Quantization isn’t a trade-off anymore, it’s a must for scalable AI.
Niranjan Akella breaks down how Qdrant’s 1.5-bit Quantization kills the Float32 tax with 24× compression, no recall loss, and sub-40 ms latency, all powered by Rust for real-time performance.
Read more: qdrant.tech/documentatio...
Niranjan Akella breaks down how Qdrant’s 1.5-bit Quantization kills the Float32 tax with 24× compression, no recall loss, and sub-40 ms latency, all powered by Rust for real-time performance.
Read more: qdrant.tech/documentatio...
November 12, 2025 at 8:53 AM
Quantization isn’t a trade-off anymore, it’s a must for scalable AI.
Niranjan Akella breaks down how Qdrant’s 1.5-bit Quantization kills the Float32 tax with 24× compression, no recall loss, and sub-40 ms latency, all powered by Rust for real-time performance.
Read more: qdrant.tech/documentatio...
Niranjan Akella breaks down how Qdrant’s 1.5-bit Quantization kills the Float32 tax with 24× compression, no recall loss, and sub-40 ms latency, all powered by Rust for real-time performance.
Read more: qdrant.tech/documentatio...
Powering next-gen e-commerce recommendations with hybrid sparse + dense vectors in Qdrant
Sayanteka Chakraborty shares how combining keyword + semantic search boosted relevance and speed
⚡ 3× faster recs
📈 30–40% higher engagement
Hybrid search = smarter personalization
Read more: t.co/dlVzDhdc1o
Sayanteka Chakraborty shares how combining keyword + semantic search boosted relevance and speed
⚡ 3× faster recs
📈 30–40% higher engagement
Hybrid search = smarter personalization
Read more: t.co/dlVzDhdc1o
November 11, 2025 at 6:22 PM
Powering next-gen e-commerce recommendations with hybrid sparse + dense vectors in Qdrant
Sayanteka Chakraborty shares how combining keyword + semantic search boosted relevance and speed
⚡ 3× faster recs
📈 30–40% higher engagement
Hybrid search = smarter personalization
Read more: t.co/dlVzDhdc1o
Sayanteka Chakraborty shares how combining keyword + semantic search boosted relevance and speed
⚡ 3× faster recs
📈 30–40% higher engagement
Hybrid search = smarter personalization
Read more: t.co/dlVzDhdc1o
🧩 Community highlight: Matthieu Nicolescu built a fully self-hosted, cloud-native RAG stack using Qdrant, KServe, and Envoy AI Gateway - all on Kubernetes, no external APIs.
A great blueprint for scalable, data-sovereign AI pipelines.
Check here: medium.com/h7w/cloud-na...
A great blueprint for scalable, data-sovereign AI pipelines.
Check here: medium.com/h7w/cloud-na...
November 6, 2025 at 7:46 AM
🧩 Community highlight: Matthieu Nicolescu built a fully self-hosted, cloud-native RAG stack using Qdrant, KServe, and Envoy AI Gateway - all on Kubernetes, no external APIs.
A great blueprint for scalable, data-sovereign AI pipelines.
Check here: medium.com/h7w/cloud-na...
A great blueprint for scalable, data-sovereign AI pipelines.
Check here: medium.com/h7w/cloud-na...
🗞️ The October Qdrant Newsletter is live!
🚀 Highlights:
• Launch of Qdrant Academy & “Essentials” course
• New tools, tutorials & integrations
• Community projects & ecosystem growth
👉 Read: try.qdrant.tech/october-news...
📩 Subscribe: qdrant.tech/subscribe
#Qdrant #VectorSearch #AI #OpenSource
🚀 Highlights:
• Launch of Qdrant Academy & “Essentials” course
• New tools, tutorials & integrations
• Community projects & ecosystem growth
👉 Read: try.qdrant.tech/october-news...
📩 Subscribe: qdrant.tech/subscribe
#Qdrant #VectorSearch #AI #OpenSource
November 4, 2025 at 4:56 PM
🗞️ The October Qdrant Newsletter is live!
🚀 Highlights:
• Launch of Qdrant Academy & “Essentials” course
• New tools, tutorials & integrations
• Community projects & ecosystem growth
👉 Read: try.qdrant.tech/october-news...
📩 Subscribe: qdrant.tech/subscribe
#Qdrant #VectorSearch #AI #OpenSource
🚀 Highlights:
• Launch of Qdrant Academy & “Essentials” course
• New tools, tutorials & integrations
• Community projects & ecosystem growth
👉 Read: try.qdrant.tech/october-news...
