Qdrant(@qdrant_engine)

We’re coming to New York for an AI debate night where you’ll defend the side you didn’t choose. Joi...

Qdrant (@qdrant_engine) — Fri, 14 Aug 2026 12:37:32 GMT

We’re coming to New York for an AI debate night where you’ll defend the side you didn’t choose.

Join us for Hard Negatives: AI Engineers Debate & Game Night.

You’ll draw a controversial AI take at random, get 3 minutes to prepare, and 10 minutes to convince the room. The audience votes live, and the strongest arguments win prizes.

Prizes, food, drinks, pool, darts, foosball, ping pong, and shuffleboard included.

Date: August 26
Time: 6:30 PM - 10:00 PM EDT
Venue: Sugar Mouse NYC

Limited spots. 21+. Registration approval required.
Register: luma.com/nyc-meetup-qdr…

💬1🔄1❤️2👀223📊2

⚡ Powered by xgo.ing

How @Bayer built an enterprise search engine for 116,000 employees on Qdrant Hybrid Cloud:1 35M poi...

Qdrant (@qdrant_engine) — Thu, 13 Aug 2026 18:17:10 GMT

How @Bayer built an enterprise search engine for 116,000 employees on Qdrant Hybrid Cloud:1

35M points on 4 nodes. Hybrid search for deep agents. Semantic caching to control agent cost. A measured 20% efficiency gain.

Three years in production, from prototype to platform: qdrant.tech/blog/case-stud…

💬2🔄1❤️12👀426📊4

⚡ Powered by xgo.ing

We’re coming to San Francisco for a night of AI debates, games, and prizes. Join Qdrant and @neo4j ...

Qdrant (@qdrant_engine) — Thu, 13 Aug 2026 15:00:02 GMT

We’re coming to San Francisco for a night of AI debates, games, and prizes.

Join Qdrant and @neo4j for Hard Negatives Meetup: Engineers Debate Night.

You’ll be paired into teams and randomly assigned a controversial AI topic to defend. You’ll get a few minutes to prepare, then it’s time to convince the room. The audience decides who wins.

Prizes:
- First prize: Nintendo Switch
- Second prize: Surprise LEGO set
- Third prize: Qdrant hoodie

Food, drinks, games, and networking with AI engineers, researchers, and builders.

Date: August 25
Time: 6:30 PM - 8:30 PM PDT

Register: luma.com/nyc-meetup-qdr…

Your browser does not support the video tag.

🔗 View on Twitter

💬0🔄2❤️3👀396📊1

⚡ Powered by xgo.ing

Let’s Talk about Qdrant 1.19! It’s time to discuss what’s new. Join us for our next Qdrant Discord...

Qdrant (@qdrant_engine) — Thu, 13 Aug 2026 06:00:01 GMT

Let’s Talk about Qdrant 1.19!

It’s time to discuss what’s new.

Join us for our next Qdrant Discord Office Hours as we walk through the latest features and updates, followed by an open Q&A and community discussion.

Date: August 20
Time: 5:00 PM CEST
Link: discord.gg/PGemY6ugf?even…

Bring your questions, projects, and ideas. We’d love to hear what you’re working on!

More details about 1.19 update: qdrant.tech/blog/qdrant-1.…

See you there!

💬1🔄2❤️12👀841📊4

⚡ Powered by xgo.ing

2 Days Until We Give Slack a Memory Join Qdrant and @cognee_ in Berlin for a hands-on hack night wh...

Qdrant (@qdrant_engine) — Wed, 12 Aug 2026 18:37:49 GMT

2 Days Until We Give Slack a Memory

Join Qdrant and @cognee_ in Berlin for a hands-on hack night where you’ll build a memory layer that helps AI agents reason over your Slack history.

-  €1,200 prize pool
-  Swag, datasets, API keys + support from both teams
- Bring your laptop and build with us!

Date: August 14
Location: Paul-Lincke-Ufer 39-40, Berlin

Register now: luma.com/cognee-m078

💬1🔄2❤️6👀441📊3

⚡ Powered by xgo.ing

Keyword indexes in Qdrant are built for exact matching. They’re ideal for values like URLs, file pat...

Qdrant (@qdrant_engine) — Tue, 11 Aug 2026 14:21:04 GMT

Keyword indexes in Qdrant are built for exact matching. They’re ideal for values like URLs, file paths, SKUs, and unique identifiers.

The challenge? If you wanted to find values that start with something, for example, all URLs beginning with “https://qdrant”., you had two options:

- Scan every value in the payload, or
- Switch to a text index, which tokenizes the value and no longer supports exact matching.

Qdrant 1.19 solves this.

You can now enable prefix matching on keyword indexes with "prefix": true in the index configuration. After that, prefix filters are served directly from the index, giving you fast prefix lookups while keeping exact matching.

Full release here: qdrant.tech/blog/qdrant-1.…

💬4🔄4❤️24👀1055📊9

⚡ Powered by xgo.ing

BM25 scoring relies on IDF (Inverse Document Frequency). In simple terms, the rarer a word is in you...

Qdrant (@qdrant_engine) — Mon, 10 Aug 2026 15:29:33 GMT

BM25 scoring relies on IDF (Inverse Document Frequency). In simple terms, the rarer a word is in your data, the more important it becomes during search.

