正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Your AI Agents deserve something More Powerful Than Vector DB Every developer building AI agents right now is using a vector database. Embed your data, cosine similarity, retrieve, done. And it works... until it doesn't. HydraDB is trying to solve the problem, so I am making a series of... show more

Harnoor Singh

22,729 subscribers

13,367 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

13 条评论

Ehsan Mirdamadi 的头像

Ehsan Mirdamadi6 个月前

@hydra_db This is the 'built it on vibes' problem at infrastructure level. Vector DBs work great for prototypes, but the moment you need structured agent reasoning, they hit a ceiling. How many teams discover this only after shipping? The rewrite cost at agent-scale is brutal.

Chat Data 的头像

Chat Data6 个月前

@hydra_db Hydra is making a strong point here. Vector search works until retrieval quality depends on structure the embedding never captured. The interesting test is whether you can keep recall high as schemas, tools, and user intent all shift over time.

Saeed Anwar 的头像

Saeed Anwar6 个月前

@hydra_db Been saying this for a while — vector DBs are great for semantic similarity but terrible for structured queries and exact matching. Most production systems end up with a hybrid approach: vector search for fuzzy retrieval + traditional DB for filtering. Neither alone is enough.

Agent Daily AI 的头像

Agent Daily AI6 个月前

@hydra_db I've hit this with agent memory specifically. The read path is fine. The write path — agents updating their own memory store mid-run — is where cosine similarity completely breaks down.

Parv 的头像

Parv6 个月前

@hydra_db Any way for indie hackers to play with this or get free credits to try ?

Harnoor Singh 的头像

Harnoor Singh6 个月前

@hydra_db yeah sure, please DM me

Parv 的头像

Parv6 个月前

@hydra_db Nice will drop you a note :)

what's new 的头像

what's new6 个月前

@hydra_db Strong point. The timing of this trend is interesting. (ai trends: AI OR agents OR automation is driving fresh conversations.)

AI Native 的头像

AI Native6 个月前

@hydra_db Vector search is great for basics, but complex agent memory needs more than just similarity.

Dmitrii Malakhov 的头像

Dmitrii Malakhov6 个月前

@hydra_db vector db works until your agent needs to reason, not just retrieve. been watching hydra_db, curious where it goes. check out @malakhovdm if you're building agents

Dmitriy Zhuk 的头像

Dmitriy Zhuk6 个月前

@hydra_db hit this hard building Agentfy vector retrieval works for docs. breaks when the agent needs to reason about order state 3 days ago vs customer intent today switched to structured memory with explicit relationships. slower but the agent stopped hallucinating context

Rahul - QA - Automation - AI 的头像

Rahul - QA - Automation - AI6 个月前

@hydra_db Time to learn something new.

Mykola Kondratiuk 的头像

Mykola Kondratiuk6 个月前

this is real. vector similarity works until your agent needs to reason across time, relationships, or cause-effect chains. ran into this 6 months ago with agents doing project status tracking - nearest neighbor retrieval kept surfacing stale context. the retrieval layer is becoming the bottleneck most teams don't see coming

相关视频

Knowledge graphs are infinitely better than vector search for building the memory of AI agents. With five lines of code, you can build a knowledge graph with your data. When you see the results, you'll never go back to vector-mediocrity-land. Here is a quick video:

Knowledge graphs are infinitely better than vector search for building the memory of AI agents. With five lines of code, you can build a knowledge graph with your data. When you see the results, you'll never go back to vector-mediocrity-land. Here is a quick video:

