Inicia tu Agente IA con Qdrant: ¡IA con memoria ultra rápida! 🤖🧠 #LeiferMendez #BoltAgent #Qdrant #VectorDatabase #AI #Programacion #SoftwareArchitecture
0:40
Inicia tu Agente IA con Qdrant: ¡IA con memoria ultra rápida! 🤖🧠 #LeiferMendez #BoltAgent #Qdrant #VectorDatabase #AI #Programacion #SoftwareArchitecture
466 views2 weeks ago
TikTokleifermendez
Turn Claude Code into a “chat with your meeting notes” assistant: Obsidian Qdrant a tiny Python fetch step so the right context shows up instantly in your terminal #claudecode #obsidian #vectordatabase #aiautomation #aiproductivity
0:56
Turn Claude Code into a “chat with your meeting notes” assistant: Obsidian Qdrant a tiny Python fetch step so the right context shows up instantly in your terminal #claudecode #obsidian #vectordatabase #aiautomation #aiproductivity
14.6K views5 months ago
TikTokraleighawesome84
Nothing beats a clean startup log. 💻 The NeuralTrade infrastructure is breathing. 🧠 #QDrant #Prometheus #Docker #infrastructure #fintech
0:29
Nothing beats a clean startup log. 💻 The NeuralTrade infrastructure is breathing. 🧠 #QDrant #Prometheus #Docker #infrastructure #fintech
117 views5 months ago
TikTokerdincerdgn
Just had the first revenue come in for the Qdrant AGI house hackathon! First of many gongs! | Thierry Damiba
Just had the first revenue come in for the Qdrant AGI house hackathon! First of many gongs! | Thierry Damiba
2 views1 month ago
linkedin.com
LLM × 網路爬蟲終極實戰：n8n 串接資料爬取 × Qdrant × RAG 打造本機 AI Agent- TAAZE 讀冊生活
LLM × 網路爬蟲終極實戰：n8n 串接資料爬取 × Qdrant × RAG 打造本機 AI Agent- TAAZE 讀冊生活
6 months ago
taaze.tw
Packed house for Qdrant at DeepLearning.AI Dev Day! Got to meet Andrew Ng and some other cool people! Giving a talk tommorow at 1:45 on stage 2! | Thierry Damiba
Packed house for Qdrant at DeepLearning.AI Dev Day! Got to meet Andrew Ng and some other cool people! Giving a talk tommorow at 1:45 on stage 2! | Thierry Damiba
2 views1 month ago
linkedin.com
Join the VECTORS IN ORBIT AI Hackathon!
1:18
Join the VECTORS IN ORBIT AI Hackathon!
12.7K views5 months ago
TikTokzulfacode
IQ200YukaF - Twitch
Dec 27, 2020
TwitchIQ200YukaF
2:05
every claude code session you close is a memory thrown away. i fixed that with a thing i call the brain. the brain is a giant semantic database of every coding session, every email, every voice note, and every git commit i've ever made. all in the same vector space so my agents can look up anything by meaning. gemini multimodal embeddings, qdrant vector store, rtx 3090 on my agent box. Q: what gets ingested? A: claude code jsonl transcripts, codex and gemini cli sessions, every git commit across
132 views1 month ago
TikTokconnorgallic
FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research | Companion Proceedings of the ACM on Web Conference 2025
May 23, 2025
acm.org
0:03
Here are the 3 Core Pillars of Every AI Agent's ContextHere's why MCP, RAG and Skills are now unavoidable...Before we dive in, here's why all 3 exist in the first place:Every AI Agent struggles with 3 core problems:- Connecting to external tools requires writing custom API code every time- Answering accurately from knowledge it was never trained on- Repeating the same instructions in prompts; wasting tokens on every single callMCP, RAG, and Skills were each built to solve exactly one of these pr
30.9K views1 month ago
x.comVaidehi
6:16
Python Introduction - GeeksforGeeks
Aug 30, 2020
geeksforgeeks.org
0:03
Every AI system must have these 5 layers.I've explained each layer with examples.1. 𝗗𝗮𝘁𝗮This layer manages how data is stored, processed, and retrieved for AI systems.• Vector databases → Store embeddings for search• Embedding models → Convert text into vectors• Document processing → Parse and structure documents• Knowledge graphs → Connect entities and relationships• RAG systems → Retrieve external context for LLM• Semantic caching → Cache responses for faster reuse𝗘𝘅𝗮𝗺𝗽𝗹𝗲𝘀: Pinecon
5.9K views1 month ago
x.comVaidehi
0:35
Md Imran | AI/ML | Tech | Coding | Hackathon | Teacher on Instagram: "🔥 AI ka future yaha hai — Top 50+ LLM Tools & Frameworks! AI ecosystem roz evolve ho raha hai — naye tools aur frameworks launch ho rahe hain. Sirf LLMs nahi, ab agent orchestration, fine-tuning, vector DBs, production tools aur observability frameworks sab market me boom kar rahe hain. Is reel me maine ek exclusive repo share ki hai jo aapko future-ready banayegi! 🚀 AI tools, LLM frameworks, agent orchestration, production
60.3K views8 months ago
Instagrammdimran.py
0:06
Ganesh Jha on Instagram: "Real RAG systems are way more than what people build as demo. They can fail in the boring parts—ingestion, drift, prompts, and lead to 3 a.m. outages. Enterprise RAG isn’t a pipeline. It’s an ecosystem. Here’s the stack that one can actually refer to build production rag apps: 1. The obvious ones - Code assistance where engineers really work Terminal-native tools like ForgeCode, Claude Code CLI, Gemini CLI keep mental flow intact while refactoring retrievers, chunking,
12K views5 months ago
Instagramjganesh.ai
0:04
Priyal | DS & ML on Instagram: "1) FAISS – Fast similarity search for large-scale embeddings, great for research & local prototypes. 2) Pinecone – Fully managed vector DB for production grade semantic search & RAG apps. 3) ChromaDB – Lightweight, developer-friendly vector DB for LLM apps and rapid experimentation. 4) Weaviate – Vector DB with built-in ML + GraphQL for semantic search & recommendation systems. 5) Milvus – High-performance, distributed vector DB for billion-scale AI applications.
16.3K views5 months ago
Instagrampriyal.py
0:05
Ganesh | AI Engineer on Instagram: "So how should one decide which one to pick. There’s no “best” vector database. There’s only what fits your stage and the cost factor.. If you’re prototyping or building a POC then use Chroma or pgvector ● Run locally ● Almost zero cost ● Latency is fine for demos 💰 Cost intuition: basically free 👉 Goal: validate the idea, not optimize infra If you’re in early production then use Qdrant or Pinecone ● Fast and reliable ● Handles filters well (important for RAG
7.5K views5 months ago
Instagramjganesh.ai
0:58
David McWilliams | Stop paying $1000+ monthly for AI APIs! 🤯 I run Whisper, Kokoro TTS, Qdrant, and Ollama on one GPU box locally for $31/month — OpenClaw... | Instagram
4.2K views4 months ago
Instagramdavidmcwilliams
Simone Rizzo AI on Instagram: "Sistema RAG in locale sui PDF senza GPU usando modelli di piccola taglia super leggeri. Garntendo privacy ed essendo super accessibile! Ho usato: Ollama + N8N + Qdrant. #intelligenzaartificiale #llm #n8n"
31.6K views9 months ago
Instagramsimorizzo_ai
0:44
Scale Your SaaS with an AI Assistant
4.9K viewsApr 3, 2025
TikTokoumnyaknowstech
See more
Static thumbnail place holder