In a multi-tenant collection, IDF was previously calculated across all tenants combined. That meant if Tenant A and Tenant B used very different vocabularies, their statistics were mixed together. As a result, a word that was rare for one tenant might not be treated as rare, leading to less accurate BM25 scores.

Qdrant 1.19 fixes this.

You can now calculate IDF statistics per tenant instead of across the entire collection. Each tenant’s BM25 scores are now based only on their own data, resulting in more accurate lexical search without requiring separate collections.

Full release here: qdrant.tech/blog/qdrant-1.…

💬0🔄6❤️31👀1533📊7

⚡ Powered by xgo.ing

Qdrant 1.18 introduced TurboQuant, a quantization technique that speeds up vector search by keeping ...

Qdrant (@qdrant_engine) — Fri, 07 Aug 2026 06:51:58 GMT

Qdrant 1.18 introduced TurboQuant, a quantization technique that speeds up vector search by keeping a 4-bit compressed copy of your vectors in memory while storing the original float32 vectors on disk for rescoring.

Great recall, but two copies of every vector.

We just released Qdrant 1.19, which introduces Turbo4, a new datatype that stores only the 4-bit representation, removing the original float32 copy entirely.

That reduces storage from 36 bits per coordinate to just 4 bits, a 9× storage reduction. With less data to read and write, search throughput also improves.

The tradeoff is simple: without the original vectors, rescoring isn’t possible. If storage efficiency is your priority, Turbo4 is the right choice. If you need the highest possible recall, TurboQuant with full-precision storage is still the better option.

The same storage savings apply to multi-vector collections, making ColBERT-style late interaction search significantly more space-efficient.

Full release here: qdrant.tech/blog/qdrant-1.…

💬2🔄15❤️72👀3837📊19

⚡ Powered by xgo.ing

Can your Slack remember what your team already knows? Join Qdrant and @cognee_ in Berlin for an eve...

Qdrant (@qdrant_engine) — Thu, 06 Aug 2026 11:00:00 GMT

Can your Slack remember what your team already knows?

Join Qdrant and @cognee_ in Berlin for an evening of building AI memory that goes beyond context windows.

At this hands-on hack night, you’ll build a memory layer that turns your Slack workspace into something agents can actually reason over, using cognee for structured memory and Qdrant for fast semantic retrieval.

- €1,200 prize pool:
- Plus, you’ll get swag, API keys, sample datasets, and support from the cognee and Qdrant teams throughout the event.

Date: August 14
Location: Paul-Lincke-Ufer 39-40/hof 4, Berlin

Register now: luma.com/cognee-m078

💬1🔄1❤️7👀536📊2

⚡ Powered by xgo.ing

(6/6) One upgrade note: the legacy /search, /recommend, and /discover endpoints are gone. Migrate to...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 22:32:55 GMT

(6/6) One upgrade note: the legacy /search, /recommend, and /discover endpoints are gone. Migrate to /query before you upgrade.

Full release blog here: qdrant.tech/blog/qdrant-1.…

💬0🔄0❤️2👀173

⚡ Powered by xgo.ing

(5/6) Filtering: Prefix matching on keyword indexes means no more full payload scans, and no more tr...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 22:32:25 GMT

(5/6) Filtering: Prefix matching on keyword indexes means no more full payload scans, and no more trading exact matching for a text index.

💬0🔄0❤️2👀216

⚡ Powered by xgo.ing

(4/6) Per-Tenant IDF Statistics: You can now narrow the corpus to a single tenant, so term rarity re...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 22:32:15 GMT

(4/6) Per-Tenant IDF Statistics: You can now narrow the corpus to a single tenant, so term rarity reflects that tenant's data instead of the whole dataset.

💬0🔄0❤️2👀62

⚡ Powered by xgo.ing

(3/6) Memory Tiers: One memory parameter now replaces on_disk, always_ram, and on_disk_payload, and ...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 22:32:00 GMT

(3/6) Memory Tiers: One memory parameter now replaces on_disk, always_ram, and on_disk_payload, and it works the same way on every component of a collection.

💬0🔄0❤️4👀40📊1

⚡ Powered by xgo.ing

(2/6) TurboQuant Datatype: Version 1.18 shipped TurboQuant as a quantization layer. 1.19 enables the...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 22:31:45 GMT

(2/6) TurboQuant Datatype: Version 1.18 shipped TurboQuant as a quantization layer. 1.19 enables the new Turbo4 datatype, which keeps only the 4-bit representation. That takes 36 bits per coordinate (the float32 original plus the 4-bit copy) down to four, a ninefold storage reduction, and fewer reads and writes per operation lifts throughput

💬0🔄0❤️4👀121📊1

⚡ Powered by xgo.ing

(1/6) Qdrant 1.19 is now here! Below are the main updates 🧵 Full release blog: https://t.co/v52PS1...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 22:31:28 GMT

(1/6) Qdrant 1.19 is now here! Below are the main updates 🧵

Full release blog:qdrant.tech/blog/qdrant-1.…Z

💬5🔄6❤️19👀917📊9

⚡ Powered by xgo.ing

Why does your RAG agent get worse over time? Join @DylanCouzon and Rishabh from FutureAGI tomorrow ...

