Weaviate AI Database(@weaviate_io)

It is not often researchers design a new filtered ANN algorithm and also implement it in Weaviate bu...

Weaviate AI Database (@weaviate_io) — Wed, 14 Oct 2026 13:01:44 GMT

It is not often researchers design a new filtered ANN algorithm and also implement it in Weaviate but we are happy when this occurs!

PathSeer, now available in Weaviate 1.40, makes that decision dynamically to improve search without query-specific tuning.

In our benchmarks, PathSeer was the fastest strategy across almost every workload tested, including all six production-like conjunction filters.

It also works with existing HNSW indexes, so you can switch an existing collection without reindexing: 

"filterStrategy": "pathseer"

Read the full breakdown:
weaviate.io/blog/pathseer-…

💬2🔄6❤️16👀972📊7

⚡ Powered by xgo.ing

Going live today 👀 Join Connor Shorten, Ivan Despot & Alexander Ledbetter for a look inside Weavia...

Weaviate AI Database (@weaviate_io) — Wed, 14 Oct 2026 09:00:24 GMT

Going live today 👀

Join Connor Shorten, Ivan Despot & Alexander Ledbetter for a look inside Weaviate’s MCP Ecosystem.

See Weaviate Database + Query Agent MCP in action, plus how Delegance Brokerage built their own MCP server on Weaviate.

⏰ 17:00 CEST / 16:00 BST 

There’s still time to save your spot 👇weaviate.io/webinars/insid…px

💬2🔄6❤️10👀834📊5

⚡ Powered by xgo.ing

There is no "best" embedding model. There's only the best one for your data, your task, and your la...

Weaviate AI Database (@weaviate_io) — Tue, 13 Oct 2026 15:00:08 GMT

There is no "best" embedding model.

There's only the best one for your data, your task, and your latency budget.

If you're still wondering which one to chose, Victoria made a video breaking it down. The short version:

𝗦𝘁𝗮𝗿𝘁 𝘄𝗶𝘁𝗵 𝘆𝗼𝘂𝗿 𝗮𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻, 𝗻𝗼𝘁 𝘁𝗵𝗲 𝗹𝗲𝗮𝗱𝗲𝗿𝗯𝗼𝗮𝗿𝗱. The questions that matter:
• Domain: legal, medical, e-commerce? Specialized models understand the terminology and what matters in it better
• Modality and language: text-only, images, multilingual?
• Task: a model that's strong at retrieval can behave very differently from one tuned for summarization
• Size: bigger models capture more nuance but cost you latency and memory, and can overfit on top of that

𝗧𝗵𝗲𝗻 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗲 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗱𝗮𝘁𝗮. The MTEB leaderboard is a solid starting point for picking a baseline, but scores are self-reported and benchmark data may look nothing like yours (it may even be in the training data).

You don't need much to start - 50 to 100 hand-labeled objects and a few queries with defined relevance judgments. In the blog post's example comparing OpenAI's small and large embedding models on a tiny pastry dataset, the two models tied on average precision and recall (0.5 and 0.58)... while taking turns beating each other on individual queries. Bigger wasn't better. It was just different.

𝗧𝗵𝗲𝗻 𝘁𝗵𝗲𝗿𝗲'𝘀 𝘁𝗵𝗲 𝗼𝗽𝗲𝗿𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝘀𝗶𝗱𝗲. Closed APIs mean rate limits and one more vendor to manage. Self-hosting open-source models means GPUs and maintenance. Weaviate Embeddings removes all this work: models hosted next to your data, no external API calls, no artificial limits on how fast you can embed, and pay-as-you-gyoutube.com/watch?v=djp420…l baselweaviate.io/blog/how-to-ch…ur own data, iterate fweaviate.io/product/embedd…s://t.co/tWcJFd7DAM
Blog: https://t.co/wKz29G62i8
Weaviate Embeddings: https://t.co/BwjEgtX9at

💬3🔄1❤️19👀1159📊7

⚡ Powered by xgo.ing

Your CLAUDE.md tells Claude how to work on a project. It doesn't tell Claude what you actually did t...

Weaviate AI Database (@weaviate_io) — Thu, 08 Oct 2026 14:00:20 GMT

Your CLAUDE.md tells Claude how to work on a project. It doesn't tell Claude what you actually did there.

The feature you added last week. The approach you chose after trying two others. The library you rejected, and why.

That history matters, but Claude Code's notes stay attached to the repo where they were written. Switch repos and the next session starts cold.