📩 Subscribe: qdrant.tech/subscribe
#Qdrant #VectorSearch #AI #OpenSource
📅 Nov 12, 6 PM CET - Join Dat Daryl Ngo (Arize AI) to explore how to make Agentic RAG systems observable, accountable & self-improving with open-source tools and real-world insights.
👉 Register here:
#AI #RAG #Observability #ArizeAI
👉 Register here:
#AI #RAG #Observability #ArizeAI
November 4, 2025 at 4:55 PM
📅 Nov 12, 6 PM CET - Join Dat Daryl Ngo (Arize AI) to explore how to make Agentic RAG systems observable, accountable & self-improving with open-source tools and real-world insights.
👉 Register here:
#AI #RAG #Observability #ArizeAI
👉 Register here:
#AI #RAG #Observability #ArizeAI
Exciting news from our partner @confluent.io!
Confluent’s new Streaming Agents and Real-Time Context Engine bring live context to AI agents and enterprise apps.
Together, Qdrant × Confluent enable developers to build real-time, AI powered by streaming data and vector search.
👉 t.co/DurLLwYMXO
Confluent’s new Streaming Agents and Real-Time Context Engine bring live context to AI agents and enterprise apps.
Together, Qdrant × Confluent enable developers to build real-time, AI powered by streaming data and vector search.
👉 t.co/DurLLwYMXO
October 30, 2025 at 7:11 PM
Exciting news from our partner @confluent.io!
Confluent’s new Streaming Agents and Real-Time Context Engine bring live context to AI agents and enterprise apps.
Together, Qdrant × Confluent enable developers to build real-time, AI powered by streaming data and vector search.
👉 t.co/DurLLwYMXO
Confluent’s new Streaming Agents and Real-Time Context Engine bring live context to AI agents and enterprise apps.
Together, Qdrant × Confluent enable developers to build real-time, AI powered by streaming data and vector search.
👉 t.co/DurLLwYMXO
Qdrant joins the AI-Powered Search course as a guest lecturer!
Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull.
🔗 Details: aipoweredsearch.com/articles/ai-...
Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull.
🔗 Details: aipoweredsearch.com/articles/ai-...
October 29, 2025 at 12:33 PM
Qdrant joins the AI-Powered Search course as a guest lecturer!
Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull.
🔗 Details: aipoweredsearch.com/articles/ai-...
Our @mrscoopers.bsky.social will speak on “Mixing Sparse & Dense Representations” in Week 2 of Modern Retrieval for Humans and Agents by Trey Grainger and Doug Turnbull.
🔗 Details: aipoweredsearch.com/articles/ai-...
🫶 Big thanks to everyone who joined Qdrant’s Discord Office Hours!
Loved the energy, ideas, and stories - and special thanks to Brian, Joshua, Clelia, and Tarun for the great insights.
See you next month for more tech, chats, and demos! 💬
Loved the energy, ideas, and stories - and special thanks to Brian, Joshua, Clelia, and Tarun for the great insights.
See you next month for more tech, chats, and demos! 💬
October 17, 2025 at 9:37 AM
🫶 Big thanks to everyone who joined Qdrant’s Discord Office Hours!
Loved the energy, ideas, and stories - and special thanks to Brian, Joshua, Clelia, and Tarun for the great insights.
See you next month for more tech, chats, and demos! 💬
Loved the energy, ideas, and stories - and special thanks to Brian, Joshua, Clelia, and Tarun for the great insights.
See you next month for more tech, chats, and demos! 💬
An open source engineer from @llamaindex.bsky.social shares trial-and-error-learned lessons.
For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social!
✅ useful tips, from chunking to evals-related;
✅ projects applying each tip in the wild.
👉 qdrant.tech/blog/hitchhi...
For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social!
✅ useful tips, from chunking to evals-related;
✅ projects applying each tip in the wild.
👉 qdrant.tech/blog/hitchhi...
July 10, 2025 at 2:52 PM
An open source engineer from @llamaindex.bsky.social shares trial-and-error-learned lessons.
For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social!
✅ useful tips, from chunking to evals-related;
✅ projects applying each tip in the wild.
👉 qdrant.tech/blog/hitchhi...
For anyone implementing textual RAG, check the blog by @cle-does-things.bsky.social!
✅ useful tips, from chunking to evals-related;
✅ projects applying each tip in the wild.
👉 qdrant.tech/blog/hitchhi...
☕ Guess what? We're sponsoring the coffee breaks at @berlinbuzzwords.de 2025!
