Qdrant offers 14 official skills for Claude Code.
They guide sizing and debugging, but they don't build search for you.
The test ran on local mode only, with no real Qdrant server.
aiparabellum.com/qdrant-skill...
They guide sizing and debugging, but they don't build search for you.
The test ran on local mode only, with no real Qdrant server.
aiparabellum.com/qdrant-skill...
November 11, 2026 at 1:30 AM
Qdrant offers 14 official skills for Claude Code.
They guide sizing and debugging, but they don't build search for you.
The test ran on local mode only, with no real Qdrant server.
aiparabellum.com/qdrant-skill...
They guide sizing and debugging, but they don't build search for you.
The test ran on local mode only, with no real Qdrant server.
aiparabellum.com/qdrant-skill...
I use Smart Connections inside Obsidian. That plugin acts as a lightweight, embedded vector store and semantic search engine. But it is not a traditional dedicated vector database like Chroma, Pinecone, Qdrant, or Milvus.
November 7, 2026 at 11:35 PM
I use Smart Connections inside Obsidian. That plugin acts as a lightweight, embedded vector store and semantic search engine. But it is not a traditional dedicated vector database like Chroma, Pinecone, Qdrant, or Milvus.
Good call, thank you. It's now pinned at the top of the changelog: if you're on 3.8.1 or earlier, upgrade, and re-ingest any documents with access restrictions stored in Qdrant, Pinecone, Weaviate or pgvector.
November 10, 2026 at 6:23 AM
Good call, thank you. It's now pinned at the top of the changelog: if you're on 3.8.1 or earlier, upgrade, and re-ingest any documents with access restrictions stored in Qdrant, Pinecone, Weaviate or pgvector.
Watch the full Private AI Box tutorial here: www.youtube.com/watch?v=_6Qo...
Build a private AI box, step by step: Ollama + Qdrant on AWS
YouTube video by Conn3x
www.youtube.com
November 7, 2026 at 5:40 PM
Watch the full Private AI Box tutorial here: www.youtube.com/watch?v=_6Qo...
Nice setup. A small script that re-indexes the notes folder on a schedule keeps Qdrant in sync without thinking about it.
November 3, 2026 at 8:17 PM
Nice setup. A small script that re-indexes the notes folder on a schedule keeps Qdrant in sync without thinking about it.
Vector search misses exact terms; scanned pages need OCR.
Qdrant 1.20 adds BM25 over text payloads without embeddings. An Elasticsearch demo used OCR and hybrid retrieval to make a 56-page scan searchable with page-marked citations in under five minutes.
Read more on Kimbodo:
Qdrant 1.20 adds BM25 over text payloads without embeddings. An Elasticsearch demo used OCR and hybrid retrieval to make a 56-page scan searchable with page-marked citations in under five minutes.
Read more on Kimbodo:
How to Build More Reliable RAG Search with Hybrid Retrieval, OCR and Cited Answers
What Happened Recent releases and implementations show RAG search moving beyond vector similarity alone. Qdrant 1.20 adds BM25 ranking over full-text payloads without requiring embeddings, a tokenizer for code search,…
kimbodo.com
November 6, 2026 at 7:50 PM
Vector search misses exact terms; scanned pages need OCR.
Qdrant 1.20 adds BM25 over text payloads without embeddings. An Elasticsearch demo used OCR and hybrid retrieval to make a 56-page scan searchable with page-marked citations in under five minutes.
Read more on Kimbodo:
Qdrant 1.20 adds BM25 over text payloads without embeddings. An Elasticsearch demo used OCR and hybrid retrieval to make a 56-page scan searchable with page-marked citations in under five minutes.
Read more on Kimbodo:
That's a solid setup for keeping notes private. One thing worth considering: if you're tunneling over SSH, make sure your Qdrant vector DB isn't exposed on 0.0.0.0 by default—binding to 127.0.0.1 only is the right call you've already got there.
November 4, 2026 at 9:29 AM
That's a solid setup for keeping notes private. One thing worth considering: if you're tunneling over SSH, make sure your Qdrant vector DB isn't exposed on 0.0.0.0 by default—binding to 127.0.0.1 only is the right call you've already got there.