We built the 𝗘𝗻𝗴𝗿𝗮𝗺 𝗽𝗹𝘂𝗴𝗶𝗻 𝗳𝗼𝗿 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 to give Claude long-term memory across sessions, codebases, and teams.

Before each answer, it recalls short, relevant memories. Afterward, it saves the exchange asynchronously and extracts what is worth keeping.

There is no "remember this" command. Memory becomes a side effect of normal work.

Read the blog to see how iweaviate.io/blog/engram-fo…:
https://t.co/bubGD4p6mc

💬3🔄3❤️8👀1100📊7

⚡ Powered by xgo.ing

Join Connor Shorten, Ivan Despot, and Alexander Ledbetter for a live look inside Weaviate's MCP Ecos...

Weaviate AI Database (@weaviate_io) — Thu, 08 Oct 2026 12:00:06 GMT

Join Connor Shorten, Ivan Despot, and Alexander Ledbetter for a live look inside Weaviate's MCP Ecosystem!

📅 October 14, 2026 | 17:00–18:00 CEST

See the Weaviate Database and Weaviate Query Agent MCP servers in action, and hear how Delegance Brokerage built their own MCP server on top of Weaviate. 

Save your spot �weaviate.io/webinars/insid…px

💬0🔄4❤️9👀731📊2

⚡ Powered by xgo.ing

A slow query is easy to spot. Explaining 𝘸𝘩𝘺 it's slow is the hard part. The latency could come ...

Weaviate AI Database (@weaviate_io) — Tue, 06 Oct 2026 13:30:11 GMT

A slow query is easy to spot. Explaining 𝘸𝘩𝘺 it's slow is the hard part.

The latency could come from HNSW traversal, resolving a filter, BM25 scoring, compression rescoring, or fetching objects from disk. Each points to a completely different fix.

𝗤𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 𝗶𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 makes that breakdown available for each specific search.

Set 𝗾𝘂𝗲𝗿𝘆_𝗽𝗿𝗼𝗳𝗶𝗹𝗲 in the request metadata and the profile is returned alongside the response, organized by shard and node. The coordinating node collects timings from every shard involved, so distributed queries no longer require manually piecing together logs from multiple nodes.

Consider a shard that takes 48.2ms:

• Vector search: 8.4ms
• Filter resolution: 2.1ms
• Object hydration: 36.8ms

HNSW isn't the bottleneck here. Object hydration is. Blindly increasing compute would miss the problem entirely. Page-cache misses, storage latency, a large result limit, or oversized objects are the more useful places to investigate.

𝗤𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 is generally availableweaviate.io/blog/query-pro…rn more about it in our blog: https://t.co/KczBA52Onp

💬4🔄3❤️9👀951📊6

⚡ Powered by xgo.ing

Weaviate `v1.39.3` includes a fix for a high-severity credential disclosure vulnerability affecting ...

Weaviate AI Database (@weaviate_io) — Thu, 01 Oct 2026 14:30:21 GMT

Weaviate `v1.39.3` includes a fix for a high-severity credential disclosure vulnerability affecting Weaviate's Google-backed modules.

The vulnerability affects `text2vec-google`, `multi2vec-google`, and `generative-google`, where an unvalidated `apiEndpoint` setting could cause Google credentials to be sent to an unintended host.

Users running impacted versions of Weaviate (`< v1.39.3`) should upgrade to `v1.39.3` or later.

Weaviate Cloud and Marketplace customers have already been patched and we have no indication that the vulnerability has been exploited.

Thank you to Syed Anas Mohiuddin for responsibly reporting the issue through our Vulnerability Disclosure Program.

Full details: 
weaviate.io/blog/weaviate-…

💬13🔄1❤️16👀831📊16

⚡ Powered by xgo.ing

Not every search query needs maximum retrieval effort. Connor introduces the new query agent effort...

Weaviate AI Database (@weaviate_io) — Tue, 29 Sep 2026 14:01:56 GMT

Not every search query needs maximum retrieval effort.

Connor introduces the new query agent effort tiers in this video! 👇

Query Agent Search Mode now supports an effort parameter, so you can control how much work the agent puts into each request:

• 𝗺𝗲𝗱𝗶𝘂𝗺
• 𝗵𝗶𝗴𝗵
• 𝘂𝗹𝘁𝗿𝗮𝗵𝗶𝗴𝗵

Higher effort scales computation in two places:

1️⃣ 𝗤𝘂𝗲𝗿𝘆 𝘄𝗿𝗶𝘁𝗶𝗻𝗴: the agent spends longer decomposing the request and translating it into structured searches

2️⃣ 𝗥𝗲𝗿𝗮𝗻𝗸𝗶𝗻𝗴: retrieved documents are evaluated more thoroughly before the final ranking is returned

Test the tiers against your own accuracy, latency, and cost requirements - the right tier depends heavily oweaviate.io/blog/search-mo…ore in this blog:
https://t.co/SsXnBYNNwv

Your browser does not support the video tag.