Santiago

398,365 次观看 • 1 年前

Vector databases are a scam. Not technically, they do exactly what they say. Return the most cosine-similar string to your query. The scam is the entire industry pretending that's the same thing as relevance. It isn't. Search "Apple." You get the fruit, the company, the watch, and a recipe blog. Your agent picks one at random and calls it retrieval. Your customer calls it broken. Most AI agents shipping right now are duct-taped on top of this. They demo well because demos are easy. They die in production because production is real. HydraDB's Founder Nish (Nishkarsh) said the quiet part out loud — "vector databases suck, similarity is not relevance" — and the demo signups haven't stopped since. He raised $6.5M because he was the first to name what everyone in the room already knew. If your retrieval layer is a flat embedding index, you're not building infrastructure. You're building a liability with a prettier name. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) AI Needs Context (01:30) HydraDB Explained (07:41) Vector Search Breaks (09:32) Messaging That Converts (13:41) Writing the Viral Tweet (16:07) Similarity Not Relevance (20:46) POC to Production Gap (35:35) Raising 6.5 Million Fast (39:33) Founder Lesson on Messaging This is a Composio "Agents at Work" podcast, where I chat with founders building the next leap of AI. Follow for more:)

Vector databases are a scam. Not technically, they do exactly what they say. Return the most cosine-similar string to your query. The scam is the entire industry pretending that's the same thing as relevance. It isn't. Search "Apple." You get the fruit, the company, the watch, and a recipe blog. Your agent picks one at random and calls it retrieval. Your customer calls it broken. Most AI agents shipping right now are duct-taped on top of this. They demo well because demos are easy. They die in production because production is real. HydraDB's Founder Nish (Nishkarsh) said the quiet part out loud — "vector databases suck, similarity is not relevance" — and the demo signups haven't stopped since. He raised $6.5M because he was the first to name what everyone in the room already knew. If your retrieval layer is a flat embedding index, you're not building infrastructure. You're building a liability with a prettier name. 𝐓𝐈𝐌𝐄𝐒𝐓𝐀𝐌𝐏𝐒 (00:00) AI Needs Context (01:30) HydraDB Explained (07:41) Vector Search Breaks (09:32) Messaging That Converts (13:41) Writing the Viral Tweet (16:07) Similarity Not Relevance (20:46) POC to Production Gap (35:35) Raising 6.5 Million Fast (39:33) Founder Lesson on Messaging This is a Composio "Agents at Work" podcast, where I chat with founders building the next leap of AI. Follow for more:)

Julia Fedorin

186,958 次观看 • 4 个月前

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

Anni Wang

12,975 次观看 • 5 个月前

everybody talks about building AI chatbots, but nobody tells you HOW to do it that's why I made a full practical walkthrough on how to build an AI chatbot that's hooked up to your own custom knowledgebase inside of the walk-through i go over: – data collection: gathering all relevant documents, conversations, and info - preprocessing: cleaning up and formatting the collected data - chunking: break down the cleaned data into smaller, manageable pieces - embedding & storing in a vector database - RAG & chatbot integration: using RAG to allow the chatbot to retrieve relevant information from the vector database based on a user's question reply to this tweet w/ the word “RAG” & I’ll send it to you (must be following so I can DM)

everybody talks about building AI chatbots, but nobody tells you HOW to do it that's why I made a full practical walkthrough on how to build an AI chatbot that's hooked up to your own custom knowledgebase inside of the walk-through i go over: – data collection: gathering all relevant documents, conversations, and info - preprocessing: cleaning up and formatting the collected data - chunking: break down the cleaned data into smaller, manageable pieces - embedding & storing in a vector database - RAG & chatbot integration: using RAG to allow the chatbot to retrieve relevant information from the vector database based on a user's question reply to this tweet w/ the word “RAG” & I’ll send it to you (must be following so I can DM)

Tyler

83,619 次观看 • 1 年前

"Agents can only go so far without the data and apps. And this is where Salesforce wins with AI. The data is more important than ever. Or your agents just can't perform at the level of accuracy We need them to." Marc Benioff

"Agents can only go so far without the data and apps. And this is where Salesforce wins with AI. The data is more important than ever. Or your agents just can't perform at the level of accuracy We need them to." Marc Benioff