June 10, 2025 at 8:20 AM
☕ Guess what? We're sponsoring the coffee breaks at @berlinbuzzwords.de 2025!
🥨 Come to the Bavarian Search Meetup!
The 2nd meeting of 𝐁avaria, 𝐀dvancements in 𝐒𝐞arch 𝐃evelopment meetup, co-organized by our @mrscoopers.bsky.social, is happening in #Munich on the 12th of June!
👇
The 2nd meeting of 𝐁avaria, 𝐀dvancements in 𝐒𝐞arch 𝐃evelopment meetup, co-organized by our @mrscoopers.bsky.social, is happening in #Munich on the 12th of June!
👇
June 2, 2025 at 1:20 PM
🥨 Come to the Bavarian Search Meetup!
The 2nd meeting of 𝐁avaria, 𝐀dvancements in 𝐒𝐞arch 𝐃evelopment meetup, co-organized by our @mrscoopers.bsky.social, is happening in #Munich on the 12th of June!
👇
The 2nd meeting of 𝐁avaria, 𝐀dvancements in 𝐒𝐞arch 𝐃evelopment meetup, co-organized by our @mrscoopers.bsky.social, is happening in #Munich on the 12th of June!
👇
Want to see MCP in action? Learn how to orchestrate OpenAI agents using MCP, AugmentCode, and Qdrant.
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
April 14, 2025 at 5:21 PM
Want to see MCP in action? Learn how to orchestrate OpenAI agents using MCP, AugmentCode, and Qdrant.
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
📅 April 29 @ 11 am ET
🔗 Save your spot: try.qdrant.tech/mcp-agent-in...
Relevance feedback helps search systems iteratively improve results toward relevance. It’s been studied for 60+ years — yet remains rare in modern neural search.
We explored the field to understand why — and gathered this summary of methods proposed over the years.
⬇️
We explored the field to understand why — and gathered this summary of methods proposed over the years.
⬇️
April 2, 2025 at 3:30 PM
Relevance feedback helps search systems iteratively improve results toward relevance. It’s been studied for 60+ years — yet remains rare in modern neural search.
We explored the field to understand why — and gathered this summary of methods proposed over the years.
⬇️
We explored the field to understand why — and gathered this summary of methods proposed over the years.
⬇️
🚧 We ran vector search over 400M CLIP embeddings from LAION-400M — using Qdrant and just 64GB RAM.
We wanted to see how far we could push Qdrant with minimal hardware and how much we could squeeze out of quantization, indexing, and async I/O.
We wanted to see how far we could push Qdrant with minimal hardware and how much we could squeeze out of quantization, indexing, and async I/O.
March 28, 2025 at 3:06 PM
🚧 We ran vector search over 400M CLIP embeddings from LAION-400M — using Qdrant and just 64GB RAM.
We wanted to see how far we could push Qdrant with minimal hardware and how much we could squeeze out of quantization, indexing, and async I/O.
We wanted to see how far we could push Qdrant with minimal hardware and how much we could squeeze out of quantization, indexing, and async I/O.
A lot of people ask us: “𝗪𝗵𝘆 𝘀𝗵𝗼𝘂𝗹𝗱 𝗜 𝘂𝘀𝗲 𝗮 𝗱𝗲𝗱𝗶𝗰𝗮𝘁𝗲𝗱 𝘃𝗲𝗰𝘁𝗼𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 when I can simply add a vector plugin or extension to my existing database?”
We wrote an article addressing this very common question.
Article: qdrant.tech/articles/ded...
We wrote an article addressing this very common question.
Article: qdrant.tech/articles/ded...
February 19, 2025 at 4:56 PM
A lot of people ask us: “𝗪𝗵𝘆 𝘀𝗵𝗼𝘂𝗹𝗱 𝗜 𝘂𝘀𝗲 𝗮 𝗱𝗲𝗱𝗶𝗰𝗮𝘁𝗲𝗱 𝘃𝗲𝗰𝘁𝗼𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 when I can simply add a vector plugin or extension to my existing database?”
We wrote an article addressing this very common question.
Article: qdrant.tech/articles/ded...
We wrote an article addressing this very common question.
Article: qdrant.tech/articles/ded...
We built our own storage engine to replace RocksDB for payload and sparse vector storage.
It eliminates compaction overhead, optimizes sequential key access, and provides direct control over data writes.
Benchmarks show 2x faster ingestion with stable throughput.
Now live in Qdrant 1.13!
It eliminates compaction overhead, optimizes sequential key access, and provides direct control over data writes.
