Activeloop AI Knowledge Agent - Deep Research on Your Multi-Modal Data
by•
Need to find answers to hard questions across multiple sources, including your private data? Use our Knowledge Agents, powered by AI search to scan up to billions of rows of any data - images, PDFs, text, tables and more, and provide a well-researched answer.
Replies
Congrats on the launch, @david_buniatyan! I saw Deep Lake works with all kinds of data. How do you handle something like videos or images compared to text?
@karen_khachikyan2 thanks for the question - I think the best use case for AI Knowledge Agent on our end is images, PDFs, text, and tables at the moment. AI Knowledge Agent can't readily process videos (unless you convert it into sequences of images). The temporal component is a blocker.
However, if you're using Deep Lake outside of Knowledge Agent use case (i.e. to train ML models), it's readily available to sue with videos and we have multiple customers using it that way. In that case, it depends on what the use case is (and videos can be handled in their raw format, or sequence of images format, etc.).
Does this answer your question? Happy to dive deeper into it.
What about my local files on my computer? Or is it cloud first? I might need to sync files to dropbox or google cloud first maybe?
@sentry_co good question. in the video demo you can see the example of local data upload (4:03)! What would be your use case?
OCR-free retrieval of documents, images, and videos? This truly feels like the next era of AI-driven data utilization! Huge congratulations on your launch! 🎉
@kay_arkain thank you so much, Kay! You're absolutely right.
This looks like an incredibly useful tool for tackling complex, multi-source research questions. The ability to search across diverse data types and extract well-researched answers is definitely something the community will benefit from. Looking forward to seeing how people adopt it in different use cases.
Congrats on the launch, @david_buniatyan and team!
@samvelyanmany thanks! What would be your preferred use case?
Looks like a very powerful tool! Does it support searching over Google Drive as well?
@tleyden Thanks for the question! Not yet, but we're planning to add other connectors soon.
@tleyden for now, you can integrate Dropbox as well as your favorite cloud provider (AWS, GCP, Azure).
Behind every great product there is a great team.
Congrats Davit and the team with the launch.
@sargis_karapetyan2 thanks a lot, Sargis!
Congrats on the launch of Deep Lake AI Knowledge Agent! The ability to perform deep research across multiple data types and sources is impressive!
@mikita_aliaksandrovich thanks a lot, Mikita. How would you use it?
@david_buniatyan You're welcome! I'd use Deep Lake AI Knowledge Agent for tasks like analyzing large datasets across various formats, such as research papers, financial reports, and customer feedback!
This is exciting! Compelling demo!
I am curious how effective Deep Lake's integrated knowledge retrieval approach is for avoiding hallucinations and finding relevant articles not found by other tools in the same space?
@ngalstyan4 good question!
I wouldn't say it's possible to completely avoid hallucinations. Hallucinations happen for two reasons: wrong context, wrong answer by model, and right context, but still a wrong answer by a model. In the latter case, we can't do much. But we focus on making the former case obsolete!
How we do this:
Query planning and gathering context from various datasets.
Querying flexibility (choose to do hybrid, vector, keyword search, etc.)
Multi-modality (on ingestion, gaining more depth of insight into what data is about - what is contained in figures, for instance), which helps pass more imoprtant context to the model.
We also learn over time what queries you consider correct, which helps further improve search experience and increase retrieval accuracy. No other vendor can handle this, as well as #3 as well as we do!
@denisss haha, not sure how you mean this exactly but thank you! :)
@denisss thanks!
Considering the most valuable data tends to be in-house, this is amazing 🤩 Great work, @mikayel_harut !
@nicozensara thank you so much <3