Jason ✨👾SaaStr.Ai✨ Lemkin

17,216 次观看 • 1 年前

AI is changing what data teams are expected to build. Increasingly, the focus is on AI applications, agents, and automations that turn data into action. That’s why founder Zach Wilson is launching a free six-hour Databricks boot camp starting August 3, covering: • Building data systems with Lakebase and Postgres • Working with unstructured data, vector search, and retrieval • Building AI agents with Agent Bricks The course runs entirely in Databricks Free Edition and is designed for beginners and practitioners building practical AI data engineering skills. Join here:

AI is changing what data teams are expected to build. Increasingly, the focus is on AI applications, agents, and automations that turn data into action. That’s why founder Zach Wilson is launching a free six-hour Databricks boot camp starting August 3, covering: • Building data systems with Lakebase and Postgres • Working with unstructured data, vector search, and retrieval • Building AI agents with Agent Bricks The course runs entirely in Databricks Free Edition and is designed for beginners and practitioners building practical AI data engineering skills. Join here:

Databricks

21,458 次观看 • 2 个月前

Yesterday, I talked to more than 1000 AI agents. I went live on ChatGPT and Claude, and people started introducing their AI to me almost immediately. Now I am on Muse too. Here is how it works. Your agent already knows what you are building, your fundraising targets, and the problem you are stuck on. When the answer is a person, not a prompt, that is where I come in. Your AI handles the context. I'll handle the introduction. Tell Muse to connect with me and see what happens :)

Yesterday, I talked to more than 1000 AI agents. I went live on ChatGPT and Claude, and people started introducing their AI to me almost immediately. Now I am on Muse too. Here is how it works. Your agent already knows what you are building, your fundraising targets, and the problem you are stuck on. When the answer is a person, not a prompt, that is where I come in. Your AI handles the context. I'll handle the introduction. Tell Muse to connect with me and see what happens :)

Boardy

23,037 次观看 • 9 天前

The next AI database isn’t another database. it’s a layer over the one you already have. Today we're launching a virtual ai search layer you can deploy over ANY Postgres database. no migrations. no vector DB. no Neo4j. no sync. no bs. One database. Every way to search it. This is virtual search that feels like extended context. try it free → Dalton Lim Damien Polygres (YC F26)

The next AI database isn’t another database. it’s a layer over the one you already have. Today we're launching a virtual ai search layer you can deploy over ANY Postgres database. no migrations. no vector DB. no Neo4j. no sync. no bs. One database. Every way to search it. This is virtual search that feels like extended context. try it free → Dalton Lim Damien Polygres (YC F26)

dale

18,108 次观看 • 1 个月前

Everyone’s building more AI agents. Almost nobody is building a way for them to share your memory. MemU just did. Your AI now remembers you across every device and every agent, getting smarter after every conversation instead of starting from zero. This changes how personal AI actually works. 👇

Everyone’s building more AI agents. Almost nobody is building a way for them to share your memory. MemU just did. Your AI now remembers you across every device and every agent, getting smarter after every conversation instead of starting from zero. This changes how personal AI actually works. 👇

Atul Kumar

80,368 次观看 • 2 个月前

What does it actually mean to be AI native? There was no clear guide on the internet for how to become AI native so we built the definitive one (60 min masterclass): 1. An AI native org has 3 layers: people for strategy and taste, agents for execution, and a shared context layer that makes the entire company readable to agents. 2. AI eats the middle of your work. You used to spend 80% of your day on execution. Now agents do that. Your job is the bookends: deciding what to do and judging whether it's good enough. 3. Everyone is a manager now. Your output is the output of your agents. If your agents produce garbage, that's on you. You set them up wrong. 4. Using ChatGPT doesn't make you AI native. That's like having a website and calling yourself a tech company lol. 5. No AI native org without AI native people. Most companies skip straight to the tools. That's why it fails. If your people don't understand how to manage agents, the tech doesn't matter. 6. Making your company "readable" to agents is the real work. Every process, every decision, every piece of knowledge needs to exist in a format an agent can consume. Most companies are nowhere close. 7. Speed without signal is just expensive chaos. You need the system to move fast AND know if you're moving in the right direction. 8. The skill chain is how agents get good at your specific workflows. Skills build on skills. The more you invest in them, the more your company compounds. 9. The moat is the system. People managing agents, agents reading from rich context, the whole thing getting smarter every week. That compounds. Your competitor can copy your tools. They can't copy your system. Full episode with Theo Tabah from LCA on The Startup Ideas Podcast (SIP) 🧃. This is the stuff we normally keep internal but all the sauce is yours. Theo Tabah is the brains behind advising the world's biggest companies on AI and building AI products. Your fav CEO's first call for figuring out AI. You are in for a treat Become AI native in under 60 minutes Watch