Qdrant (@qdrant_engine) — Wed, 05 Aug 2026 16:22:11 GMT

Why does your RAG agent get worse over time?

Join @DylanCouzon and Rishabh from FutureAGI tomorrow as they build, debug, and optimize a RAG agent live, covering embedding migrations, deduplication, reranking, and evaluation to measure what actually improves retrieval quality.

Time: 6:30 PM CEST | 9:30 AM PDT | 10:00 PM IST

Register now: luma.com/future-pq6q

💬2🔄2❤️6👀520📊4

⚡ Powered by xgo.ing

You know you are hitting the API and making round trips again and again when a user asks the same qu...

Qdrant (@qdrant_engine) — Tue, 04 Aug 2026 10:54:57 GMT

You know you are hitting the API and making round trips again and again when a user asks the same question, like "what's the refund policy?" or "what are the conditions of a refund?"

You might not have a cache layer built in, or if you do it's probably keyword-based, which only works on exact matches. In that case semantic cache can be useful.

What semantic cache does is store previously asked questions along with their answers. When a new query comes in, it checks for semantic similarity against cached questions. If the similarity score is above a threshold, it returns the cached answer without going through retrieval and generation again. Same answer, no unnecessary API calls or retrieval round trips.

You can learn more about how semantic cache works in practice in our guide: qdrant.tech/articles/seman…

💬1🔄4❤️10👀808📊4

⚡ Powered by xgo.ing

Search. Hybrid retrieval. Faceted filters. Recommendations. Personalization. Visual similarity. Merc...

Qdrant (@qdrant_engine) — Mon, 03 Aug 2026 07:48:55 GMT

Search. Hybrid retrieval. Faceted filters. Recommendations. Personalization. Visual similarity. Merchandising.

All over 5.8M real products.

Performance:
- 40 ms for search with filters and personalization
- 10 ms for similar products
- <1 ms for product lookups
- 96% Precision@10
- ~1.9 GB RAM

One Query API call. That's the whole stack.

The demo and code are both open source. Shoutout to @DylanCouzon for building it. 👏

Demo:demo-ecommerce-search.vercel.appJ
Code:github.com/qdrant-labs/de…N

💬2🔄1❤️13👀732📊4

⚡ Powered by xgo.ing

One week to go! Join us for “Why does my RAG-agent get worse? A live autopsy” with @DylanCouzon fro...

Qdrant (@qdrant_engine) — Fri, 31 Jul 2026 15:00:02 GMT

One week to go!

Join us for “Why does my RAG-agent get worse? A live autopsy” with @DylanCouzon from Qdrant and Rishabh from FutureAGI.

As your RAG system evolves, quality can quietly degrade. In this live session, we’ll build, debug, and improve a RAG agent while measuring the impact of every change.

We’ll cover:
→ Finding where your agent is losing quality
→ Migrating to a new embedding model with zero downtime
→ Removing duplicate and fragmented chunks
→ Adding late interaction reranking
→ Comparing evaluation scores before and after each optimization

We’re also looking for 5-minute community demos before the webinar. If you’d like to present your project, apply here: docs.google.com/forms/d/10-9oy…

Date: August 6
Time: 6:30 PM CEST | 9:30 AM PDT | 10:00 PM IST

Register now: luma.com/future-pq6q

💬1🔄1❤️9👀504📊3

⚡ Powered by xgo.ing

We’re coming to New York for AI debates where you’ll defend the side you didn’t choose. Join us for...

Qdrant (@qdrant_engine) — Thu, 30 Jul 2026 19:20:27 GMT

We’re coming to New York for AI debates where you’ll defend the side you didn’t choose.

Join us for Hard Negatives: AI Engineers Debate & Game Night, where controversial AI takes are assigned at random, and it’s your job to convince the room.

Debate topics like:
→ “RAG is dead”
→ “AI is already sentient”
→ “Open weights should be banned”

- Win a Nintendo Switch, LEGO sets, Qdrant hoodies & more
- Drinks, appetizers, and arcade games

Meet AI engineers, researchers, and builders from across NYC

Date: August 26 | Venue: Sugar Mouse NYC

Register now: luma.com/nyc-meetup-qdr…

💬1🔄4❤️9👀501📊4

⚡ Powered by xgo.ing

Bulk uploading at scale doesn't have to be expensive. A few things worth knowing if you're ingestin...

Qdrant (@qdrant_engine) — Thu, 30 Jul 2026 14:28:22 GMT

Bulk uploading at scale doesn't have to be expensive.

A few things worth knowing if you're ingesting at scale:

Dense vectors may eat RAM fast. The fix? Store the original vectors on disk and keep only the compressed ones in RAM. TurboQuant can get you 8x smaller with almost no recall loss, or 32x if you're really tight on memory.

Sparse vectors have a different case. It's not the vectors that get large, it's the index. You can store that on disk too and use float16 precision to cut it in half.

Create payload indexes before uploading. Qdrant's HNSW builds filter-aware edges during graph construction. Create them after and the graph has to rebuild from scratch.

Full guide: qdrant.tech/articles/bulk-…

💬0🔄1❤️8👀502📊2

⚡ Powered by xgo.ing

Most people treat video like a bag of frames or a transcript with timestamps. But you end up missing...