Want to ask questions of your own notes without pasting them into someone's chatbot?
One conn3x apply builds a droplet, closes everything but SSH, and runs Ollama and Qdrant on 127.0.0.1. You reach them through an SSH tunnel. $24 a month.
conn3x.org/blog/private-ai-box
One conn3x apply builds a droplet, closes everything but SSH, and runs Ollama and Qdrant on 127.0.0.1. You reach them through an SSH tunnel. $24 a month.
conn3x.org/blog/private-ai-box
A private AI box in one apply
One conn3x apply builds a droplet, shuts everything but SSH, and runs Ollama and Qdrant where only the box can reach them. You ask questions of your own notes through an SSH tunnel, and nothing goes t...
conn3x.org
November 3, 2026 at 4:19 PM
Want to ask questions of your own notes without pasting them into someone's chatbot?
One conn3x apply builds a droplet, closes everything but SSH, and runs Ollama and Qdrant on 127.0.0.1. You reach them through an SSH tunnel. $24 a month.
conn3x.org/blog/private-ai-box
One conn3x apply builds a droplet, closes everything but SSH, and runs Ollama and Qdrant on 127.0.0.1. You reach them through an SSH tunnel. $24 a month.
conn3x.org/blog/private-ai-box
🔴 Qdrant Cloud: Cloud UI and login unavailable
The Qdrant Cloud UI and login do not work. Qdrant reports that it is investigating this issue. Existing clusters and database operations continue to work normally.
Major outage · Cloud UI
https://outages.live/outages/qdrant-14sy9yj7lf2
The Qdrant Cloud UI and login do not work. Qdrant reports that it is investigating this issue. Existing clusters and database operations continue to work normally.
Major outage · Cloud UI
https://outages.live/outages/qdrant-14sy9yj7lf2
Qdrant Cloud: Cloud UI and login unavailable
The Qdrant Cloud UI and login do not work. Qdrant reports that it is investigating this issue. Existing clusters and database operations continue to work normally.
outages.live
November 2, 2026 at 1:31 PM
🔴 Qdrant Cloud: Cloud UI and login unavailable
The Qdrant Cloud UI and login do not work. Qdrant reports that it is investigating this issue. Existing clusters and database operations continue to work normally.
Major outage · Cloud UI
https://outages.live/outages/qdrant-14sy9yj7lf2
The Qdrant Cloud UI and login do not work. Qdrant reports that it is investigating this issue. Existing clusters and database operations continue to work normally.
Major outage · Cloud UI
https://outages.live/outages/qdrant-14sy9yj7lf2
🚨 Multiple tools not enough for predictable AI agents?
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
From Local RAG to an AI Agent in C# with Ollama and Qdrant - Part 3 - Ottorino Bruni
Learn how to build AI Agent workflows with Human-in-the-Loop approval using C#, Microsoft Agent Framework, Ollama, and Qdrant.
www.ottorinobruni.com
November 3, 2026 at 2:16 PM
🚨 Multiple tools not enough for predictable AI agents?
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
✅ Resolved: Qdrant - Cloud UI and login unavailable
⚠️ Qdrant is reporting an incident: Cloud UI and login unavailable
Investigating: We are investigating an issue affecting the Qdrant Cloud UI and login. Users may be unable to sign in or use the Cloud UI. Existing clusters and database operations are not affected and continue to…
t.lpl.dev/isiOsxW
Investigating: We are investigating an issue affecting the Qdrant Cloud UI and login. Users may be unable to sign in or use the Cloud UI. Existing clusters and database operations are not affected and continue to…
t.lpl.dev/isiOsxW
November 2, 2026 at 2:25 PM
✅ Resolved: Qdrant - Cloud UI and login unavailable
✅ Resolved. Qdrant Cloud reports this incident as resolved after 1 min.
November 2, 2026 at 2:27 PM
✅ Resolved. Qdrant Cloud reports this incident as resolved after 1 min.
