Bay.Area.AI: Interview with Jiang Chen, Zilliz

hello everybody my name is Alexi kro I'm hello everybody my name is Alexi kro I'm the founder and organizer of B area AI the founder and organizer of B area AI which is the most established AI up in which is the most established AI up in the Bay Area in the world running the Bay Area in the world running continuously for 10 years in Vera in the continuously for 10 years in Vera in the headquarters of the best technical headquarters of the best technical companies in the world today we're at companies in the world today we're at GitHub you see all the developer GitHub you see all the developer activity happening right behind us it's activity happening right behind us it's the live dashboard and uh tonight we the live dashboard and uh tonight we have a meop uh which covers several key have a meop uh which covers several key topics in AI uh programming uh it's DP topics in AI uh programming uh it's DP PR from Stanford rigorous way to program PR from Stanford rigorous way to program LMS and we have serious about rag so we LMS and we have serious about rag so we have uh rag Vector rag we have graph rag have uh rag Vector rag we have graph rag we have several speakers and uh uh today we have several speakers and uh uh today I have with me JN Chen who is the head I have with me JN Chen who is the head of system and development relations at of system and development relations at zillis and the database called Milos zillis and the database called Milos welcome John well thanks for having me welcome John well thanks for having me yes thank you thanks a lot so you're one yes thank you thanks a lot so you're one of the leading open source uh rare of the leading open source uh rare company so tell us a little bit you know company so tell us a little bit you know uh it's fairly recent so how did you uh it's fairly recent so how did you this you know project started how did this you know project started how did you become the head of devil uh and how you become the head of devil uh and how basically you see all this uh new area basically you see all this uh new area unfolding well yeah yeah sure um so unfolding well yeah yeah sure um so everything started from um 2019 2020 everything started from um 2019 2020 when we started to build the first open when we started to build the first open source Vector database in the world source Vector database in the world which is called Milas um and the company which is called Milas um and the company behind this is zillis so I know we have behind this is zillis so I know we have two names so it created some confusion two names so it created some confusion for the users um but yeah we are uh um for the users um but yeah we are uh um we donated the mil product to Linux we donated the mil product to Linux Foundation data and AI um but till today Foundation data and AI um but till today we're still the uh the main uh we're still the uh the main uh contributor and maintainer of the contributor and maintainer of the project M and it has been very popular project M and it has been very popular among the developers it now has 29k among the developers it now has 29k stars um so yeah really really awesome stars um so yeah really really awesome numbers um we love to contribute and to numbers um we love to contribute and to create the value to the community so at create the value to the community so at the very early days of M us um you know the very early days of M us um you know probably most of the users of vector probably most of the users of vector search were in the uh recommender system search were in the uh recommender system and you know machine learning um domain and you know machine learning um domain but however over the time as the you but however over the time as the you know AI is really democratizing the know AI is really democratizing the whole stack of um AI power search uh we whole stack of um AI power search uh we have seen more and more users um like have seen more and more users um like full like web developers mobile full like web developers mobile developers who didn't really have a lot developers who didn't really have a lot of experience with machine learning of experience with machine learning start to use Vector search and start to start to use Vector search and start to embrace the power of semantic search uh embrace the power of semantic search uh into their uh technical uh into their into their uh technical uh into their tax stack so this is um really a a great tax stack so this is um really a a great time to you know um democratize the the time to you know um democratize the the very complex AI stack which was used very complex AI stack which was used which was um only available to large which was um only available to large teams like with hundreds of people in teams like with hundreds of people in the instructor team um now like with the the instructor team um now like with the uh EAS of use of iding models and Vector uh EAS of use of iding models and Vector database um everyone can build a search database um everyone can build a search everyone can embrace you know rag or everyone can embrace you know rag or image search into their applications MH image search into their applications MH now this is great so like you got an now this is great so like you got an early start you were lucky when CH hit early start you were lucky when CH hit right suddenly you know this kind of right suddenly you know this kind of whole opportunity happened and this is whole opportunity happened and this is interesting because uh I am now ai interesting because uh I am now ai commune architect at NE which is an commune architect at NE which is an established Dr database which created established Dr database which created the segment of graph databases right it the segment of graph databases right it exists for decades and so it also is now exists for decades and so it also is now the key vehicle to De hallucinate LMS the key vehicle to De hallucinate LMS right and so um it's very interesting so right and so um it's very interesting so so when you guys started like what was so when you guys started like what was the use case right it was it was not the the use case right it was it was not the ls right it was more traditional yeah we ls right it was more traditional yeah we talk about history uh I mean I I I'll talk about history uh I mean I I I'll dive a bit deeper into that so actually dive a bit deeper into that so actually the history about myself is that I had the history about myself is that I had years of years of experience in Search years of years of experience in Search and indexing in the traditional web and indexing in the traditional web search image and video search search image and video search so in the old days like 5 years ago yeah so in the old days like 5 years ago yeah not that long ago um there was two not that long ago um there was two vehicles