Qdrant (@qdrant_engine) — Wed, 29 Jul 2026 07:56:23 GMT

Most people treat video like a bag of frames or a transcript with timestamps. But you end up missing the most important parts of it:
- Motion
- Causality
- Temporal progression
- The relationship between what happens and why it matters

At Vector Space Day SF, James Le from @twelve_labs walked through 3 failure modes that come from this:
- Wrong Context
- Wrong Memory
- Wrong Reasoning

And he introduced the stack built to fix it:
→ Marengo: a retrieval model that makes video searchable
→ Pegasus: a video language model that turns retrieved moments into structured answers
→ Jockey: an agentic framework and memory layer for video corpus workflows

With Qdrant handling the storage and retrieval underneath it all.

Full talk is live on our YouTube channel: youtube.com/watch?v=i8xZeK…

💬0🔄2❤️10👀527📊2

⚡ Powered by xgo.ing

Most agents trust the first search result and keep going, even when retrieval fails. That's the pro...

Qdrant (@qdrant_engine) — Tue, 28 Jul 2026 17:50:08 GMT

Most agents trust the first search result and keep going, even when retrieval fails.

That's the problem @JKupchanko41535 from the Qdrant team is tackling at this event. His talk covers how to build a self-improving retrieval loop that detects weak results, changes strategy, and knows when to retry, escalate, or stop before the agent hallucinates.

Joining him are Nikhil Pareek from Future AGI on engineering self-improving agent systems, Amazon Web Services (AWS) on agentic AI and Amazon Bedrock, and builder demos from teams shipping real agent infrastructure.

If you're in San Francisco and building agents, workflows, or AI infrastructure - this is a good room to be in.

📅 July 29th, 5pm PDT

📍 AWS Builder Loft, 525 Market St, San Francisco

Register here (AWS registration required for entry)luma.com/future-arpzD7

💬0🔄1❤️4👀482📊1

⚡ Powered by xgo.ing

On-device AI has three advantages over cloud. Cost, privacy, and latency. Alan Zhu from @Qualcomm d...

Qdrant (@qdrant_engine) — Mon, 27 Jul 2026 17:15:21 GMT

On-device AI has three advantages over cloud. Cost, privacy, and latency.

Alan Zhu from @Qualcomm demonstrated why latency is the most underestimated advantage of on-device AI at Vector Space Day SF.

Alan ran the same agentic search task on NPU, GPU, and CPU. NPU responded instantly. GPU took 12 seconds. CPU took 30, then throttled down as the device heated up.

The NPU held 90 tokens/sec for the full session at 37°C. The CPU started lower and kept dropping.

The reason: NPU prefill speed. Fast enough to process thousands of local files and return a cited answer in seconds, entirely on device, no network required.

That's what makes local AI agents actually practical, not just theoretically possible.

Full talk: youtube.com/watch?v=FlAmmV…

💬2🔄2❤️7👀489📊4

⚡ Powered by xgo.ing

0.1ms vs 52ms. That’s what happens when you remove the network. For robots, drones, wearables, and...

Qdrant (@qdrant_engine) — Thu, 23 Jul 2026 17:19:16 GMT

0.1ms vs 52ms.

That’s what happens when you remove the network.

For robots, drones, wearables, and other edge devices, that’s often the difference between waiting on the cloud and responding immediately.

At Vector Space Day SF, @DylanCouzon demoed Qdrant Edge, running the entire retrieval pipeline locally.

Same retrieval engine. Same API. Same queries.

Just no network hop.

Full talk: youtube.com/watch?v=RRhbOR…

💬1🔄2❤️11👀503📊3

⚡ Powered by xgo.ing

Less than a week away now! Join @DylanCouzon from Qdrant and James Le from @twelve_labs on July 28 ...

Qdrant (@qdrant_engine) — Wed, 22 Jul 2026 14:00:01 GMT

Less than a week away now!

Join @DylanCouzon from Qdrant and James Le from @twelve_labs on July 28 for an evening of AI memory, video intelligence, and retrieval systems in Bellevue, WA.

→ Persistent memory for video AI
→ Collective memory for Edge AI with Qdrant Edge
→ Practical retrieval architectures and live demos

Date: July 28

Place: Bellevue, WA

Register: luma.com/kyksgkak

💬2🔄3❤️8👀540📊4

⚡ Powered by xgo.ing

At Vector Space Day SF, Dave Nielsen from @cognee_ gave an amazing talk on where AI memory is headin...

Qdrant (@qdrant_engine) — Tue, 21 Jul 2026 16:00:00 GMT

At Vector Space Day SF, Dave Nielsen from @cognee_ gave an amazing talk on where AI memory is heading: from simple prompt storage to full knowledge graphs built on the fly, combining RAG, GraphRAG, and short-term memory into one unified layer.

A few things that stood out:

→ @cognee_ builds knowledge graphs automatically, extracting entities and relationships from chats, prompts, agent interactions, and pipelines, storing vectors in @qdrant_engine and graph relationships in @neo4j 

→ AI memory is expanding beyond individual agents to teams and organizations, think onboarding systems that learn from prompts, or shared knowledge bases that grow smarter over time

→ The cognee x Qdrant connector now includes TurboQuant support, and the impact is even bigger for knowledge graphs than regular vector storage, because graph data explodes in size and quantization cuts it down significantly

Full talk is live on our youtube channel: youtube.com/watch?v=UKw6PU…

💬2🔄0❤️12👀497📊4

⚡ Powered by xgo.ing

If you're in Munich this Thursday, we have something for you. BASED Meetup #6 is happening July 23r...

