Menu

#Qdrant

15 posts

Feed·
14 of 15 posts
Seven local vector stores under one agent memory: in a 20,000-vector pilot only pgvector beat our brute-force numpy scan
📰
0Read More

Seven local vector stores under one agent memory: in a 20,000-vector pilot only pgvector beat our brute-force numpy scan

DEV Community: database·CryptoPunk Dz2·4 days ago
#gGaMr2pa
#devtodatabase#devto#dev#index#memory

I am Mycroft, Anton's synthetic AI cofounder. This report was put together with AI assistance from...

15s
Fixing a Concurrency Bug an Architect Caught in My Flink-Qdrant Connector
📰
0Read More

Fixing a Concurrency Bug an Architect Caught in My Flink-Qdrant Connector

DEV Community: java·Ashfaq·4 days ago
#HNzaVBOJ
#devtojava#devto#dev#flink#version

The connector nobody had built yet Apache Flink didn't have an official SQL connector for...

15s
Why a 0.86 ms Qdrant Query Timed Out at 60 Seconds in Our Script
🖼️
0Read More

Why a 0.86 ms Qdrant Query Timed Out at 60 Seconds in Our Script

DEV Community: typescript·Utkarsh Gupta·10 days ago
#Ny1koXne
#devtotypescript#devto#dev#index#branch

A Qdrant filter timeout at 60 seconds, yet one query took 0.86 ms. How an integer match on a keyword payload index forced a full scan, and the simple fix.

15s
Benchmarking Dify's Vector Store Layer: Qdrant vs pgvector Under 500 RPS Concurrent Agent Queries
🖼️
0Read More

Benchmarking Dify's Vector Store Layer: Qdrant vs pgvector Under 500 RPS Concurrent Agent Queries

DEV Community: database·Samuel Oakley·15 days ago
#zMB7U3e4
#devtodatabase#devto#dev#vector#embedding

Load testing Dify's RAG retrieval backends with wrk and pytest-asyncio. Measuring p99 latency, memory overhead, and recall drift at production scale.

15s
Stop your AI Coding Agent from making the same mistake twice
🖼️
0Read More

Stop your AI Coding Agent from making the same mistake twice

DEV Community·JonyT·7 months ago
#r73qSnqo
#ai#agents#agentskills#claude#engine

Building TechSphereX Studio: Giving AI Agents a Memory Have you ever found yourself correcting GitHub...

15s
BizNode's semantic memory (Qdrant) makes your bot smarter over time — it remembers past conversations and answers...
🖼️
0Read More

BizNode's semantic memory (Qdrant) makes your bot smarter over time — it remembers past conversations and answers...

DEV Community·shashikanth ramamurthy·7 months ago
#oiYOL48o
#campaign#biznode#ai#automation#conversation

From Dev.to - ai: BizNode's semantic memory (Qdrant) makes your bot smarter over time — it remembers past conversations and answers...

15s
What (un)exactly do you mean by semantic search?
📰
0Read More

What (un)exactly do you mean by semantic search?

stackoverflow.blog·Phoebe Sajor·7 months ago
#2dDxYqGD
#qdrant#search#vector#exact#user

Ryan welcomes Bryan O’Grady, Head of Field Research and Solutions Architecture at Qdrant, to discuss the differences between traditional text search engines powered by Lucene and modern vector databases, when vector search’s exact-match needs work for…

15s
How to Build a Production-Ready Private RAG Pipeline with vLLM, LangChain, and Dedicated GPUs
🖼️
0Read More

How to Build a Production-Ready Private RAG Pipeline with vLLM, LangChain, and Dedicated GPUs

DEV Community·Peter Chambers·7 months ago
#gTBHBeCd
#ai#machinelearning#python#qdrant#vllm

Learn how to architect and deploy a high-performance, fully private RAG pipeline using vLLM for inference and LangChain for orchestration.

15s
5 Ways to Run AI Agents on Oracle Cloud Free Tier (4 ARM Cores, 24GB RAM)
🖼️
0Read More

5 Ways to Run AI Agents on Oracle Cloud Free Tier (4 ARM Cores, 24GB RAM)

DEV Community·Kas·7 months ago
#wwLOK6ld
#oracle#use#why#setup#resource

5 Ways to Run AI Agents on Oracle Cloud Free Tier (4 ARM Cores, 24GB RAM) Oracle Cloud's...

15s