🔗 View on Twitter

💬9🔄6❤️21👀1521📊15

⚡ Powered by xgo.ing

Relevance is not the same thing as coverage. For the query "japan", standard vector search can retu...

Weaviate AI Database (@weaviate_io) — Thu, 24 Sep 2026 14:25:27 GMT

Relevance is not the same thing as coverage.

For the query "japan", standard vector search can return five highly relevant images that are also near-duplicates of each other.

Hybrid search can hit the same problem when keyword and vector results converge on one dense cluster.

MMR diversity selection reduces that repetition at query time.

It selects results greedily, one at a time, balancing:
• similarity to the query
• similarity to results already selected

With 𝗯𝗮𝗹𝗮𝗻𝗰𝗲=𝟭.𝟬, ranking stays focused on pure relevance. At `balance=0.5`, that first page can spread across Mount Fuji, a train, a monkey, ramen, and torii gates.

MMR is now generally available in Weaviate 1.39 across every 𝗻𝗲𝗮𝗿_* search and hybrid search. It runs entirely at query time, so existing collections need no schema changes or reindexing.

One important caveat: pass 𝗯𝗮𝗹𝗮𝗻𝗰𝗲 explicitly. Its default is 𝟬.𝟬, which prioritizes pure diversity and can wander surprisingly far from thweaviate.io/blog/weaviate-…ttps://t.co/Azo67V9iUy

💬3🔄2❤️15👀1059📊6

⚡ Powered by xgo.ing

Your agent remembers. But does it remember well? Getting memory running takes a few API calls. Maki...

Weaviate AI Database (@weaviate_io) — Wed, 23 Sep 2026 12:56:58 GMT

Your agent remembers. But does it remember well?

Getting memory running takes a few API calls. Making sure it remembers the right things takes a little more thought.

Our new guide walks through four decisions that shape how Engram works in your setup:

• what gets remembered
• how memories are scoped and updated
• which retrieval mode to read them back
• where they belong in the prompt

It uses real outputs and test runs to show what changes when you adjust each one, from filtering out passing noise to keeping dynamic memory from breaking prompt caching.

Read the full guide: weaviate.io/blog/engram-me…

💬5🔄2❤️12👀834📊8

⚡ Powered by xgo.ing

Smaller vectors. Faster imports. Almost no recall drama. Weaviate 1.39 adds 4-bit Rotational Quanti...

Weaviate AI Database (@weaviate_io) — Thu, 17 Sep 2026 15:00:26 GMT

Smaller vectors. Faster imports. Almost no recall drama.

Weaviate 1.39 adds 4-bit Rotational Quantization.

It cuts memory usage while maintaining strong recall, with faster imports and search performance improvements across the RQ family.

This blog covers the SIMD work behind it, how recall holds as datasets scale, and how RQ compares with TurboQuant.

8-bit RQ remains the default in Weaviate Cloud and now imports 16% faster. 

If reducing RAM usage and cost is the priority, 4-bit RQ is now available!

Blog: weaviate.io/blog/4-bit-rot…

💬6🔄6❤️21👀2613📊12

⚡ Powered by xgo.ing

AI memory gets worse when you treat it as an ever-growing pile of chat history. Every turn adds mor...

Weaviate AI Database (@weaviate_io) — Tue, 15 Sep 2026 03:26:00 GMT

AI memory gets worse when you treat it as an ever-growing pile of chat history.

Every turn adds more tokens, slower responses, and more outdated or contradictory information for the model to figure out at query time.

People change their minds. Facts go stale. Eventually you have 50 memories about the same thing, all competing for space in the context window.
@victorialslocum's new video explains how 𝗘𝗻𝗴𝗿𝗮𝗺 handles this differently.

Raw messages are sent to Engram, then asynchronous pipelines:

1️⃣ Extract the facts that matter
2️⃣ Compare them with existing memories
3️⃣ Reconcile contradictions, duplicates, and updates
4️⃣ Store a relevant, pruned set of memories for retrieval

Developers control extraction with 𝗧𝗼𝗽𝗶𝗰𝘀, which are plain-language descriptions of what matters to the application.