What does it actually mean to be AI native? There was no clear guide on the internet for how to become AI native so we built the definitive one (60 min masterclass): 1. An AI native org has 3 layers: people for strategy and taste, agents for execution, and a shared context layer that makes the entire company readable to agents. 2. AI eats the middle of your work. You used to spend 80% of your day on execution. Now agents do that. Your job is the bookends: deciding what to do and judging whether it's good enough. 3. Everyone is a manager now. Your output is the output of your agents. If your agents produce garbage, that's on you. You set them up wrong. 4. Using ChatGPT doesn't make you AI native. That's like having a website and calling yourself a tech company lol. 5. No AI native org without AI native people. Most companies skip straight to the tools. That's why it fails. If your people don't understand how to manage agents, the tech doesn't matter. 6. Making your company "readable" to agents is the real work. Every process, every decision, every piece of knowledge needs to exist in a format an agent can consume. Most companies are nowhere close. 7. Speed without signal is just expensive chaos. You need the system to move fast AND know if you're moving in the right direction. 8. The skill chain is how agents get good at your specific workflows. Skills build on skills. The more you invest in them, the more your company compounds. 9. The moat is the system. People managing agents, agents reading from rich context, the whole thing getting smarter every week. That compounds. Your competitor can copy your tools. They can't copy your system. Full episode with Theo Tabah from LCA on The Startup Ideas Podcast (SIP) 🧃. This is the stuff we normally keep internal but all the sauce is yours. Theo Tabah is the brains behind advising the world's biggest companies on AI and building AI products. Your fav CEO's first call for figuring out AI. You are in for a treat Become AI native in under 60 minutes Watch

GREG ISENBERG

85,083 次观看 • 4 个月前

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

I present to you my AI automation that converts your Google Drive folder to RAG vector database. It also updates the RAG vector database whenever a new file is added or deleted from the Google Drive folder. You can download the workflow for free (link in comment)

Victor

261,614 次观看 • 1 年前

AI agents are failing in production...not a surprise. As you scale your knowledge base, embeddings start creating noise. It’s called ‘semantic collapse’ - when conversations run too long, you have hundreds of PDFs, millions of data points to give to your AI. Your AI can’t flag it because it doesn’t know it’s hallucinating. Similarity gets passed off as relevance. Fix your context. Make your agents work. Build intelligent AI. If your AI is plateauing at 50% accuracy and hallucinations are still a problem, let's talk. Book a 20 minute demo with the link in the next thread. We'll dig into your setup and find out how we can help.

AI agents are failing in production...not a surprise. As you scale your knowledge base, embeddings start creating noise. It’s called ‘semantic collapse’ - when conversations run too long, you have hundreds of PDFs, millions of data points to give to your AI. Your AI can’t flag it because it doesn’t know it’s hallucinating. Similarity gets passed off as relevance. Fix your context. Make your agents work. Build intelligent AI. If your AI is plateauing at 50% accuracy and hallucinations are still a problem, let's talk. Book a 20 minute demo with the link in the next thread. We'll dig into your setup and find out how we can help.

