Subscribe
Sign in
Tilores
p/tilores-ragCustomer data search, unification and retrieval for LLMs
Start new thread
Steven Renwick

Tilores Identity RAG - Customer data search, unification and retrieval for LLMs

by•

Data scientists connect Tilores to their LLM to search internal customer data scattered across multiple source systems. The LLM retrieves unified customer data, which it uses to answer queries or as context when querying subsequent unstructured data.

Add a comment

Replies

Best
Steven Renwick
Maker
📌
Hi Makers! I'm Steven, one of the founders of Tilores. I've very excited to introduce our LangChain integration to you so you can use Tilores as a data source for "Identity RAG". As companies increasingly turn to Large Language Models (LLMs) to enhance customer interactions, a common challenge arises: customer data is often fragmented across multiple internal databases and systems. This fragmentation makes it hard for LLMs to provide reliable, accurate responses based on complete, up-to-date information. Tilores solves this by offering a real-time API that unifies scattered customer data. Originally developed for a European consumer credit bureau to power fraud prevention and anti-money laundering solutions, Tilores' "identity resolution" technology is now available to supercharge LLMs through an integration with LangChain, the leading LLM framework. With Tilores, you can: 🖇️ Seamlessly connect all your customer data sources, including valuable metadata like orders, transactions, and more. ⚖️ Build a unified "source of truth" for your LLM, ensuring it always has access to complete and relevant customer insights. ⚡ Perform lightning-fast searches and updates, keeping your LLM working with real-time data. 🤖 Use your preferred LLM within your own infrastructure—your data stays securely within your systems. 💾 Enjoy automated scaling, enterprise-grade reliability, and GDPR compliance, all tailored to European data privacy standards. 🙌🏻 Empower your LLMs with unified customer data, and take your AI-driven customer experiences to the next level with Tilores. Tilores is designed to be used for structured customer data alongside a vector database for unstructured data to give you the ultimate enterprise LLM experience. For anyone from Product Hunt building a LLM based on Tilores' Identity RAG, we will offer you $500 of free credit to get started. You can also visit our website: https://tilores.io/RAG Go straight to the GitHub repo for our LangChain integration: https://github.com/tilotech/lang... Or read this Medium article for more context about Identity RAG: https://bit.ly/3TSwe22
Akshay Lahri
@major_grooves Interesting. So in my app, we crawl travel data from across hundreds of travel sites, articles and feed those data packets onto LLM based on user's query. Is there anyway Tilores can assist in the entire process? Super congratulations on the launch.
Steven Renwick
Maker
@akshay_lahri how do you currently feed that data into the LLM? A vector database? If you end up with lots of duplicate records when you are crawling, Tilores might be able to help you deduplicate them, but tbh when it comes to the unstuctured text in a typical website article, you might be best sticking with a vector database.
Chris Schagen
@major_grooves congrats, this is really useful. We have a lot of duplicative records in our CRM, especially when folks move on from one co to another, this could be a great extra layer to remove one frequent failure mode.
Steven Renwick
Maker
@cschagen that is certainly something we can help you with!
Tom Hibbert
@major_grooves congratulations on the launch. Cool product! How does Tilores RAG deal with data versioning? So how does it track the change in data over time and can I perform a search based on a specific point in time? Cheers
Kyrylo Silin
Hey Steven, How quickly can the system update and retrieve unified customer profiles? Have you considered expanding beyond customer data to other domains where entity resolution could be valuable? Congrats on the launch!
Hendrik Nehnes
Maker
Hi @kyrylosilin the process to update a profile takes less than 500 ms. - No matter how many profiles change at the same time. We are also using Tilores in other spaces like company data. Thank you Hendrik
Lukas Rieder
@kyrylosilin I found their API to be REALLY fast, even at scale. And what I found really nice comparing to other entity resolution systems, you can define the golden record at read-time, as opposed to at write time. This way you can get different perspectives on the same source data. For example, for some applications you might want to have the latest email of an unified customer. For some applications you might want to have all emails that belong to one unified customer. The ability to define different golden records at read-time makes Tilores really flexible.
Ditarth Desai
Well done on launching Tilores! A great step forward in streamlining data search and retrieval.
Hendrik Nehnes
Maker
Thank you @ditarth_wbs. We also want to ensure that your customers get the best service and the data stays private.
Tony Hunter
Exciting Steven and team!
Hendrik Nehnes
Maker
Thank you @tony_hunter
Ali Jan
Congrats on the launch! 🚀 Connecting Tilores to LLMs for unified customer data retrieval is a powerful tool for data scientists. Looking forward to seeing how it streamlines customer data management and enhances query capabilities across multiple systems!
lxfater
十分硬核的技术。
Steven Renwick
Maker
@lxfater 谢谢。我们有非常过硬的工程师。
Arthur Poot
Nice, will recommend it to my marketing agency. I love the RAG feature. Does it also support real time syncing my contacts across LinkedIn, Google Sheets, Eventbrite, Meetup and HubSpot in one database?
Steven Renwick
Maker