Qdrant (@qdrant_engine) — Tue, 21 Jul 2026 10:22:49 GMT

If you're in Munich this Thursday, we have something for you.

BASED Meetup #6 is happening July 23rd at TNG Technology Consulting. This time it’s a mix of BarCamp and OpenSpace formats: open discussions on search, retrieval, RAG, and everything in between. There won’t be a pre-set agenda, topics will be taken from the room.

Our very own @krotenWanderung from the Qdrant DevRel team is co-hosting, so if you want to talk about vectors, retrieval, or anything search-related with someone from the Qdrant team, this is your chance.

Bring a question, a pain point, something you built, or something that broke in prod, be it:
→ Agentic RAG and memory
→ Production-scale retrieval optimization
→ Modern search quality metrics
→ Multimodal and cross-lingual search
→ ...or whatever you feel fits

Thursday July 23, 6PM - 9PM GMT+2

TNG Technology Consulting, Arabellastraße 4a, Munich

Register here: luma.com/mnh67d5m

See you there!

💬3🔄2❤️10👀624📊5

⚡ Powered by xgo.ing

How do you run vector search at 20B+ vectors across 5 regions for 38 teams? @HubSpot built VAST - V...

Qdrant (@qdrant_engine) — Mon, 20 Jul 2026 16:00:30 GMT

How do you run vector search at 20B+ vectors across 5 regions for 38 teams?

@HubSpot built VAST - Vector as a Service, entirely on Qdrant. 150 clusters, 2K+ pods, 9.5B vectors in a single collection, 5K writes/sec with spikes to 100K.

the real story: they outgrew Helm fast. Helm can't call the Qdrant API to transfer shards, maintain replication factor, or handle state-aware scaling. cluster creation took hours.

so they built a Kubernetes operator specifically for Qdrant. shard management, replication, lifecycle automation, all handled automatically. cluster spin-up: hours → minutes.

result: 65% reduction in resource skew on a 3B+ point BM42 sparse vector collection.

full talk here:
youtube.com/watch?v=46aQff…

thanks Oleg Tereshin and Xin Liu from @HubSpot team, for sharing at Vector Space Day SF 🙌

💬3🔄6❤️17👀804📊7

⚡ Powered by xgo.ing

congrats to @Haystack_AI on 3.0 🎉. If you're building with Haystack 3.0, Qdrant integrates natively...

Qdrant (@qdrant_engine) — Mon, 20 Jul 2026 15:35:20 GMT

congrats to @Haystack_AI on 3.0 🎉. If you're building with Haystack 3.0, Qdrant integrates natively with dense, sparse, and hybrid retrieval. the Haystack team put together a great movie recommendation agent demo showing exactly this pattern with Qdrant:qdrant.tech/course/essenti…8

Haystack@Haystack_AI

Haystack 3.0 is here 🚀

Agents move to the center of the framework:
🤖 Pre-built agents: deep research + advanced RAG, ready out of the box
 🪝 Hooks to control the agent loop
 🧰 First-class skills with progressive disclosure
 📉 A leaner core: we deleted 3 lines for every 1 we added

And this is just Day 1. New drops every day this week at 3 PM CEST.
Full announcemehaystack.deepset.ai/blog/haystack-…p7lEnp

🔗 View Quoted Tweet

💬3🔄4❤️16👀871📊5

⚡ Powered by xgo.ing

Join us for an upcoming webinar on “Why does my RAG-agent get worse? A live autopsy” As collections...

Qdrant (@qdrant_engine) — Mon, 20 Jul 2026 12:20:53 GMT

Join us for an upcoming webinar on “Why does my RAG-agent get worse? A live autopsy”

As collections grow, documents change, chunks get duplicated, and retrieval pipelines evolve, Agent's quality can decline without an obvious breaking point. @DylanCouzon from Qdrant and Rishabh Hada from Future AGI will build, debug, and fix RAG agents through a single end-to-end workflow.

Qdrant powers the retrieval layer, while Future AGI will trace and evaluate the agent throughout the same workflow.

What we’ll cover:
- Build a RAG agent and observe where the agent is losing quality
- Migrate to a new embedding model with zero downtime
- Remove duplicate and fragmented chunks from the collection
- Add late interaction reranking
- Compare evaluation scores before and after each change to verify what actually worked

Date & Time: Thursday, August 6 at 6:30 PM CEST | 9:30 AM PDT | 10:00 PM IST

Register for the webinar now: luma.com/future-pq6q

💬3🔄4❤️11👀799📊6

⚡ Powered by xgo.ing

"Continual learning isn't a training problem. It's a memory problem." @taranjeetio (co-founder & CE...

Qdrant (@qdrant_engine) — Fri, 17 Jul 2026 16:00:01 GMT

"Continual learning isn't a training problem. It's a memory problem."

@taranjeetio (co-founder & CEO, @mem0ai) breaks down why agents need memory before they need retraining at our Vector Space Day conducted in SF.

