It was already indexed!

I recently had the pleasure of chatting with @dmitrykan on his Vector Podcast. Check it out: https://dmitry-kan.medium.com/vector-podcast-with-sid-probstein-search-in-siloed-data-with-swirl-f2b9595a2715

We talked about quite a few things, including:

• The challenges of enterprise search in the post-cloud era

• How cross-silo search is particularlyt tricky because of entitlements (aka permissions) across silos

• Zero-code configuration of connectors in Swirl, where JSON path and developer API doc get the job done

• How large language models contextually re-rank disparate search results

There was an interesting twist at the end of the call. Dmitry uses a service called Clearword to transcribe recordings. Dmitry asked: “how quickly can you index the transcript and search it with Swirl?”

Here is my answer: It was already indexed!

Since there is no audio and it goes by quickly, let me explain ... Clearword emailed the transcript to both of us shortly after recording ended. It was indexed by Microsoft Outlook within seconds of arriving in my inbox.

To verify this, I copied some text from the middle of the transcript and pasted it into Swirl, which returned the link to the email message with the transcript and the phrase I searched for.

That simple truth - that the average enterprise is awash in search forms - is the entire reason metasearch is such a game-changing approach. Instead of making yet another repository, Swirl sends queries to existing search APIs and re-ranks the results from everything. It saves users a huge amount of time without a major IT project.

Want to see for yourself? git it going with 2 commands via Docker here: https://github.com/swirlai/swirl-search