@arthurpoot yes - as long as we can access them via API we can both pull data from them and push data back to keep them updated - in real-time. Glad you like it!
Vimal Kumar
🎉 Congratulations on the launch of Tilores Identity RAG! 🚀 I’ve created an interactive demo of your product using Supademo to showcase its features in action. You can check it out here: https://app.supademo.com/demo/cm... Supademo allows you to create engaging, interactive demos in minutes, and it's a great way to highlight key aspects of your product for potential users. I'd love to see this demo added to your launch page—it could help drive more engagement during your launch and beyond! Feel free to share it with your community and let us know if you’d like any updates or adjustments. Best of luck with your launch!
Hendrik Nehnes
Maker
Thank you @vimal_kumar_rai that is a nice tool that you created there.
Steven Renwick
Maker
@vimal_kumar_rai that's pretty cool actually.
Jan Oberhauser
Congratulations on the launch. It looks really cool and powerful, and it seems like something that will simplify many use cases. I'm looking forward to seeing what people build with it.
Hendrik Nehnes
Maker
Thank you @janoberhauser. I opens the door for so many different use cases and allows all Python users to easily access their data in Tilores. I am looking forward to see people using it from within N8N.
Alex Gordon-Furse
Excited to check it out thanks Tilores team
Hendrik Nehnes
Maker
@giomate let us know if you have any questions.
Nicolas
This is interesting, will share with my engineering colleagues right away. We had good experiences using Tilores' other product in our risk engine, but the RAG product could really solve some issues in our LLMs. Quick question: can you shed some light on scalability?
Steven Renwick
Maker
@nicolas39 so Tilores is designed to be highly-scaling with zero input required, since we use serverless technology. So we can ingest as much data and provide as many searches, in parallel, as you could ever need. The only thing you would have to keep an eye on is the cost of the LLMs themselves, since that is outwith our control.
Arpit Choudhury
Congrats to the team on this milestone! Excited to see how Tilores is evolving!
Steven Renwick
Maker
@irhymeth your support and the support of the good data people, has been invaluable!
Abhay Talreja
wow @major_grooves, hats off. love the idea of seamlessly unifying scattered data - sounds like a game-changer.
Hendrik Nehnes
Maker
@major_grooves @abhaytalreja it really is and it is soo easy to use
Madeline Lawrence
god speed tilo team! forever in your corner. 🔥🔥
Stefan Berkner
Maker
@madelinelawren Thank you for your support Madeline!
Hendrik Nehnes
Maker
@madelinelawren Thank you :-)
Scott Taylor
Great work, love this!
Sage Wang
Tilores really simplifies the process. I especially love the fuzzy search that corrects inaccuracies, such a smart feature. Looking forward to seeing this in action!
Steven Renwick
Maker
@flashsonic thanks Sage. People often forget about how important fuzzy search is, but it deals with the reality of real-world data - it is messy and often contains inaccuracies.
Hendrik Nehnes
Maker
@flashsonic thanks looking forward to see you testing
Jon Boush
Following this launch closely
Steven W.
Wow, @major_grooves, this is truly a game-changer for data scientists and enterprises leveraging LLMs! 🚀 The fragmentation of customer data has always been a significant hurdle, and Tilores seems to offer a seamless and efficient solution to this problem. The fact that it was initially developed for high-stakes environments like fraud prevention and AML really speaks to its robustness and reliability. Integrating Tilores with LangChain to unify and streamline customer data is brilliant. The potential for enhanced customer interactions and more accurate query responses is immense. Plus, the emphasis on GDPR compliance and data security is crucial for businesses operating within European standards. The $500 free credit offer is a generous touch and a great incentive for the Product Hunt community to dive in and explore the capabilities of Tilores. Kudos to the team for creating something that can significantly elevate AI-driven customer experiences. Can't wait to see how this transforms the landscape for LLM applications! 🌟
Steven Renwick
Maker
@steven_wang_0804 glad you like it. Thanks for your comment!
Olia Nemirovski
Impressive integration with LangChain for unified customer data. This could significantly enhance AI-driven customer experiences. How do you handle data freshness and consistency when aggregating information from multiple sources in real-time?
Hendrik Nehnes
Maker
@olia_nemirovski data can be ingested from different sources in real-time while resulting in consistent data. If you are interested in the details let’s talk
Steven Renwick
Maker
@olia_nemirovski hi Olia. Good question. The real-time data ingestion is a major feature of Tilores. Other systems might do this in batch, but Tilores will literally ingest customer data from any source via API, in real-time regardless of volume. It doesn't matter if it is 1 record per second or 1,000.
Jonathan Viet Pham
Congrats to the Tilores team on the launch of Identity RAG! This sounds like a powerful tool for streamlining access to unified customer data. Are there any specific integrations available for different source systems to enhance data retrieval?
Hendrik Nehnes
Maker
@vietpham there is a snowflake and webhook integration, howeverwe also provide a graphql API and a python sdk which easily integrates with most systems
Steven Renwick
Maker
@vietpham our most used integrator is actually for Snowflake. Other than that, using our GraphQL API you can connect to any data source or we can discuss building a specific connector for you for specific sources.