Benchmarks show 2x faster ingestion with stable throughput.
Now live in Qdrant 1.13!
February 6, 2025 at 12:27 PM
We built our own storage engine to replace RocksDB for payload and sparse vector storage.
It eliminates compaction overhead, optimizes sequential key access, and provides direct control over data writes.
Benchmarks show 2x faster ingestion with stable throughput.
Now live in Qdrant 1.13!
It eliminates compaction overhead, optimizes sequential key access, and provides direct control over data writes.
Benchmarks show 2x faster ingestion with stable throughput.
Now live in Qdrant 1.13!
Join us Feb 13 @ 11 AM ET for a live session on deploying DeepSeek for agentic RAG purely open-source and in your own environment.
✅ Deploy DeepSeek locally
✅ Secure vector search with Qdrant
✅ Optimize AI for privacy-first use cases
👉 RSVP: buff.ly/40SkyAf
✅ Deploy DeepSeek locally
✅ Secure vector search with Qdrant
✅ Optimize AI for privacy-first use cases
👉 RSVP: buff.ly/40SkyAf
January 31, 2025 at 2:14 AM
Join us Feb 13 @ 11 AM ET for a live session on deploying DeepSeek for agentic RAG purely open-source and in your own environment.
✅ Deploy DeepSeek locally
✅ Secure vector search with Qdrant
✅ Optimize AI for privacy-first use cases
👉 RSVP: buff.ly/40SkyAf
✅ Deploy DeepSeek locally
✅ Secure vector search with Qdrant
✅ Optimize AI for privacy-first use cases
👉 RSVP: buff.ly/40SkyAf
Qdrant 1.13 introduces GPU Accelerated Indexing 🚀
Enabling up to 10x faster HNSW index construction compared to CPU-based systems while remaining platform-agnostic, with support for NVIDIA, AMD, and Intel GPUs.
Release Notes: qdrant.tech/blog/qdrant-...
Documentation: qdrant.tech/documentatio...
Enabling up to 10x faster HNSW index construction compared to CPU-based systems while remaining platform-agnostic, with support for NVIDIA, AMD, and Intel GPUs.
Release Notes: qdrant.tech/blog/qdrant-...
Documentation: qdrant.tech/documentatio...
January 24, 2025 at 3:16 PM
Qdrant 1.13 introduces GPU Accelerated Indexing 🚀
Enabling up to 10x faster HNSW index construction compared to CPU-based systems while remaining platform-agnostic, with support for NVIDIA, AMD, and Intel GPUs.
Release Notes: qdrant.tech/blog/qdrant-...
Documentation: qdrant.tech/documentatio...
Enabling up to 10x faster HNSW index construction compared to CPU-based systems while remaining platform-agnostic, with support for NVIDIA, AMD, and Intel GPUs.
Release Notes: qdrant.tech/blog/qdrant-...
Documentation: qdrant.tech/documentatio...
Our New Storage Architecture 🌐
There are four elements: the Data Layer, Mask Layer, the Region and Tracker Layer.
This new backend ensures constant-time reads/writes, even for massive datasets.
There are four elements: the Data Layer, Mask Layer, the Region and Tracker Layer.
This new backend ensures constant-time reads/writes, even for massive datasets.
January 23, 2025 at 3:05 PM
Our New Storage Architecture 🌐
There are four elements: the Data Layer, Mask Layer, the Region and Tracker Layer.
This new backend ensures constant-time reads/writes, even for massive datasets.
There are four elements: the Data Layer, Mask Layer, the Region and Tracker Layer.
This new backend ensures constant-time reads/writes, even for massive datasets.
HNSW Graph Compression 📈
We’ve now adapted Delta Encoding for the HNSW graph structure.
In our experiments, the memory footprint of the HNSW graph was reduced by up to 30% with no measurable performance degradation.
We’ve now adapted Delta Encoding for the HNSW graph structure.
In our experiments, the memory footprint of the HNSW graph was reduced by up to 30% with no measurable performance degradation.
January 23, 2025 at 3:05 PM
HNSW Graph Compression 📈
We’ve now adapted Delta Encoding for the HNSW graph structure.
In our experiments, the memory footprint of the HNSW graph was reduced by up to 30% with no measurable performance degradation.
We’ve now adapted Delta Encoding for the HNSW graph structure.
In our experiments, the memory footprint of the HNSW graph was reduced by up to 30% with no measurable performance degradation.
Strict Mode for Operational Control 🖥️
Additional config for consistent performance in multi-tenant setups. Set advanced operational restrictions and ensure detailed error feedback.
api.qdrant.tech/api-referenc...
