Vector Database
topic on 6 shows · 26 statements across 19 episodes
Latent Space 
No Priors 
the Startup Ideas Podcast 
A Product Market Fit Show 
the MAD Podcast 
Big Technology
26 statements about Vector Database, every show
Greg Isenberg: Dumping Unstructured Content Into Vector Databases Produces Flawed AI Products
“A lot of people get lazy at this part. They throw everything into a vector database, and then they just call it a day. That usually gives you a search box with confidence. But a real product needs structure.”
Xin: Vector databases should never have been a separate category
“Vector database should have never been a separate category.”
Ghai: Brute-force vectorizing of unstructured enterprise data causes AI hallucinations
“Let's vectorize petabytes of data and hope we can figure it out. That's when hallucinations happen. That's when other issues happen. So there needs to be some structure around it.”
Swix: Standalone Vector Databases Are Over as a Category
“Everyone has vector indexes now, but like, I think it's fair to say vector databases as a standalone category are over.”
Eifrem: Good Enough Vector Features in Existing Databases Suffice
“Between everyone else adding it as a feature there, like the good enough ends up being good enough for most situations.”
Singleton: Dreamer replaced Vector DB RAG for agent memory due to complexity
“Very early on, we were putting lots of facts into a vector database and doing embeddings and pulling them back out using, you know, reverse look of embeddings. Rag that actually worked, but turned out to be much more complexity than was actually required. So, …”
Jiang: Peek uses a vector database to store thousands of user signals
“We have a vector database that actually stores memory from the user. So we have like actually thousands of signals that we save down, right?”
Alberti: Cognition built its own in-house vector database
“This culture of like building everything in-house. It's also kind of funny, like we, there's like a rack component to this. And I've been actually, I personally advocate, I can just like use a vector database and make life easy. But then there's a really stron…”
Bergum: The standalone vector database infrastructure category is dying
“I'm not saying that the companies are dying, right? I'm just saying that the separate infrastructure category is dying, right? Because you have vector search capabilities in almost any DB technology nowadays, right?”
Liberty: The term 'vector database' did not exist when Pinecone started
“The term vector database didn't exist. It just didn't exist. We'd, nobody talked about it this way.”
Liberty: 70% of Early Users Already Called Pinecone a Vector Database
“We literally asked them like, Hey, you internally in your team, you talk about using this pine cone thing. What do you think it is? What do you call this internally? Seven out of 10 would say, we just call it a vector database. It's like, that's where it's, we…”
Kiela: FAISS was the first vector database
“In the initial paper, we used a vector database or a face. So the words vector database didn't exist at the time. But so face was the first vector database.”
Bernhardsson: AI-native data storage will take 5–10 years to mature
“The more native, like AI native storage solution would be, you put text in, you put, you know, video in, you put image in, and then you can search by that. Like to me, that would be like a more sort of native, AI native sort of storage solution. So that's like…”
Companies will need custom formulas combining qualitative and quantitative vector data
“Each company will need to embed a different formula for defining vectors, For the content or the recommendations that you need to make that will have many different components that will be both qualitative and quantitative.”
Liu: Rank and retrieve tool definitions instead of passing dozens to LLMs
“If you're running into issues where you have, like, 20 or 50 or 60 function calls, I think you're much better having those specifications saved in a vector database, and then have them be retrieved. So if there are 30 tools, like, you should basically be, like…”
Liberty: RAG Architectures Pair Small Models With Trillion-Parameter Vector Databases
“Already today, we have users who use not even very large models, you know, maybe a few billion parameters, and the vector database next to the model contains trillions of parameters. And they get, you know, much better performance that way.”
Liberty: Vector databases enable GDPR compliance without complex model unlearning
“And the added benefit to that is, by the way, that you can be GDPR compliant. You can actually delete data. So if, you know, so, you know, if you're a company like a legal company and somebody deletes a document, you can just delete it from the vector database…”
Van Luijt: RAG was the first unique vector database use case
“And reg was the first unique use case, if you will, that emerged around the ecosystem of vector databases.”
Van Luijt: Vector database value comes from indexing, not basic storage
“The vector embedding is just a data type. So it's just an array of floating point numbers. I mean, you can store that in an old Oracle database, right? So, but the thing where it becomes interesting is the index.”
Maturing database products differentiate, making integrations harder to maintain
“All these products are maturing and also differentiating, right? So it is becoming more and more of an effort, to be honest, to really manage this.”
LlamaIndex is not building a vector database, integrates with 12-20 existing ones
“We're not building our own vector database, but we have a rich set of integrations with, you know like 12 to like 20 different vector databases out there these days.”
Huber: Vector databases must support both transactional and analytical workloads
“And we think that both certainly transactional has to be the case because it is a online database. It's gonna sit in the loop of applications. Again, you've already seen demos of this happening tonight. But also to make this technology useful for developers, y…”
Huber: 'Vector database' is too narrow a term for information retrieval
“I don't actually like the term vector database that much. I think it's sort of narrow. I think the job to be done is information retrieval more broadly, and vector search happens to be a useful tool in our toolbox to doing information retrieval.”
Huber: Asking whether vector databases replace classic databases is dumb
“People, there's this, like, you know, big question about, oh, are vector databases gonna replace classic databases? Are these competitive in some way? And I think it's just kind of a dumb question.”
Huber: Vector databases primarily handle un-databased unstructured data
“Vector databases are primarily about unstructured data. It's actually taking data that had no database that knew about it and loading it in for the very first time. Most applications of this stuff is not about taking data that's already in your relational data…”