Memories are also fully scoped:

• 𝗣𝗿𝗼𝗷𝗲𝗰𝘁-𝘄𝗶𝗱𝗲 for memories shared across a team of humans or agents
• 𝗨𝘀𝗲𝗿-𝘀𝗰𝗼𝗽𝗲𝗱 for memories isolated to an individual
• 𝗨𝘀𝗲𝗿-𝗮𝗻𝗱-𝗽𝗿𝗼𝗽𝗲𝗿𝘁𝘆 𝘀𝗰𝗼𝗽𝗲𝗱 for combinations like `user_id` + `conversation_id`

The video also walks through setting up a basic user-scoped memory project: choose the personalization template, use the default pipeline, create an API key, and manage myoutu.be/kX9IhyltvuQns from the dashboweaviate.io/product/engram…co/zfTEengram.playground.weaviate.io/?utm_source=ch…https://t.co/P4bsqEFCVQ
Demo: https://t.co/Vp9PaG4Vfh

Your browser does not support the video tag.

🔗 View on Twitter

💬12🔄7❤️35👀2050📊21

⚡ Powered by xgo.ing

Is the fastest vector index always the right vector index? HNSW is difficult to beat when an applic...

Weaviate AI Database (@weaviate_io) — Wed, 09 Sep 2026 14:00:36 GMT

Is the fastest vector index always the right vector index?

HNSW is difficult to beat when an application needs the lowest latency and highest query throughput.

But production systems optimise for different constraints:

1. Some need to support very large datasets without keeping the full index in memory.
2. Some are limited by available memory or infrastructure cost.
3. Some change frequently and cannot depend on disruptive full-index rebuilds.

HFresh takes a different approach.

It uses a compact HNSW index to route each query towards the most relevant centroids, then searches compressed postings stored on disk.

Underneath that architecture:

- RQ8 makes centroid vectors approximately four times smaller before overhead.
- RQ1 reduces stored posting-vector data by up to 32 times compared with 32-bit floats.
- Background split, merge, and reassign operations keep the index balanced incrementally.

The result is a disk-based index designed for lower heap usage, controlled query I/O, and large mutable datasets—without periodic full rebuilds.

The choice is not HFresh or HNSW in every situation.

Choose HNSW when peak query performance is the priority. Choose HFresh when memory efficiency matters more than peak throughput.

Read how HFresh works: weaviate.io/blog/hfresh?ut…

💬5🔄10❤️46👀2588📊18

⚡ Powered by xgo.ing

What if you remember exactly what an asset looks like, but not what it was called? Creative teams r...

Weaviate AI Database (@weaviate_io) — Tue, 08 Sep 2026 14:00:39 GMT

What if you remember exactly what an asset looks like, but not what it was called?

Creative teams rarely think in filenames. They remember a mood, a scene, a character, or a half-finished idea from an earlier project.

The archive remembers something else:

`final_FINAL_v7.svg`

`BROLL_NEW2.svg`

`scene_14_USE_THIS.svg`

In the final episode of Building Foundry, we turn that gap into a working search experience. We explore:

1. How to scan a creative archive without moving or renaming the original files.
2. How descriptions, tags, extracted text, and metadata give each asset useful context.
3. How keyword, semantic, and hybrid search support different ways of remembering.

The result is a searchable layer over the archive teams already have.

A search for “white rabbit in a grassy landscape” can retrieve a reference image, a trailer clip, and related landscape assets, even when their filenames describe none of those things.

Read the final episode: weaviate.io/blog/building-…

💬11🔄3❤️20👀866📊15

⚡ Powered by xgo.ing

Filters exclude. Boost reorders. New in Weaviate 1.38, the 𝗕𝗼𝗼𝘀𝘁 𝗔𝗣𝗜 adds query-time rescor...

Weaviate AI Database (@weaviate_io) — Thu, 03 Sep 2026 13:36:06 GMT

Filters exclude. Boost reorders.

New in Weaviate 1.38, the 𝗕𝗼𝗼𝘀𝘁 𝗔𝗣𝗜 adds query-time rescoring when a hard filter is too strict.

Take a search for 𝘆𝗲𝗹𝗹𝗼𝘄 𝗮𝗿𝗺𝗰𝗵𝗮𝗶𝗿: Filtering on 𝗶𝗻_𝘀𝘁𝗼𝗰𝗸=𝘁𝗿𝘂𝗲 removes every out-of-stock result. Boosting the same condition ranks available products higher while keeping other relevant matches in the response.

