Mimir semantic search finds assets using natural language

Mimir brings meaning to asset search

BERGEN — Cloud-native asset management company Mimir announces adding semantic search capabilities to its cloud video production and collaboration solution, ensuring content creators and media companies can find and use the assets they need using natural language search.

A new way to search – and find

With this technology, users can search their media assets and have results returned on the meaning of a query and not on its exact wording. The query can combine abstract concepts, visual context, and transcript-based content – all in a regular sentence in the searcher’s language. So asking for “George Bush speaking about the war on terror in front of a military crowd at an outdoor event under stormy, threatening clouds.” will get you a result if you have it in your archive – and other results near what you asked for. This natural language approach is the same we are now accustomed to using when interacting with Chat GPT and similar models.

Because Mimir has been using automated AI-powered tagging for a long time, the shift for existing Mimir uses will not be as tectonic as for those used to less enhanced asset search. The difference will be in the user experience; the ability to use natural human language and improved quality of search results.

Soft searches, hard results

With semantic search, it’s unnecessary to be an archive aficionado, knowing exactly what to search for and what will get returned – nor does the material need to be manually logged with specific keywords or metadata. For those editing a story, looking for archive, edited, near-live or live material to add to it, the semantic search will open a world of content discovery. Journalists and editors can find any relevant material they did not know was in their archive and leverage the gold mine of historical content they can access. In Mimir itself, it will be possible to toggle between existing, term-matching tagged, and precise search and natural language semantic search, ensuring the right tool can be used in the right context.

Mimir uses Amazon’s just-released multimodal LLMs running on AWS Bedrock to power its new semantic search – but customers can also choose to integrate their preferred semantic search providers. This flexible approach to integrating AI services combined with a continuous delivery method means Mimir can adapt to the rapidly changing reality of semantic search capabilities.

Cut, render, deliver

Mimir has also further enhanced the quick-cutting capabilities introduced by the Mimir Cutter. Users can now add material from any source to a sequence to be rendered or delivered to an NLE, such as Adobe Premiere Pro, for full-feature editing.

By adding the capability to extract content from growing files as they are captured, Mimir makes it possible to mix and match any content in Mimir Cutter and Adobe Premiere Pro, from archive through edited, near-live, and live sources. This functionality adds value in both MAM, PAM, and DAM workflows, as the technical limitations sometimes found between different types of content are obliterated.

For users of Adobe Premiere Pro, Mimir will now work with partial downloads for high-res files – only downloading the sections of assets being worked on, thus increasing efficiency when working with larger assets by an order of magnitude.

Share and care

Taking collaborative working capabilities to the next level, Mimir users can now securely share, collaborate on, and receive any view, file, editing project, folder, or ongoing live ingest with other users in their organization or with external collaborators. Dynamic upload portals can be set up ad-hoc or permanently to allow stringers and freelancers to deliver time-critical material, one-off and in bulk, to the media organization.

The ability to collaborate on video projects across departments, easily handing off from one editor to another, and reusing and repurposing assets and work is necessary for using creative resources to their fullest potential. Combined with fast cutting capabilities and the paradigm-shifting addition of semantic search, Mimir makes it possible to create more, create faster, and create better.

Want to see it in action? Book a demo at NAB!