Additional config for consistent performance in multi-tenant setups. Set advanced operational restrictions and ensure detailed error feedback.
api.qdrant.tech/api-referenc...
January 23, 2025 at 3:05 PM
Strict Mode for Operational Control 🖥️
Additional config for consistent performance in multi-tenant setups. Set advanced operational restrictions and ensure detailed error feedback.
api.qdrant.tech/api-referenc...
Additional config for consistent performance in multi-tenant setups. Set advanced operational restrictions and ensure detailed error feedback.
api.qdrant.tech/api-referenc...
GPU Accelerated Indexing ⚡️
Index up to 10x faster with architecture-free support for NVIDIA, AMD, and Intel GPUs!
Here is a picture of us, running Qdrant with GPU support on a SteamDeck (AMD Van Gogh GPU):
Index up to 10x faster with architecture-free support for NVIDIA, AMD, and Intel GPUs!
Here is a picture of us, running Qdrant with GPU support on a SteamDeck (AMD Van Gogh GPU):
January 23, 2025 at 3:05 PM
GPU Accelerated Indexing ⚡️
Index up to 10x faster with architecture-free support for NVIDIA, AMD, and Intel GPUs!
Here is a picture of us, running Qdrant with GPU support on a SteamDeck (AMD Van Gogh GPU):
Index up to 10x faster with architecture-free support for NVIDIA, AMD, and Intel GPUs!
Here is a picture of us, running Qdrant with GPU support on a SteamDeck (AMD Van Gogh GPU):
Agentic RAG With LangGraph and Qdrant 🚀
Built as a developer assistant for Hugging Face 🤗 and Transformers libraries, this AI agent retrieves guides, docs, and real-time info to answer complex technical queries instantly.
🧰 Begin the tutorial here: qdrant.tech/documentatio...
Built as a developer assistant for Hugging Face 🤗 and Transformers libraries, this AI agent retrieves guides, docs, and real-time info to answer complex technical queries instantly.
🧰 Begin the tutorial here: qdrant.tech/documentatio...
January 13, 2025 at 9:41 PM
Agentic RAG With LangGraph and Qdrant 🚀
Built as a developer assistant for Hugging Face 🤗 and Transformers libraries, this AI agent retrieves guides, docs, and real-time info to answer complex technical queries instantly.
🧰 Begin the tutorial here: qdrant.tech/documentatio...
Built as a developer assistant for Hugging Face 🤗 and Transformers libraries, this AI agent retrieves guides, docs, and real-time info to answer complex technical queries instantly.
🧰 Begin the tutorial here: qdrant.tech/documentatio...
🌟 We’re happy to welcome @cle-does-things.bsky.social as our newest Qdrant ambassador! 🎉
Clelia has already made waves in the Qdrant ecosystem, and we’re excited to have her officially on board. 🚀
If you love vector search and want to make an impact, join the Qdrant Stars! ✨
Clelia has already made waves in the Qdrant ecosystem, and we’re excited to have her officially on board. 🚀
If you love vector search and want to make an impact, join the Qdrant Stars! ✨
January 6, 2025 at 5:03 PM
🌟 We’re happy to welcome @cle-does-things.bsky.social as our newest Qdrant ambassador! 🎉
Clelia has already made waves in the Qdrant ecosystem, and we’re excited to have her officially on board. 🚀
If you love vector search and want to make an impact, join the Qdrant Stars! ✨
Clelia has already made waves in the Qdrant ecosystem, and we’re excited to have her officially on board. 🚀
If you love vector search and want to make an impact, join the Qdrant Stars! ✨
🚀 Our Developer Portal has officially launched with a brand-new design!
We’ve redesigned the experience to make it faster, clearer, and more intuitive, helping you focus on what matters most: vectors.
👉 Tell us what you think: qdrant.tech/documentation/
We’ve redesigned the experience to make it faster, clearer, and more intuitive, helping you focus on what matters most: vectors.
👉 Tell us what you think: qdrant.tech/documentation/
December 30, 2024 at 4:21 PM
🚀 Our Developer Portal has officially launched with a brand-new design!
We’ve redesigned the experience to make it faster, clearer, and more intuitive, helping you focus on what matters most: vectors.
👉 Tell us what you think: qdrant.tech/documentation/
We’ve redesigned the experience to make it faster, clearer, and more intuitive, helping you focus on what matters most: vectors.
👉 Tell us what you think: qdrant.tech/documentation/