⚠️ Qdrant is reporting an incident: Cloud UI and login unavailable
Investigating: We are investigating an issue affecting the Qdrant Cloud UI and login. Users may be unable to sign in or use the Cloud UI. Existing clusters and database operations are not affected and continue to…
t.lpl.dev/isiOsxW
Investigating: We are investigating an issue affecting the Qdrant Cloud UI and login. Users may be unable to sign in or use the Cloud UI. Existing clusters and database operations are not affected and continue to…
t.lpl.dev/isiOsxW
November 2, 2026 at 1:32 PM
⚠️ Qdrant is reporting an incident: Cloud UI and login unavailable
Investigating: We are investigating an issue affecting the Qdrant Cloud UI and login. Users may be unable to sign in or use the Cloud UI. Existing clusters and database operations are not affected and continue to…
t.lpl.dev/isiOsxW
Investigating: We are investigating an issue affecting the Qdrant Cloud UI and login. Users may be unable to sign in or use the Cloud UI. Existing clusters and database operations are not affected and continue to…
t.lpl.dev/isiOsxW
🚨 Multiple tools not enough for predictable AI agents?
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
From Local RAG to an AI Agent in C# with Ollama and Qdrant - Part 3 - Ottorino Bruni
Learn how to build AI Agent workflows with Human-in-the-Loop approval using C#, Microsoft Agent Framework, Ollama, and Qdrant.
www.ottorinobruni.com
November 2, 2026 at 9:37 AM
🚨 Multiple tools not enough for predictable AI agents?
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
Part 3: add Agent Workflows + Human-in-the-Loop with Ollama, Qdrant & Microsoft Agent Framework fully local! 🤖🔒
Guide: www.ottorinobruni.com/from-local-r...
Following the series? 👇
#dotnet #CSharp #AIAgents #RAG
Build a RAG pipeline that survives bot blocks and JavaScript pages: fetch LLM-ready Markdown with Zyte API, gate bad pages, and test it before deploying. https://zpr.io/Y9chvGX3cmzz
#webscraping #webdata #web #data #zyte
#webscraping #webdata #web #data #zyte
How to get uninterrupted web data for your RAG pipelines using Zyte API, Qdrant and LangChain?
Build a RAG pipeline that survives bot blocks and JavaScript pages: fetch LLM-ready Markdown with Zyte API, gate bad pages, and test it before deploying.
zpr.io
November 5, 2026 at 7:47 AM
Build a RAG pipeline that survives bot blocks and JavaScript pages: fetch LLM-ready Markdown with Zyte API, gate bad pages, and test it before deploying. https://zpr.io/Y9chvGX3cmzz
#webscraping #webdata #web #data #zyte
#webscraping #webdata #web #data #zyte
Just starred memory-os. It's a 7-layer memory system for Hermes Agent that uses Qdrant for persistent memory and structured facts. It's a great local-first way to handle context injection with any LLM.
https://github.com/ClaudioDrews/memory-os
https://github.com/ClaudioDrews/memory-os
ClaudioDrews/memory-os
⭐ 1,388 stars • Python
A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.
github.com
November 2, 2026 at 5:34 PM
Just starred memory-os. It's a 7-layer memory system for Hermes Agent that uses Qdrant for persistent memory and structured facts. It's a great local-first way to handle context injection with any LLM.
https://github.com/ClaudioDrews/memory-os
https://github.com/ClaudioDrews/memory-os
📦 kipchak/driver-vector 1.2
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
November 2, 2026 at 11:59 AM
📦 kipchak/driver-vector 1.2
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
🚀 Final part of my C# AI Agent series is out!
What happens when an AI Agent needs to take action, not just answer questions?
In Part 3, we add:
✅ Controlled workflows
✅ Human-in-the-Loop approval
✅ Simulated deployment restart
🔗 www.ottorinobruni.com/from-local-r...
#dotnet #AI #MicrosoftMVP
What happens when an AI Agent needs to take action, not just answer questions?
In Part 3, we add:
✅ Controlled workflows
✅ Human-in-the-Loop approval
✅ Simulated deployment restart
🔗 www.ottorinobruni.com/from-local-r...
#dotnet #AI #MicrosoftMVP
From Local RAG to an AI Agent in C# with Ollama and Qdrant - Part 3 - Ottorino Bruni
Learn how to build AI Agent workflows with Human-in-the-Loop approval using C#, Microsoft Agent Framework, Ollama, and Qdrant.
www.ottorinobruni.com
November 1, 2026 at 8:31 AM
🚀 Final part of my C# AI Agent series is out!