Boost runs after the primary search and supports:

• filter conditions
• numeric property values
• time decay for recency
• numeric decay around a target value

You can blend up to 20 conditions, adjust how strongly they influence the original relevance score, or use negative condition weights to demote matches without excluding them.

Boost only reorders candidates retrieved by the primary search. The 𝗱𝗲𝗽𝘁𝗵 parameter controls the size docs.weaviate.io/weaviate/searc…

Learn more:  https://t.co/zJgnvVogiK

💬1🔄2❤️9👀780📊3

⚡ Powered by xgo.ing

Skip the evaluation and get a faster, cheaper answer. Or get a precise set of sources that match yo...

Weaviate AI Database (@weaviate_io) — Wed, 02 Sep 2026 13:36:02 GMT

Skip the evaluation and get a faster, cheaper answer.

Or get a precise set of sources that match your answer.

Now you have full control between latency and verifiability.

𝗔𝘀𝗸 𝗠𝗼𝗱𝗲 turns a natural-language question into searches or aggregations across your Weaviate Cloud collections, then generates an answer grounded in the retrieved data.

Previously, the result evaluation step always ran. Now you can customise the behavior of your ask mode run, using 𝗿𝗲𝘀𝘂𝗹𝘁_𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 in Python or 𝗿𝗲𝘀𝘂𝗹𝘁𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 in JavaScript/TypeScript:

- Set it to "𝘯𝘰𝘯𝘦" to retrieve data and generate the final answer. This is the default, faster and cheaper workflow.
- Set it to "𝘭𝘭𝘮" to evaluate the answer against the retrieved context using an additional model call. This retains the sources relevant to or used in the answer, and report possible incompleteness or missing information.

The workflow becomes:

1. Retrieve data
2. Generate an answer
3. Optionally evaluate the answer and refine its sources

Since the evaluation requires an additional LLM call, it adds latency and cost. But it also enables extra fields: 𝘪𝘴_𝘱𝘢𝘳𝘵𝘪𝘢𝘭_𝘢𝘯𝘴𝘸𝘦𝘳 and 𝘮𝘪𝘴𝘴𝘪𝘯𝘨_𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘰𝘯, giving you useful signals about whether the answer is complete and what may still be missing.

You can now choose the right tradeoff for each application: faster responses when source refinement isn't required, or additional evaluation when docs.weaviate.io/query-agent/gu…eness signals matter.

Read the Ask Mode documentation: https://t.co/6Q5aptisKk

💬2🔄3❤️8👀988📊5

⚡ Powered by xgo.ing

We stopped asking PDFs to become text before we searched them. With late-interaction multi-vector r...

Weaviate AI Database (@weaviate_io) — Tue, 01 Sep 2026 12:56:19 GMT

We stopped asking PDFs to become text before we searched them.

With late-interaction multi-vector retrieval, you can embed each PDF page as an image and search the charts, tables, and layouts that text extraction misses.

We tested it on 92 pages of NVIDIA investor decks. A query about automotive revenue retrieved the exact five-quarter bar chart, even though the words "change" and "over time" never appeared on the page.

No OCR. No chunking. Just drag your PDFs into Weaviate Cloud and start asking questions.

See how it works: weaviate.io/blog/charts-ta…

💬1🔄8❤️21👀3980📊10

⚡ Powered by xgo.ing

Weaviate 1.39 is out 🚀 Two search features graduate to GA, plus a preview, one experimental, and a...

Weaviate AI Database (@weaviate_io) — Thu, 27 Aug 2026 15:30:21 GMT

Weaviate 1.39 is out 🚀

Two search features graduate to GA, plus a preview, one experimental, and a much quieter disk:

🎯 𝗕𝗼𝗼𝘀𝘁 𝗔𝗣𝗜 (𝗚𝗔) - nudge results up or down at query time. Nothing gets dropped, things just move in the results as you want them to.

👉 𝗠𝗠𝗥 𝗱𝗶𝘃𝗲𝗿𝘀𝗶𝘁𝘆 𝘀𝗲𝗹𝗲𝗰𝘁𝗶𝗼𝗻 (𝗚𝗔) - stop page one from being the same answer nine times. Works on hybrid and vector search.

🗜️ 𝟰-𝗯𝗶𝘁 𝗥𝗤 (𝗽𝗿𝗲𝘃𝗶𝗲𝘄) - If 8-bit compression was too much for you and 1-bit wasn’t enough, you will love this feature.