driving the innovation of vehicles driving the innovation of search technology one is embedding AKA search technology one is embedding AKA different networks and all the data different networks and all the data generated from them and the other one is generated from them and the other one is kg Knowledge Graph yes so I I really kg Knowledge Graph yes so I I really think that those are two um important think that those are two um important Technologies Knowledge Graph the way I Technologies Knowledge Graph the way I see is that it has a structured and see is that it has a structured and systematic way to mining to to mine the systematic way to mining to to mine the dat the information out of the you know dat the information out of the you know unstructured data and Vector embedding unstructured data and Vector embedding is a again um efficient systematic way is a again um efficient systematic way to you know encode to extract the um you to you know encode to extract the um you know representation to extract the the know representation to extract the the essence of the semantic out of the essence of the semantic out of the unstructured data so both of the unstructured data so both of the Technologies are very important in terms Technologies are very important in terms of understanding the the like joint of understanding the the like joint amount of unstructured data in the world amount of unstructured data in the world because you know from the um even from because you know from the um even from the Y age um most of the information on the Y age um most of the information on the world in the world was like web the world in the world was like web pages and there wasn't really that much pages and there wasn't really that much structure data yes yeah um so that in structure data yes yeah um so that in order to tackle this problem we really order to tackle this problem we really need some rather than you know having need some rather than you know having human labor to to you know label the human labor to to you know label the data to do annotations we need a more data to do annotations we need a more scalable a more systematical way and de scalable a more systematical way and de neural network and knowledge knowledge neural network and knowledge knowledge engineering are very important engineering are very important techniques to tackle that problem and techniques to tackle that problem and that's kind of leads to why that's kind of leads to why um I believe um both the vector database um I believe um both the vector database and uh graph database are popular and and uh graph database are popular and continue will continue to be pro pro continue will continue to be pro pro Prosper yes you know it's interesting I Prosper yes you know it's interesting I when I basically started to follow the when I basically started to follow the commun events you were guys were one of commun events you were guys were one of the first who started popularizing the r the first who started popularizing the r right like I think one of the first right like I think one of the first events I've seen where your Mups and events I've seen where your Mups and what was super interesting to me what was super interesting to me majority of the people were not the majority of the people were not the people I've seen in developer commun people I've seen in developer commun before around developer m for 10 years before around developer m for 10 years and more right so I started the very and more right so I started the very first Spark M up with mat you know I run first Spark M up with mat you know I run the biggest scull M up we have the you the biggest scull M up we have the you know apik kovka like all these know apik kovka like all these distributed systems and like you kind of distributed systems and like you kind of know what traditional developers do and know what traditional developers do and now have this completely new now have this completely new generational developers some of them generational developers some of them most of them were not developers before most of them were not developers before right they plunge into this like AI right they plunge into this like AI Engineers so like I wonder how do you go Engineers so like I wonder how do you go about like teaching uh right as Le like about like teaching uh right as Le like this new generation of people coming in this new generation of people coming in right how do you kind of help them right how do you kind of help them become a Engineers yes with with with ra become a Engineers yes with with with ra you know talking about the community and you know talking about the community and um making friends with developers and um making friends with developers and creating value I think like empathy is creating value I think like empathy is the the first priority you need to know the the first priority you need to know like what they are thinking about what's like what they are thinking about what's their um you know um the the challenges their um you know um the the challenges that they are facing um so that despite that they are facing um so that despite that um most of of us uh came from the that um most of of us uh came from the database and infrastructure perspective database and infrastructure perspective we do know that you know as a fullstack we do know that you know as a fullstack mobile uh developer you probably don't mobile uh developer you probably don't know that much context in machine know that much context in machine learning and data instructors and learning and data instructors and however in order to build a really however in order to build a really awesome application you have to master awesome application you have to master that um so how how do you do that I that um so how how do you do that I think we are trying to provide two think we are trying to provide two values um in in terms of this aspect one values um in in terms of this aspect one is that we're um kind of articulating is that we're um kind of articulating the machine learning and Def NE Network the machine learning and Def NE Network Technologies from the perspective that Technologies from the perspective that uh like any like any U uh developer uh like any like any U uh developer without deep experience in marchine without deep experience in marchine learning can comprehend like you know learning can comprehend like you know some of the time you just need to tell a some of the time you just need to tell a story that really makes sense like from story that really makes sense like from their perspective like they are really their perspective like they are really familiar with say microservices right familiar with say microservices right and then we talk about you know the and then we talk about you know the machine learning stack not from the machine learning stack not from the models but from a microservice service models but from a