What happens when an AI Agent needs to take action, not just answer questions?
In Part 3, we add:
✅ Controlled workflows
✅ Human-in-the-Loop approval
✅ Simulated deployment restart
🔗 www.ottorinobruni.com/from-local-r...
#dotnet #AI #MicrosoftMVP
What happens when an AI Agent needs to take action, not just answer questions?
In Part 3, we add:
✅ Controlled workflows
✅ Human-in-the-Loop approval
✅ Simulated deployment restart
🔗 www.ottorinobruni.com/from-local-r...
#dotnet #AI #MicrosoftMVP
The full programme for #LondonSearchWeek is now available londonsearchweek.com - the 20th Search Solutions conference plus tutorials, two Meetups and a pub quiz sponsored by Qdrant! We'd love to see you - everything is free apart from the (very reasonable) conference.
London Search Week
londonsearchweek.com
November 2, 2026 at 10:28 AM
The full programme for #LondonSearchWeek is now available londonsearchweek.com - the 20th Search Solutions conference plus tutorials, two Meetups and a pub quiz sponsored by Qdrant! We'd love to see you - everything is free apart from the (very reasonable) conference.
📦 kipchak/driver-vector 1.1
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
November 1, 2026 at 5:59 AM
📦 kipchak/driver-vector 1.1
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
A vector database driver for semantic search and RAG with Qdrant, pgvector or OpenSearch from the Kipchak API Development Kit (ADK)
🔗 https://1x.ax/mamluk/kipchak/drivers/vector.git
The docker containers you need for #AI at home: www.kdnuggets.com/5-docker-con... #ArtificialIntelligence
5 Docker Containers You Need for a Home AI Lab - KDnuggets
Learn which five Docker containers make a reliable home AI lab, from Ollama and Open WebUI to Qdrant, n8n and Portainer CE, what job each one does, and the first mistake to avoid with each.
www.kdnuggets.com
November 2, 2026 at 5:04 AM
The docker containers you need for #AI at home: www.kdnuggets.com/5-docker-con... #ArtificialIntelligence
📦 condoedge/ai v0.0.21
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
October 31, 2026 at 2:59 AM
📦 condoedge/ai v0.0.21
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
32K-token embeddings don't end RAG chunking.
DMIS Lab’s UltraBERT-Embed-150M maps up to 32K tokens to one vector. A Qdrant comparison includes 512-token chunks and hybrid retrieval, but establishes no winner. Document vectors aid discovery; chunks pinpoint evidence.
Read more on Kimbodo:
DMIS Lab’s UltraBERT-Embed-150M maps up to 32K tokens to one vector. A Qdrant comparison includes 512-token chunks and hybrid retrieval, but establishes no winner. Document vectors aid discovery; chunks pinpoint evidence.
Read more on Kimbodo:
Can 32K-Token Embeddings Replace Chunking in RAG? How to Choose the Right Retrieval Design
What Happened DMIS Lab’s UltraBERT-Embed-150M is a 151M-parameter English embedding model that accepts inputs up to 32K tokens and produces one 768-dimensional vector per input. That makes a single-vector representation…
kimbodo.com
November 2, 2026 at 6:10 PM
32K-token embeddings don't end RAG chunking.
DMIS Lab’s UltraBERT-Embed-150M maps up to 32K tokens to one vector. A Qdrant comparison includes 512-token chunks and hybrid retrieval, but establishes no winner. Document vectors aid discovery; chunks pinpoint evidence.
Read more on Kimbodo:
DMIS Lab’s UltraBERT-Embed-150M maps up to 32K tokens to one vector. A Qdrant comparison includes 512-token chunks and hybrid retrieval, but establishes no winner. Document vectors aid discovery; chunks pinpoint evidence.
Read more on Kimbodo:
📦 condoedge/ai v0.0.17
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
October 30, 2026 at 8:00 PM
📦 condoedge/ai v0.0.17
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI
AI-powered text-to-query system with RAG, Neo4j, and Qdrant
🔗 https://github.com/condoedge/AI