or key points in faces for analysis. -- [Search Documents stored in Object Storage using Opensearch, Generative AI, Semantic Search, RAG](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3762) -# Useful Links +## LiveLabs and Workshops -- [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/) -- [Oracle AI Vision on oracle.com](https://www.oracle.com/uk/artificial-intelligence/vision/) -- [Oracle AI Vision documentation](https://docs.oracle.com/en-us/iaas/vision/vision/using/home.htm) +- [AI Services: Introduction to OCI Vision](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=931&clear=RR,180&session=101189893786132) +- [Use Data Labeling Service to Create a Biomedical Image Classification Model](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3097&clear=RR,180&session=101189893786132) +- [Premier League Video Analysis with Deep Learning](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3489&clear=RR,180&session=101189893786132) +- [How to Use AI Vision and Drones for Inventory Management](https://go.oracle.com/LP=135420) +- [Classify X-Ray Images for Pneumonia using Analytics Cloud and Vision AI Services](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3576) +- [Automate and accelerate inventory analytics](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3426) +- [Develop with Oracle AI and Database Services: Gen, Vision, Speech, Language, OML, Select AI, RAG and Vector](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3874&clear=RR,180&session=10041712875174) +- [Search Documents and Images stored in Object Storage using OpenSearch, AI Vision, Text Recognition](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3442) +- [Search Documents stored in Object Storage using Opensearch, Generative AI, Semantic Search, RAG](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3762) + +## GitHub + +- [OCI image classification using data labeling and vision service](https://github.com/carlgira/oci-image-classification) +- [OCI object detection using data labeling and vision service](https://github.com/carlgira/oci-object-detection) +- [AI vision web client](https://github.com/oracle-devrel/oci-tf-vision-web-client) + - Terraform script that will create a set of resources on OCI to create a web app to test an existing vision model. ## Architecture Center - [Build a real-time object identifier using OCI Vision and Oracle Autonomous Database](https://docs.oracle.com/en/solutions/realtime-ocivision-object-identification/index.html) + - The reference architecture describes how you can integrate an OCI Vision-trained model with a front-end web app to perform real-time object identification with a mobile phone camera. +- [Search documents and images stored in Object Storage using OpenSearch, OCI Vision, Text Recognition](https://docs.oracle.com/en/solutions/oci-opensearch-vision/index.html) +- [Automate and streamline your image classification workflow with OCI AI services](https://docs.oracle.com/en/solutions/automate-image-classification-workflow-with-ai/index.html) +- [Enable a Low Code Modular LLM App Engine using Oracle Integration and OCI Generative AI](https://docs.oracle.com/en/solutions/oci-generative-ai-integration/index.html) +- [Use OCI Vision + DU to extract data from images and scanned documents](https://docs.oracle.com/en/solutions/ai-vision-extract-data/index.html) +- [Use OCI Vision to automate inventory management](https://docs.oracle.com/en/solutions/oci-vision-inventory/index.html) -## LiveLabs and Workshops +# Useful Links -- [LiveLabs - AI Vision introduction](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=931&clear=RR,180&session=101189893786132) - - Introduction: OCI Vision - - Lab 1: Use Vision Service through the OCI Console - - Lab 2: Create a custom model through the OCI Console - - Lab 3: Access OCI Vision in DataScience Notebook Session -- [Live Labs - Biomedical Image Classification](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3097&clear=RR,180&session=101189893786132) - - Lab 1: Use DLS to Bulk Label Dataset - - Lab 2: Create Custom AI Vision Model -- [Live Labs - Premier League Video Analysis](https://apexapps.oracle.com/pls/apex/r/dbpm/livelabs/view-workshop?wid=3489&clear=RR,180&session=101189893786132) - - Lab 1: Provision OCI Data Science - - Lab 2: Provision Autonomous Data Warehouse - - Lab 3: Recognize Players and Shirt Numbers (OCI Console) - - Lab 4: Recognize Players and Shirt Numbers (Programmatically) - - Lab 5: Translate Camera Coordinates to Football Pitch Coordinates - - Lab 6: Connecting to Autonomous Data Warehouse - - Lab 7: Processing the entire video -- [How to Use AI Vision and Drones for Inventory Management](https://go.oracle.com/LP=135420) +- [AI Solutions Hub](https://www.oracle.com/artificial-intelligence/solutions/) +- [Oracle AI Vision on