A tool to automate image processing using AI
The challenge
We developed a solution that consisted of automating the processing, identification, tagging, and searching of product images using AI. The final outcome would be a media library with a search engine.
What we did
Smart architecture and AI features
We designed and implemented a cloud-based architecture using Azure Storage, Azure Functions, Azure AI Foundry, and Azure AI Search to deliver an efficient and scalable image-management workflow.
Our solution uses generative AI models to automatically extract product names, descriptions, and tags from images. All this information is stored in Azure AI Search with vector capabilities, enabling powerful search experiences through a custom interface and a dedicated search API.
Advanced search and user experience through AI
- Intelligent enrichment: The inference model processes the image and identifies the product, executing a flow to extract its data (description, tags and other details).
- Advanced indexing: Enriched data is converted by an embedding model and stored in a vector-enabled index, ready to power smarter and more relevant search experiences.
- Powerful search: When the user performs a query (via Azure Search connected through a REST API), the embedding model vectorizes the search input and compares it against the indexed content, returning the most relevant results. This approach enables hybrid search, going beyond traditional text-based search.
- Additionally, an automated image-processing pipeline takes care of renaming, compression, and intelligent cropping to deliver consistent product images.
What we achieved
- A hybrid semantic search that provides faster and relevant results.
- An enhanced user experience that reduces manual work.
- A robust solution that can be applied across multiple industries.
A tool to automate image processing using AI
The challenge
We developed a solution that consisted of automating the processing, identification, tagging, and searching of product images using AI. The final outcome would be a media library with a search engine.
What we did
Smart architecture and AI features
We designed and implemented a cloud-based architecture using Azure Storage, Azure Functions, Azure AI Foundry, and Azure AI Search to deliver an efficient and scalable image-management workflow.
Our solution uses generative AI models to automatically extract product names, descriptions, and tags from images. All this information is stored in Azure AI Search with vector capabilities, enabling powerful search experiences through a custom interface and a dedicated search API.
Advanced search and user experience through AI
- Intelligent enrichment: The inference model processes the image and identifies the product, executing a flow to extract its data (description, tags and other details).
- Advanced indexing: Enriched data is converted by an embedding model and stored in a vector-enabled index, ready to power smarter and more relevant search experiences.
- Powerful search: When the user performs a query (via Azure Search connected through a REST API), the embedding model vectorizes the search input and compares it against the indexed content, returning the most relevant results. This approach enables hybrid search, going beyond traditional text-based search.
- Additionally, an automated image-processing pipeline takes care of renaming, compression, and intelligent cropping to deliver consistent product images.
How to change an entire data strategy
I imagine 8wires as that sincere and honest partner that takes you out of all that noise and helps you focus on what is important, no matter how unsexy it may be, to achieve a great long-term goal.
The one who accompanies you through the hard times and helps you through the tough decisions, knowing that there is no easy road. The one who gives you the push or the tools so that you climb and be yourself the one who reaches the summits you propose in a healthy, sustainable and energetic way. And above all, the one who steps aside when he knows that he is not helping you or that he will not be able to give you what you need.
I don't know if it is helpful, but somehow I saw on the web a visual explanation of the problem in the data/technology world (I don't know if with this metaphor) before showing how it is to work with us and finally, another visual explanation of the result.
Like a bridge over troubled waters
I imagine 8wires as that sincere and honest partner that takes you out of all that noise and helps you focus on what is important, no matter how unsexy it may be, to achieve a great long-term goal.
The one who accompanies you through the hard times and helps you through the tough decisions, knowing that there is no easy road. The one who gives you the push or the tools so that you climb and be yourself the one who reaches the summits you propose in a healthy, sustainable and energetic way.
A tool to automate image processing using AI
The challenge
We developed a solution that consisted of automating the processing, identification, tagging, and searching of product images using AI. The final outcome would be a media library with a search engine.
What we did
Smart architecture and AI features
We designed and implemented a cloud-based architecture using Azure Storage, Azure Functions, Azure AI Foundry, and Azure AI Search to deliver an efficient and scalable image-management workflow.
Our solution uses generative AI models to automatically extract product names, descriptions, and tags from images. All this information is stored in Azure AI Search with vector capabilities, enabling powerful search experiences through a custom interface and a dedicated search API.
Advanced search and user experience through AI
- Intelligent enrichment: The inference model processes the image and identifies the product, executing a flow to extract its data (description, tags and other details).
- Advanced indexing: Enriched data is converted by an embedding model and stored in a vector-enabled index, ready to power smarter and more relevant search experiences.
- Powerful search: When the user performs a query (via Azure Search connected through a REST API), the embedding model vectorizes the search input and compares it against the indexed content, returning the most relevant results. This approach enables hybrid search, going beyond traditional text-based search.
- Additionally, an automated image-processing pipeline takes care of renaming, compression, and intelligent cropping to deliver consistent product images.
How to change an entire data strategy
I imagine 8wires as that sincere and honest partner that takes you out of all that noise and helps you focus on what is important, no matter how unsexy it may be, to achieve a great long-term goal.
The one who accompanies you through the hard times and helps you through the tough decisions, knowing that there is no easy road. The one who gives you the push or the tools so that you climb and be yourself the one who reaches the summits you propose in a healthy, sustainable and energetic way. And above all, the one who steps aside when he knows that he is not helping you or that he will not be able to give you what you need.
I don't know if it is helpful, but somehow I saw on the web a visual explanation of the problem in the data/technology world (I don't know if with this metaphor) before showing how it is to work with us and finally, another visual explanation of the result.
Like a bridge over troubled waters
I imagine 8wires as that sincere and honest partner that takes you out of all that noise and helps you focus on what is important, no matter how unsexy it may be, to achieve a great long-term goal.
The one who accompanies you through the hard times and helps you through the tough decisions, knowing that there is no easy road. The one who gives you the push or the tools so that you climb and be yourself the one who reaches the summits you propose in a healthy, sustainable and energetic way.
.png){kind=small}