🌐 𝗦𝗲𝗮𝗿𝗰𝗵 𝗥𝗘𝗦𝗧 𝗔𝗣𝗜 (𝗲𝘅𝗽𝗲𝗿𝗶𝗺𝗲𝗻𝘁𝗮𝗹) - plain JSON over HTTP. No client, no gRPC, no GraphQL. Handy from a shell script or an edge function.

💾 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗰 𝗛𝗡𝗦𝗪 𝘀𝗻𝗮𝗽𝘀𝗵𝗼𝘁𝘀 - commit logs get cleaned up on their own. Less disk, faster startup, five settings you no longer need to think about.

Also worth knowing: gRPC-Web has been on by default since 1.38.3, so you can reach the gRPC API straightweaviate.io/blog/weaviate-…source on GitHub, or spin up a free cluster on Weaviate Cloud!

Learn more: https://t.co/eIFlQiNqN4

💬3🔄3❤️11👀1258📊6

⚡ Powered by xgo.ing

RAG has a text-shaped bottleneck. Transcripts lose tone. OCR mangles layouts. Captions miss what ha...

Weaviate AI Database (@weaviate_io) — Tue, 25 Aug 2026 15:00:01 GMT

RAG has a text-shaped bottleneck.

Transcripts lose tone. OCR mangles layouts. Captions miss what happens on screen.

Native multimodal RAG skips that text conversion step.

With @GoogleDeepMind's Gemini Embedding 2 and Weaviate, text, images, audio, and video can be embedded in one shared vector space. One query can retrieve a PDF page, an audio chunk, or the right moment in a video.

Use it when the original media carries meaning that text cannot preserve.

If your corpus is pure text, sticking with text embeddings is just fine. They are cheaper, faster, and usually enough.

Explore the carousel and read the full guide with runnable code examples:

weaviate.io/blog/multimoda…

💬1🔄4❤️16👀1187📊5

⚡ Powered by xgo.ing

🔗 Notebooks: - Audio RAG: https://t.co/I7nwA3IVLl - Video RAG: https://t.co/MQSbKCeC5J - Multimoda...

Weaviate AI Database (@weaviate_io) — Tue, 25 Aug 2026 15:00:01 GMT

🔗 Notebooks:

- Audio RAG:github.com/weaviate/recip…l
- Video RAG:github.com/weaviate/recip…J
- Multimodal PDF RAG:github.com/weaviate/recip…o

💬0🔄1❤️2👀238📊1

⚡ Powered by xgo.ing

Better prompts won't fix a broken context pipeline. Reliable agentic RAG depends on controlling ...

Weaviate AI Database (@weaviate_io) — Thu, 20 Aug 2026 16:02:18 GMT

Better prompts won't fix a broken context pipeline.

Reliable agentic RAG depends on controlling 𝘄𝗵𝗮𝘁 𝗶𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗿𝗲𝗮𝗰𝗵𝗲𝘀 𝘁𝗵𝗲 𝗺𝗼𝗱𝗲𝗹, 𝘄𝗵𝗲𝗻 𝗶𝘁 𝗮𝗿𝗿𝗶𝘃𝗲𝘀, 𝗮𝗻𝗱 𝗶𝗻 𝘄𝗵𝗮𝘁 𝗳𝗼𝗿𝗺.

In @victorialslocum’s latest video, she breaks context engineering into 5 interconnected systems:

𝟭. 𝗤𝘂𝗲𝗿𝘆 𝗮𝘂𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻

User input is messy. Rewriting, expanding, or decomposing queries helps translate intent into something your retrieval system can actually use. No retrieval technique can compensate for misunderstood intent.

𝟮. 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹

Chunking creates a real trade-off: small chunks improve precision but lose surrounding meaning, while large chunks add context but consume more of the window. Start with a simple baseline, then benchmark recursive or semantic chunking on representative data.

𝟯. 𝗠𝗲𝗺𝗼𝗿𝘆

Dumping complete conversation history into the prompt creates noise. Long-term memory should live outside the model and only be retrieved when relevant.

It also needs maintenance: pruning stale information, merging duplicates, resolving contradictions, and deliberately forgetting what is no longer useful.

𝟰. 𝗧𝗼𝗼𝗹𝘀

Tool descriptions, argument formats, and tool selection all consume context. Exposing 100 poorly described tools doesn't make an agent more capable. It makes the relevant tool harder to find.

𝟱. 𝗔𝗴𝗲𝗻𝘁𝘀

Agents connect everything together by deciding what to retrieve, which tools to call, what to retain, and how to recover when a step fails.