microservice service aceration perspective and I think that's aceration perspective and I think that's also one of the reason why say longchain also one of the reason why say longchain and Lama index are so popular among the and Lama index are so popular among the community because they are really community because they are really abstracting away those integrities in abstracting away those integrities in machine learning models and data stack machine learning models and data stack they are really just um extracting the they are really just um extracting the important pieces which are say uh in important pieces which are say uh in long chain you just need to have a few long chain you just need to have a few components and then you um streamline components and then you um streamline them into a chain L index do you know them into a chain L index do you know you provide abstraction out of the um you provide abstraction out of the um the complex retrieval stack Maybe the complex retrieval stack Maybe it will um you know touch quite a few it will um you know touch quite a few pieces but with this simple and elegant pieces but with this simple and elegant abstraction you you know just abstract abstraction you you know just abstract away all of the complexities and that's away all of the complexities and that's the similar thing uh we are doing here the similar thing uh we are doing here like we try to you know we choose to um like we try to you know we choose to um partner with um all of the awesome R partner with um all of the awesome R acction Frameworks and evaluation acction Frameworks and evaluation Frameworks out in their in the market in Frameworks out in their in the market in the open source Community um by the open source Community um by integrating MERS and abstracting away um integrating MERS and abstracting away um you know like vector uh distance Matrix you know like vector uh distance Matrix and things like that uh extract away and things like that uh extract away those complexities and only leave the um those complexities and only leave the um most frequently used features in those most frequently used features in those um obstructive API those interface um obstructive API those interface however if you really have a complex um however if you really have a complex um problem to T tackle and you need to like problem to T tackle and you need to like find through or like um um you know find through or like um um you know customize those knobs we still provide a customize those knobs we still provide a um a way to do that like through a bench um a way to do that like through a bench of um complex knobs for power users yeah of um complex knobs for power users yeah for power user for the advanced use for power user for the advanced use cases so that's one thing the other one cases so that's one thing the other one is just like what we're doing today and is just like what we're doing today and also what have been doing a lot in the also what have been doing a lot in the GitHub awesome GitHub menu U we um you GitHub awesome GitHub menu U we um you know host the Meetup events we uh invite know host the Meetup events we uh invite the speakers to talk about the new the speakers to talk about the new trends in this domain so that we um trends in this domain so that we um provide you know useful information and provide you know useful information and like um best practices to the developers like um best practices to the developers so that they don't like 10 years of so that they don't like 10 years of experience in data pipelines M they can experience in data pipelines M they can still build a an awesome uh like still build a an awesome uh like production ready data pipeline by production ready data pipeline by leveraging The Experience from all of leveraging The Experience from all of the you know experts in this domain yes the you know experts in this domain yes you know I really love it that like you you know I really love it that like you really follow the spirit of Open Source really follow the spirit of Open Source right then you not only do your own right then you not only do your own right and then you invite others so I right and then you invite others so I started joing this he days and what I started joing this he days and what I see is amazing because multiple see is amazing because multiple companies in the space they kind of companies in the space they kind of bring each other and they together show bring each other and they together show the stack to developers right because the stack to developers right because Rising tide lifts all the boats if we Rising tide lifts all the boats if we help everybody do their piece in the help everybody do their piece in the stack better and we use open source you stack better and we use open source you know we do it better so I've started know we do it better so I've started this new commission called Dev real Dev this new commission called Dev real Dev real. it's basically Dev but keeping it real. it's basically Dev but keeping it real right and so so we kind of you know real right and so so we kind of you know want to invite kind of the best Deval want to invite kind of the best Deval advocates in in it and my question to advocates in in it and my question to you is kind of one of the leading the you is kind of one of the leading the real folks right doing this for a while real folks right doing this for a while how do you think we should kind of how do you think we should kind of maximize impact what what works best for maximize impact what what works best for developers because it's really hard to developers because it's really hard to like you said to find what should you do like you said to find what should you do like you can just be overwhelmed with like you can just be overwhelmed with all this new information right and like all this new information right and like there's so many possibilities you have there's so many possibilities you have five of these companies which should I five of these companies which should I pick how should I put them together like pick how should I put them together like how do you help developers to think how do you help developers to think about this how can they start and how do about this how can they start and how do we keep them happy by learning more and we keep them happy by learning more and more and become more comfortable with more and become more comfortable with this stuff yeah so um I think first of this stuff yeah so um I think first of all I I I wish that we can you know all I I I wish that we can you know collaborate even more so that we create collaborate even more so that we create those um integrated those well those um integrated those well Illustrated dios and best practices Illustrated dios and best practices through you know notebooks and and blogs through you know notebooks and and blogs and and even better video content so