- Weights = stable, general stuff (skills, reasoning patterns)
- Memory = everything tied to a specific user/team/org -  fast, inspectable, reversible, portable

His 5-step loop for agent memory:
observe → extract → retrieve → act → forget/update

Built on real lessons scaling @mem0ai (open-source memory layer, running on @qdrant_engine under the hood) in production.

Full talk: youtube.com/watch?v=yw-7Of…

💬5🔄1❤️9👀562📊7

⚡ Powered by xgo.ing

If you're building a system for multiple customers or teams and need to keep their data isolated, mu...

Qdrant (@qdrant_engine) — Fri, 17 Jul 2026 10:30:00 GMT

If you're building a system for multiple customers or teams and need to keep their data isolated, multitenancy is what you need.

Pavan put together a great guide on building a scalable multitenant search system with Qdrant and @llama_index.

The guide shows how to:
 → Isolate each customer's data within a single Qdrant collection (yes, you don't need multiple collections)
 → Build secure, payload-filtered retrieval pipelines
 → Implement hybrid search with Qdrant and @llama_index 
 → Scale to many tenants without the overhead of managing hundreds of collections

Read Pavan's article:
 towardsdev.com/scaling-search…

We also have a full guide covering tiered multitenancy, tenant isolation patterns, and performance tuning for your production use cases:
 qdrant.tech/documentation/…

💬4🔄5❤️23👀1266📊10

⚡ Powered by xgo.ing

Don’t forget to join today’s Qdrant Office Hours on Discord! We’ll be having an open discussion, an...

Qdrant (@qdrant_engine) — Thu, 16 Jul 2026 10:44:16 GMT

Don’t forget to join today’s Qdrant Office Hours on Discord!

We’ll be having an open discussion, and we’d love to hear your opinions, feedback, questions, or anything else you’d like to talk about.

We host Office Hours every 3rd Thursday of the month, and going forward, we’ll keep them more discussion-oriented so everyone has a chance to bring up topics they’d like to discuss.

Time: 6:00 PM CEST | 9:00 AM PDT | 9:30 PM IST

Link to the event: discord.gg/pVDGNpjuB?even…

See you there!

💬1🔄0❤️8👀547📊3

⚡ Powered by xgo.ing

Products aren’t one-dimensional, your embeddings shouldn’t be either. Divy Yadav shows how to build...

Qdrant (@qdrant_engine) — Wed, 15 Jul 2026 10:30:00 GMT

Products aren’t one-dimensional, your embeddings shouldn’t be either.

Divy Yadav shows how to build a multi-aspect semantic search engine using Qdrant Multivectors for richer, more relevant e-commerce retrieval.

pub.towardsai.net/multi-aspect-e…

💬1🔄2❤️11👀526📊4

⚡ Powered by xgo.ing

What if your AI could remember your life, completely offline? Satyam Sahu from our community built ...

Qdrant (@qdrant_engine) — Tue, 14 Jul 2026 10:30:00 GMT

What if your AI could remember your life, completely offline?

Satyam Sahu from our community built an offline life memorizer using Gemini 2.0 + Qdrant Edge for private, on-device AI memory and semantic retrieval.

A great example of what’s possible with edge AI and vector search.

pub.towardsai.net/building-an-of…

💬2🔄1❤️5👀422📊3

⚡ Powered by xgo.ing

Our next Qdrant Office Hours is coming up, and we’ve got a great lineup of community demos and discu...

Qdrant (@qdrant_engine) — Mon, 13 Jul 2026 11:45:39 GMT

Our next Qdrant Office Hours is coming up, and we’ve got a great lineup of community demos and discussions!

Date: July 16
Time: 9:30 PM IST | 6:00 PM CEST | 9:00 AM PDT

Here’s what’s on the agenda:
- Qdrant Edge – updates, demos, and discussions.

- How to Implement Multitenant Search in Qdrant
Our Star Kameshwara Pavan kumar Mantha will walk us through building efficient multitenant search with Qdrant.

- Semantic AI Bookmarking with Qdrant
Our Star Mohammed Arbi Nsibi will showcase a Chrome extension he’s been using daily to save and semantically search AI resources.

We’ll also have an open discussion on benchmarking, retrieval quality, and whatever questions the community brings.

Link to register: discord.gg/pVDGNpjuB?even…

See you on July 16!

💬3🔄1❤️5👀501📊5

⚡ Powered by xgo.ing

AI has gotten better at reasoning, but it still forgets almost everything. Join @DylanCouzon from Q...

Qdrant (@qdrant_engine) — Thu, 09 Jul 2026 12:48:02 GMT

AI has gotten better at reasoning, but it still forgets almost everything.

Join @DylanCouzon from Qdrant and James Le from @twelve_labs on July 28 for an evening dedicated to AI memory, video intelligence, and retrieval systems.

Hear from engineers building production AI systems as they cover:
→ Persistent memory for video AI
→ Collective memory for Edge AI with Qdrant Edge
→ Practical retrieval architectures and live demos

Want to showcase your own project?

We’re also hosting community demos, and only 2 demo slots remain!

If you’re building with AI, retrieval, video intelligence, or agentic workflows, we’d love to have you present your work.

📅 July 28
📍 Bellevue, WA
🎟️ Register herluma.com/kyksgkakcGS

See you there!