But they also compound upstream errors. Wrong chunks, stale memories, and malformed tool calls propagate through the entire pipeline.

The model is only one partyoutu.be/sUoNoaatRvU?si…ble agentic RAG comes from engineering how context flows around it.

Watch here: https://t.co/0nxtfBfxZm

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄1❤️6👀937📊6

⚡ Powered by xgo.ing

Most search agents wait for instructions. Ours now reads the room first. The latest update is a bi...

Weaviate AI Database (@weaviate_io) — Tue, 18 Aug 2026 16:01:51 GMT

Most search agents wait for instructions.

Ours now reads the room first.

The latest update is a big one: 𝗶𝗺𝗽𝗿𝗼𝘃𝗲𝗱 𝗳𝗶𝗹𝘁𝗲𝗿𝘀 𝗮𝗻𝗱 𝗱𝗮𝘁𝗮 𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴.

Before performing a search, the Query Agent now explores your data first. This means it builds up a picture of what's actually in your collection - before it even starts searching.

Here's what it now understands automatically:
• 🗂️ All possible values available to filter on
• 🔢 The mean, median, min, and max of numeric properties in your collection

No need to manually describe your data structure or hardcode filter options. The agent figures it out on its own - and uses that understanding to run more precise, refined searches for you.
In practice, this means you can ask something like "show me products priced below average" or "filter by the most common category" and the agent already knows what those values look like in 𝘺𝘰𝘶𝘳 𝘴𝘱𝘦𝘤𝘪𝘧𝘪𝘤 𝘥𝘢𝘵𝘢.

Smarter filtering, better search quality, and less docs.weaviate.io/query-agent?ut…n more about the query agent: https://t.co/22av73EMe0

💬1🔄3❤️11👀1742📊5

⚡ Powered by xgo.ing

Why do creative workflows become harder to search as projects grow? Folders begin with a clear stru...

Weaviate AI Database (@weaviate_io) — Thu, 13 Aug 2026 15:01:52 GMT

Why do creative workflows become harder to search as projects grow?

Folders begin with a clear structure. Tags work when teams have time to maintain them. Keyword search works when everyone uses the same language.

Production rarely stays that tidy.

In Episode 2 of Building Foundry, we explore:

1. Why folder structures become historical records rather than useful maps.
2. Why tagging becomes inconsistent under delivery pressure.
3. Why keyword search fails when people describe the same asset differently.

These problems compound as teams change, archives expand, and project knowledge becomes dependent on the people who remember where everything lives.

The article looks at what retrieval needs to do differently. That means combining semantic similarity, exact keyword matching, and metadata filters instead of relying on one perfect naming system.

Read Episode 2:
weaviate.io/blog/building-…

💬1🔄2❤️7👀845📊3

⚡ Powered by xgo.ing

Query Agent Search Mode now makes the recall-versus-precision tradeoff configurable. Search Mode re...

Weaviate AI Database (@weaviate_io) — Wed, 12 Aug 2026 14:01:12 GMT

Query Agent Search Mode now makes the recall-versus-precision tradeoff configurable.

Search Mode rewrites a natural-language request into one or multiple Weaviate queries, each containing a search query, metadata filters, or both. It then returns the matching Weaviate objects directly.

The new 𝗳𝗶𝗹𝘁𝗲𝗿𝗶𝗻𝗴 argument controls the search strategy:

- "𝘳𝘦𝘤𝘢𝘭𝘭" (default) generates multiple queries spanning different filters and interpretations. Use it when getting relevant results matters more than satisfying each criteria.
- "𝘱𝘳𝘦𝘤𝘪𝘴𝘪𝘰𝘯" generates a single query targeting the most likely interpretation. Use it when every returned result should closely follow the original intent.

Imagine an ecommerce dataset with 𝘤𝘢𝘵𝘦𝘨𝘰𝘳𝘺, 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭, 𝘸𝘢𝘵𝘦𝘳𝘱𝘳𝘰𝘰𝘧, and 𝘱𝘳𝘪𝘤𝘦 fields. For