oracle.com](https://www.oracle.com/uk/artificial-intelligence/vision/) +- [Oracle AI Vision documentation](https://docs.oracle.com/en-us/iaas/vision/vision/using/home.htm) +- [Announcing OCI Vision stored video analysis general availability](https://blogs.oracle.com/ai-and-datascience/post/oci-vision-stored-video-analysis-ga) # Reusable Assets Overview +## Cloud Coaching + - [Cloud Coaching - Boost Your Oracle AI Services](https://youtu.be/VVWTqqlIEhg) - Describe an image using OCI AI Vision, Generative AI Service and Oracle Integration -- [OCI image classification using data labeling and vision service](https://github.com/carlgira/oci-image-classification) -- [OCI object detection using data labeling and vision service](https://github.com/carlgira/oci-object-detection) +- [Cloud Coaching - Unlock Culinary Creativity: AI Powered Cooking Adventure from Fridge to Fork!](https://www.youtube.com/watch?v=tRVwTLKS4rE&t) + - You are in the mood of cooking an exotic dish. You open the refrigerator, and using the mobile phone, access your favourite retail app to scan the items you have and submit. + - This triggers a series of actions: + - OCI AI Vision identifies the items (specific vegetables, egg, chicken etc). + - On choosing your favourite cuisine, OCI Generative AI suggests a list of dishes based on identified items. + - On selecting your favourite dish, OCI Generative AI provides the detailed recipe. Also, the missing ingredients are listed, with an option to order the same. +- [Cloud Coaching - Discover OCI Vision for Object Detection in Manufacturing, Retail, & More](https://www.youtube.com/watch?v=lHH_1MXGOc0) + - In this session you learn how OCI Vision can identify, classify, and quantify visual data in powerful ways. Watch as the service identifies objects (people, cars, trees, and so forth) and categorizes them. See how it can even detect faces or key points in faces for analysis. + +## Blogs + +- [OCI AI Vision Facial Detection in Oracle Analytics Cloud](https://blogs.oracle.com/analytics/post/ai-vision-facial-detection-in-oac) +- [Empowering Search with OCI Vision in Oracle APEX](https://blogs.oracle.com/apex/post/empowering-search-with-oci-vision-in-oracle-apex) +- [Oracle JET (VDOM) and OCI VISION](https://blogs.oracle.com/developers/post/oracle-jet-vdom-and-oci-vision) +- [Oracle Analytics Integration with AI Vision Video Analysis](https://blogs.oracle.com/analytics/post/analyze-videos-with-oracle-ai-video-and-oracle-analytics) +- [OCI Vision Healthcare Image Analysis](https://blogs.oracle.com/ai-and-datascience/post/advancing-healthcare-image-analysis-on-oci) + +## Demos & Events + - [Perform image recognition with Oracle Cloud Infrastructure OCI Vision](https://youtu.be/G11INIVtlMY?si=ixMoLE2jSq7f_Iyi) -- [AI vision web client](https://github.com/oracle-devrel/oci-tf-vision-web-client) - - Terraform script that will create a set of resources on OCI to create a web app to test an existing vision model. - [Vision Image Classification demo](https://youtu.be/9_NSumsQcMs) - [Vision Object Detection demo](https://youtu.be/iiuluuOlAKc) - [AI Vision Car parking utilisation demo (OCI AI Vision, OAC)](https://youtu.be/VlZDaUC2Jus) - [Cloud Customer Connect - How to Train Your Oracle AI Cloud Service Model](https://community.oracle.com/customerconnect/events/604740-oci-how-to-train-your-oracle-ai-cloud-service-model) - In this session, we demonstrate how you can use OCI AI services, to create custom models using the data labeling, vision and document understanding service. +- [Build a meal recommmendation Engine with OCI Vision & Generative AI](https://www.oracle.com/artificial-intelligence/build-a-meal-recommendation-engine-with-ai/) +- [Automate Defect Detection Using Drones and OCI Vision](https://www.oracle.com/artificial-intelligence/automate-defect-detection-with-drones/) +- [Breast and Lung Cancer Research with AI in OCI Vision](https://www.oracle.com/artificial-intelligence/early-detection-cancer-with-oci-vision/) +- [Automatically Identify Damaged Packages Using Oracle AI Services](https://www.oracle.com/artificial-intelligence/identify-damaged-packages-with-ai/) +- [Customized Object Detection with OCI Vision](https://www.oracle.com/artificial-intelligence/ai-vision-for-object-detection/) + +## Medium Posts +- [Configure OCI AI Vision API Using POSTMAN](https://medium.com/@nitish.joshi_74493/configure-oci-ai-vision-api-using-postman-27dabe39a5a7) +- [Terraform script to build a web app for OCI vision service](https://medium.com/@carlgira/terraform-script-to-build-a-web-app-for-oci-vision-service-b67e88d446c1) +- [Creating Composable Analytic Applications with Oracle Visual Builder, Analytics and OCI Vision AI Services](https://medium.com/oracledevs/creating-composable-analytic-applications-with-oracle-visual-builder-analytics-and-oci-vision-ai-705236c1de07) # License