💬2🔄2❤️12👀690📊4

⚡ Powered by xgo.ing

Benchmark results:

Qdrant (@qdrant_engine) — Wed, 08 Jul 2026 16:27:57 GMT

Benchmark results:

💬1🔄0❤️7👀236📊2

⚡ Powered by xgo.ing

Elastic's benchmark claims Qdrant is 7x slower on disk search. They never enabled the two features b...

Qdrant (@qdrant_engine) — Wed, 08 Jul 2026 16:25:49 GMT

Elastic's benchmark claims Qdrant is 7x slower on disk search. They never enabled the two features built for that workload. We turned them on and found 2x throughput, half the latency, 1/3 the compute.

Read more: qdrant.tech/blog/benchmark…

Elastic@elastic

7x higher vector search throughput at comparable recall.

Elasticsearch 9.4.1 DiskBBQ vs Qdrant 1.18.1, tested on network-attached persistent storage.

The storage topology most K8s and managed-cloud deployments actually run on. Not local NVMe.

The gap is disk access. DiskBBQ searches a compact quantized index and limits full-precision reads. Qdrant rescores against original vectors on disk. On network-attached storage, those random reads get expensive.

Elasticsearch latency: 120 to 150ms across recall levels.
Qdrant: 315ms to 900ms as recall increases.

Benchmark tool, dataset, and configs are all published below.

🔗 View Quoted Tweet

💬4🔄4❤️19👀1701📊7

⚡ Powered by xgo.ing

Most retrieval agents follow the same pipeline for every query. Join us tomorrow to learn how to bu...

Qdrant (@qdrant_engine) — Wed, 08 Jul 2026 14:30:00 GMT

Most retrieval agents follow the same pipeline for every query.

Join us tomorrow to learn how to build retrieval agents that evaluate, adapt, and improve mid-query.

In this live session, you’ll learn how to:
→ Choose the right retrieval strategy for each question
→ Detect weak retrieval early with lightweight signals
→ Route queries using ColBERT reranking and IRCoT query decomposition
→ Build a STOP decision so your agent abstains instead of guessing

📅 Tomorrow, July 9
🕣 8:30 AM PT | 5:30 PM CEST

Register nowluma.com/fdok2snbUn

💬1🔄0❤️13👀537📊3

⚡ Powered by xgo.ing

Qdrant is heading to WeAreDevelopers World Congress! If you’re joining us in Berlin, here’s where y...

Qdrant (@qdrant_engine) — Wed, 08 Jul 2026 09:30:00 GMT

Qdrant is heading to WeAreDevelopers World Congress!

If you’re joining us in Berlin, here’s where you can find the team:

July 9 - The Retrieval Layer for Edge AI

Chadha Sridi and Sasha Denisov will explore how retrieval powers edge AI applications, featuring a live demo of Qdrant Edge running on smart glasses.

July 10 - Workshop: Retrieval Layer in Context Engineering – From Intuition to Production

Join @krotenWanderung for a hands-on workshop where you’ll build the context-engineering layer for a medical AI copilot while learning:
→ Semantic vs. lexical search
→ Hybrid retrieval
→ Knowledge graphs & GraphRAG
→ Context engineering patterns for production AI

July 9–11 - Visit the Qdrant Booth
Stop by throughout the event for live Qdrant Edge demos, chat with the team, and see how lightweight, privacy-first vector search enables modern AI applications.

See you at WeAreDevelopers World Congress! 👋

💬3🔄0❤️13👀574📊5

⚡ Powered by xgo.ing

On-device AI RAG using Qdrant Edge https://t.co/XcDxt0adTQ

Qdrant (@qdrant_engine) — Tue, 07 Jul 2026 14:58:47 GMT

On-device AI RAG using Qdrant Edge x.com/i/broadcasts/1…

💬1🔄1❤️9👀1056📊4

⚡ Powered by xgo.ing

Going live in 15 minutes. Don't forget to join!

Qdrant (@qdrant_engine) — Tue, 07 Jul 2026 14:45:09 GMT

Going live in 15 minutes. Don't forget to join!

Qdrant@qdrant_engine

Join us for today’s Vector Space Talk with @TRJ_0751.

Discover how to build a fully on-device RAG pipeline using Qdrant Edge and Google LiteRT, powering document Q&A, personal assistants, and semantic search without relying on the cloud.

Time: 8:30 PM IST | 5:00 PM CEST | 8:00 AM PDT
Don’t miss this live session!

Join here: streamyard.com/watch/GDNR4Xtj…

See you there!

🔗 View Quoted Tweet

💬1🔄0❤️9👀907📊2

⚡ Powered by xgo.ing

Join us for today’s Vector Space Talk with @TRJ_0751. Discover how to build a fully on-device RAG p...

Qdrant (@qdrant_engine) — Tue, 07 Jul 2026 09:58:57 GMT

Join us for today’s Vector Space Talk with @TRJ_0751.

Discover how to build a fully on-device RAG pipeline using Qdrant Edge and Google LiteRT, powering document Q&A, personal assistants, and semantic search without relying on the cloud.

Time: 8:30 PM IST | 5:00 PM CEST | 8:00 AM PDT
Don’t miss this live session!