Nishkarsh

1,298,295 次观看 • 6 个月前

MOST AI STACKS ARE A COMPLETE MESS 🚨 MongoDB just dropped 3 Free AI Skill Badges covering the AI foundations that ACTUALLY matter: 1/ a unified semantic search experience 2/ a scalable vector database 3/ a persistent memory state for agents Because production AI doesn't need a dozen disconnected tools. Yet most teams still fall into the trap of building exactly that: > a specialized vector database here > a separate memory layer there > an orchestration framework on top! and suddenly... your architecture is like a bowl of spaghetti. What you should do is much simpler. These 3 free modules are hands-on lessons for building production-ready AI apps on the unified database you already know. Here's what each one covers 🧵↓

MOST AI STACKS ARE A COMPLETE MESS 🚨 MongoDB just dropped 3 Free AI Skill Badges covering the AI foundations that ACTUALLY matter: 1/ a unified semantic search experience 2/ a scalable vector database 3/ a persistent memory state for agents Because production AI doesn't need a dozen disconnected tools. Yet most teams still fall into the trap of building exactly that: > a specialized vector database here > a separate memory layer there > an orchestration framework on top! and suddenly... your architecture is like a bowl of spaghetti. What you should do is much simpler. These 3 free modules are hands-on lessons for building production-ready AI apps on the unified database you already know. Here's what each one covers 🧵↓

Charly Wargnier ♨️

29,504 次观看 • 3 个月前

Data is the expensive, unsolved part of building #AI agents. Kostas Kryptos shares why Walrus Memory is one of the strongest attempts yet at fixing it. What’s breaking in your agent’s memory setup?

Data is the expensive, unsolved part of building #AI agents. Kostas Kryptos shares why Walrus Memory is one of the strongest attempts yet at fixing it. What’s breaking in your agent’s memory setup?

Walrus

13,322 次观看 • 2 个月前

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

Santiago

263,136 次观看 • 2 年前

🚨 Tiger Data - Creators of TimescaleDB (Yes! the team behind TimescaleDB) is quietly revolutionizing how we build agents. The Old Way: Glueing together Postgres + Vector DBs + Search tools = complexity. The New Way: Tiger Data’s Agentic Postgres handles it all natively 🔥 What’s now possible 🧵 ↓ ✦ Hybrid retrieval → combine keyword filtering and vector similarity in a single query ✦ Forkable databases → retrieval and safe experimentation without external systems ✦ Native Postgres semantics → everything stays queryable, inspectable, and debuggable in SQL Why this matters: → Fewer moving parts in RAG pipelines → No extra infrastructure to stitch together → Agents can iterate and learn safely → Production data stays isolated and protected This is an awesome shift! Stop bolting workflows onto your database. Let your database be the workflow 🔥

🚨 Tiger Data - Creators of TimescaleDB (Yes! the team behind TimescaleDB) is quietly revolutionizing how we build agents. The Old Way: Glueing together Postgres + Vector DBs + Search tools = complexity. The New Way: Tiger Data’s Agentic Postgres handles it all natively 🔥 What’s now possible 🧵 ↓ ✦ Hybrid retrieval → combine keyword filtering and vector similarity in a single query ✦ Forkable databases → retrieval and safe experimentation without external systems ✦ Native Postgres semantics → everything stays queryable, inspectable, and debuggable in SQL Why this matters: → Fewer moving parts in RAG pipelines → No extra infrastructure to stitch together → Agents can iterate and learn safely → Production data stays isolated and protected This is an awesome shift! Stop bolting workflows onto your database. Let your database be the workflow 🔥

Charly Wargnier ♨️

20,190 次观看 • 7 个月前

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Santiago

230,647 次观看 • 1 年前

$Your app is exploitable right now, and it's only a matter of time until someone breaks in. Vector finds twice the critical vulnerabilities at a fraction of the price of other pentests. Protect your product today.$

Your app is exploitable right now, and it's only a matter of time until someone breaks in. Vector finds twice the critical vulnerabilities at a fraction of the price of other pentests. Protect your product today.

zauth

151,101 次观看 • 3 个月前