and and even better video content so that uh we show developers like how to that uh we show developers like how to use those Technologies in action um by use those Technologies in action um by you know combining a suite of you know combining a suite of Technologies like NE 4J and M you know Technologies like NE 4J and M you know dat all those great data stack and in dat all those great data stack and in addition um I think we also need to addition um I think we also need to build a lot of um uh uh we call it build a lot of um uh uh we call it seamless integration and I know the word seamless integration and I know the word seamless is kind of overused already but seamless is kind of overused already but really has to be because you know um really has to be because you know um when developers are using it you won't when developers are using it you won't think of it as you know product a versus think of it as you know product a versus product B we think of as a a stack as a product B we think of as a a stack as a you know as a um a solution so that by you know as a um a solution so that by you know uh doing Integrations between you know uh doing Integrations between the um adjacent stack like upstream and the um adjacent stack like upstream and downstream for example example um um downstream for example example um um embeding models and Vector database plus embeding models and Vector database plus large language model which is kind of large language model which is kind of the three important pillars in R um by the three important pillars in R um by doing this kind of Integrations we can doing this kind of Integrations we can provide more like um easier way for provide more like um easier way for developer to onboard to this new developer to onboard to this new technology and as well as you know kind technology and as well as you know kind of plot plot through all of the of plot plot through all of the challenges and you know obstacles that challenges and you know obstacles that developer May came across um may come developer May came across um may come across when they are doing this across when they are doing this integration and the last thing we want integration and the last thing we want them to do is to feel frustrated when them to do is to feel frustrated when they are combining technology a b and c they are combining technology a b and c right yeah um and also you know make right yeah um and also you know make friends and and um you know host the friends and and um you know host the community uh events so that we can talk community uh events so that we can talk we can communicate and collaborate we can communicate and collaborate fantastic this is what we're doing here fantastic this is what we're doing here and last question is you know maybe you and last question is you know maybe you can tell us something fun about yourself can tell us something fun about yourself a fun fact or what do you like to do for a fun fact or what do you like to do for fun okay um I guess yeah fun fact about fun okay um I guess yeah fun fact about uh my my role actually I I have never uh my my role actually I I have never than DAV before all right this is uh than DAV before all right this is uh this is probably probably my like third this is probably probably my like third fourth month doing DAV I I really came fourth month doing DAV I I really came from the engineering and product from the engineering and product background so um back in the days uh background so um back in the days uh well when I was at Google I was um you well when I was at Google I was um you know building short video search um by know building short video search um by you know doing semantic understanding of you know doing semantic understanding of the short videos out there like from Tik the short videos out there like from Tik Tok from YouTube shorts Instagram um so Tok from YouTube shorts Instagram um so like at that time we didn't really have like at that time we didn't really have the sense of D real the sense of D real because we only have C customers you because we only have C customers you know partner teams like in the large know partner teams like in the large organization so that you know it's organization so that you know it's really really different uh working in really really different uh working in this uh open source and um you know this this uh open source and um you know this very open Community where you have very open Community where you have unlimited amount of resources but at at unlimited amount of resources but at at the same time you also um you know con the same time you also um you know con constantly face the challenge of constantly face the challenge of connecting to to your users and connecting to to your users and developer friends so that yeah I I guess developer friends so that yeah I I guess back to the you know the the the central back to the you know the the the central topic of today is still like I think topic of today is still like I think it's never um you know we can't really it's never um you know we can't really emphasize the importance of community um emphasize the importance of community um um too much it's really really important um too much it's really really important to foster a community and Foster the um to foster a community and Foster the um the channel of communication and the the channel of communication and the free flow of information so that you free flow of information so that you know we can better build um Technologies know we can better build um Technologies but also products no I feel really happy but also products no I feel really happy that you know you said that because you that you know you said that because you know this is the first meet up in the 10 know this is the first meet up in the 10 years year span we run it which I run as years year span we run it which I run as AI committee architect which is in the AI committee architect which is in the org so I've been doing it for many years org so I've been doing it for many years but this is the third week you said a but this is the third week you said a few months this third week I do it few months this third week I do it officially in the de or and right and so officially in the de or and right and so I really want to learn from Dev like you I really want to learn from Dev like you and all of us to teach developers how to and all of us to teach developers how to tackle this a think so I think with tackle this a think so I think with folks like you and Roy and others like folks like you and Roy and others like we're going to do it I think we're going we're going to do it I think we're going to bring a eye to the people with open to bring a eye to the people with open source so thank you Chun and looking source so thank you Chun and looking forward to your talk thank you very much forward to your talk thank you very much thank you all right looking forward all