Join here: streamyard.com/watch/GDNR4Xtj…

See you there!

💬3🔄2❤️9👀1438📊6

⚡ Powered by xgo.ing

Coming up next week on Vector Space Talks! What if your AI assistant could run entirely on your dev...

Qdrant (@qdrant_engine) — Fri, 03 Jul 2026 13:00:01 GMT

Coming up next week on Vector Space Talks!

What if your AI assistant could run entirely on your device - no cloud, no servers, no internet required?

Join @TRJ_0751 (Founding Engineer at Kaivid Labs & Qdrant Star) as he shows how to build a fully local RAG pipeline using Qdrant Edge and Google LiteRT.

You’ll learn how to build:
→ On-device document Q&A
→ Personal AI assistants
→ Semantic search over your own notes
→ Private, offline AI experiences

Date: July 7
Time: 8:30 PM IST | 5:00 PM CEST | 8:00 AM PDT

Registration Link: streamyard.com/watch/GDNR4Xtj…

💬1🔄0❤️15👀819📊3

⚡ Powered by xgo.ing

Not every query deserves the same retrieval pipeline. Some questions are simple. Others require mul...

Qdrant (@qdrant_engine) — Fri, 03 Jul 2026 07:33:29 GMT

Not every query deserves the same retrieval pipeline.

Some questions are simple. Others require multiple retrieval steps, reranking, or even deciding not to answer at all.

Join our next live webinar to learn how to build retrieval agents that adapt their strategy as they search.

You’ll learn how to:
→ Choose the right retrieval strategy for each query
→ Detect weak retrieval signals early
→ Route queries to techniques like ColBERT reranking and IRCoT query decomposition
→ Build agents that know when to abstain instead of hallucinate

Date: July 9
Time: 8:30 AM PT / 5:30 PM CEST

Register here:
luma.com/fdok2snb

💬0🔄2❤️6👀594📊2

⚡ Powered by xgo.ing

Looking to Build GraphRAG? Start with This Practical Guide from our star, Pavan In this practical g...

Qdrant (@qdrant_engine) — Wed, 01 Jul 2026 10:34:33 GMT

Looking to Build GraphRAG? Start with This Practical Guide from our star, Pavan

In this practical guide, Pavan demonstrates how to build a GraphRAG architecture using LangExtract, @neo4j, Qdrant, and @ollama.

You’ll learn how to:
→ Extract entities and relationships from unstructured text with LangExtract
→ Build a knowledge graph in @neo4j
→ Use Qdrant for semantic retrieval
→ Combine graph traversal with vector search for more context-aware responses
→ Run the entire pipeline locally with @ollama 

If you’re exploring GraphRAG or building production-ready retrieval systems, this is a great walkthrough.

Read the article:
blog.stackademic.com/a-practical-gr…

💬0🔄7❤️62👀4270📊21

⚡ Powered by xgo.ing

"Do we still need (traditional) search engines when AI can do & knows everything?" That was the que...

Qdrant (@qdrant_engine) — Tue, 30 Jun 2026 05:06:22 GMT

"Do we still need (traditional) search engines when AI can do & knows everything?"

That was the question Charlie Hull put to our @krotenWanderung , Atita Arora, Jo Kristian Bergum, and Dmitry Kan at @berlinbuzzwords, and nobody agreed it was time to throw the engines away.

A few moments worth checking out:

[1] Dmitry Kan brutally admitted he closed his laptop for three days after ChatGPT first launched. Just sat there, thinking “it’s over”. Then opened it back up and got on with it, and ever since it’s not even close to “over”, for him & for all the “search” people.

[2] @krotenWanderung named three "old but gold" search techniques she keeps seeing people reinvent in their agentic search pipelines: relevance feedback loops, MMR for result diversity between hops, and crowdsourcing-style sub-agent evaluations. All from decades ago. All suddenly very relevant again.

[3] And Jo said that AI agents are better users of keyword search than humans ever were.

The honest conclusion, as @krotenWanderung put it, "I don't think we solved search. I think everything became even more complicated." But in the best possible way:)

Link to see the full video: youtube.com/watch?v=StaPk0…

💬2🔄0❤️7👀632📊3

⚡ Powered by xgo.ing

Last week, we hosted Vector Space Meetup: Retrieval in the Age of Agents. Our CTO Andrey Vasnetsov ...

Qdrant (@qdrant_engine) — Fri, 26 Jun 2026 08:00:00 GMT

Last week, we hosted Vector Space Meetup: Retrieval in the Age of Agents.

Our CTO Andrey Vasnetsov kicked things off with a look at where Qdrant is heading: storage and compute separation taken to its logical limit - querying only the index fragments you need, on your own device, without a cloud round-trip.

The panel with @cognee_, @Haystack_AI by @deepset_ai, @llama_index, and @n8n_io covered agents in production, evaluation, and the decisions that are hardest to undo. A few honest takes from the room:

Agents won't always choose to run retrieval when you need them to. That's a bigger problem than most people expect.
If you generate your eval dataset and run your LLM-as-a-judge with the same model, you're asking it to grade its own homework.

Thanks to everyone who came and pushed back.

More details and takes in the full recording on our YouTube: youtube.com/watch?v=EEXUuI…

💬2🔄0❤️6👀540📊3