Bing has made a lot of bets over the years that haven't really panned out, maybe it will be different this time.
Granted, Microsoft is much less reliant on Bing's ad revenue than Alphabet is on Google's, which might allow Bing to really change the search experience without having to worry too much about selling ads. It's going to be interesting to see how these products evolve in ways that serve both the user and the business interests behind the search results, especially if we start seeing VC backed AI search engines pop up which don't need to focus on existing advertiser revenue.
Well, Microsoft quite literally owns OpenAI (the ChatGPT devs) and they're well-known for adding pointless features to Bing (Bing Rewards, daily wallpaper, overly-formatted results pages, etc).
Even if/when Bing adds AI features, SEO will not be "dead". Not only does nobody use Bing, but the results will be mixed in with traditionally-indexed results. SEO is by-far the easier route to getting your product in search results, considering how hard AI models get pruned.
What kinda thing do you want to search? Text I guess? But there are search engines for images, gifs, video, all kinds of stuff.
I'm working at an open-source project that builds an AI-powered search framework [0], and I've built some examples in very few lines of code (for searching fashion products via image or text [1], PDF text/images/tables search [2]) and one of our community members built a protein search engine [3].
A good place to start might be with a no-code solution like (shameless self-plug time) Jina NOW [4], which lets you build a search engine and GUI with just one CLI command.
Hi thank you for your answer. Actually my original idea was to build it for something else rather than the web in particular. Can you please advice me on which masters I should pick between distributed systems , machine learning and theoretical computer science/algorithm if my end goal is this?
To be clear, Jina AI stuff helps with the search engine itself. Getting the data is another matter entirely, and pretty much outside of our scope (although we do provide some example datasets with Jina NOW, like artworks, music, etc)
For me, I'll invite as many close friends as possible to a restaurant with cuisine we've never tried before (last time was Ethiopian). It starts off a new year (relative to my birth) with novelty, good food, and warm feelings
This is more related to search tasks, where we encode text and image pairs to use text to search image. ResNet can also be served a backbone for search tasks: content-based image search/reverse image search/search image with image. You need to remove the ResNet50 classification head.
On the other hand, Tensorflow or MLNet are machine learning frameworks, to achieve the task you can choose whatever you want to build the model components.
Sets of ResNets can do search indexing. Picture similarity can be inferred by vector cosine of the two sets of ResNets evaluations between two pictures.
[Run a numerical optimizer on weights for the different ResNets' outputs for best results ]
What text-to-speech model is being used? I've seen big improvements in the past few years that could make me actually want to listen to these (since the voices sound more natural now)
In terms of matching embeddings and performing similarity search on text/images - folks are already using the framework (Jina) for that and getting decent results.
In terms of processing the PDFs and extracting that data. idk. That depends on a lot of factors - e.g. do you need to OCR the PDFs or can just extract text directly? Either way, should be possible to write a module and then easily scale it up (Jina supports shards/replicas). Anyway, lemme know. I'm in talks with folks about this kind of shitshow...uh...use case now.
Jina supports multiple vector database backends, like Weaviate, Qdrant and others. For others (like Milvus), suggest you ask on the Slack [0] - responses tend to be fast.
I may have misworded it (if I wrote those words - PDF rots the brain and my memory likewise).
Agreed on the rest. PDFs don't store machine-readable data. Often just pixelated scanned hot garbage dumpster fire text.
I hate PDFs but have to work with the satanforesaken things. Hence the notebook. It's my little way of trying to give my little PDF-bespoked-hellscape a tiny little glow-up.
I probably didn’t read your comment closely enough. When I hear about PDF parsing or PDF as data I immediately get flashbacks from a project years ago where I had to parse PDF files. I think I am still traumatized by this experience so whenever I hear somebody wants to do this I just want to scream “Nooo. Don’t do this”
[1] https://community.chocolatey.org/