𝘍𝘪𝘯𝘥 𝘮𝘦 𝘸𝘢𝘵𝘦𝘳𝘱𝘳𝘰𝘰𝘧 𝘳𝘦𝘤𝘺𝘤𝘭𝘦𝘥 𝘱𝘰𝘭𝘺𝘦𝘴𝘵𝘦𝘳 𝘣𝘰𝘰𝘵𝘴 𝘧𝘰𝘳 𝘸𝘪𝘯𝘵𝘦𝘳 𝘶𝘯𝘥𝘦𝘳 $150

The "recall" method might perform a search on 𝘸𝘪𝘯𝘵𝘦𝘳 𝘣𝘰𝘰𝘵𝘴 with filters on 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭, 𝘸𝘢𝘵𝘦𝘳𝘱𝘳𝘰𝘰𝘧 and 𝘱𝘳𝘪𝘤𝘦. Then run backup searches such as 𝘸𝘢𝘵𝘦𝘳𝘱𝘳𝘰𝘰𝘧 𝘳𝘦𝘤𝘺𝘤𝘭𝘦𝘥 𝘱𝘰𝘭𝘺𝘦𝘴𝘵𝘦𝘳 𝘣𝘰𝘰𝘵𝘴 with odocs.weaviate.io/query-agent/gu…e "precision" method would run one query for 𝘸𝘪𝘯𝘵𝘦𝘳 𝘣𝘰𝘰𝘵𝘴 with all filters applied, returning nothing if there is no exact match.

Read the documentation:
https://t.co/sJpK9hkJxQ

💬0🔄3❤️7👀961📊2

⚡ Powered by xgo.ing

Scaling Test-Time Compute is the easiest way to get higher quality outputs from AI systems, but it c...

Weaviate AI Database (@weaviate_io) — Tue, 11 Aug 2026 15:19:47 GMT

Scaling Test-Time Compute is the easiest way to get higher quality outputs from AI systems, but it comes at a cost! ⚖️

How much extra compute you want to trade for quality depends on your application.

Introducing the effort parameter in Search Mode, giving you the power to control this tradeoff!

Choose between “medium”, “high”, and “ultrahigh”.

🚀 Search Mode with ultrahigh effort achieves X nDCG@10 averaged across 5 subsets of the BRIGHT benchmark, improving by Y over medium effort and Z over hybrid search alone.

Learn more in our latest blog post:weaviate.io/blog/search-mo…F

💬2🔄4❤️10👀8443📊8

⚡ Powered by xgo.ing

Your database can now speak MCP. Compatible clients such as Claude Code, Cursor, and VS Code can co...

Weaviate AI Database (@weaviate_io) — Thu, 06 Aug 2026 13:36:01 GMT

Your database can now speak MCP.

Compatible clients such as Claude Code, Cursor, and VS Code can connect directly to `/v1/mcp` on the same port as the REST API, without operating a separate MCP service.

The server exposes four tools:

• 𝘄𝗲𝗮𝘃𝗶𝗮𝘁𝗲-𝗰𝗼𝗹𝗹𝗲𝗰𝘁𝗶𝗼𝗻𝘀-𝗴𝗲𝘁-𝗰𝗼𝗻𝗳𝗶𝗴 to inspect the actual collection config
• 𝘄𝗲𝗮𝘃𝗶𝗮𝘁𝗲-𝘁𝗲𝗻𝗮𝗻𝘁𝘀-𝗹𝗶𝘀𝘁 to list tenants
• 𝘄𝗲𝗮𝘃𝗶𝗮𝘁𝗲-𝗾𝘂𝗲𝗿𝘆-𝗵𝘆𝗯𝗿𝗶𝗱 to run BM25 + vector search
• 𝘄𝗲𝗮𝘃𝗶𝗮𝘁𝗲-𝗼𝗯𝗷𝗲𝗰𝘁𝘀-𝘂𝗽𝘀𝗲𝗿𝘁 to insert or update objects

Agents work with the actual collection configuration and database operations, while Weaviate's existing authentication and tool-specific RBAC remain in control.

The MCP server and write access are disabled independently by dedocs.weaviate.io/weaviate/confi…toggled at runtime without restarting the cluster.

Learn more: https://t.co/SvEwjh9Ijr

💬2🔄4❤️14👀1293📊7

⚡ Powered by xgo.ing

Most AI chat interfaces fail before the first message is even sent. Here's the small but powerful f...

Weaviate AI Database (@weaviate_io) — Wed, 05 Aug 2026 10:07:34 GMT

Most AI chat interfaces fail before the first message is even sent.

Here's the small but powerful fix we just added to the Weaviate Query Agent.

The Query Agent is your AI-powered concierge for data - ask it anything in natural language, and it handles the search, aggregation, and ranking behind the scenes.

The latest addition: 𝗦𝘂𝗴𝗴𝗲𝘀𝘁 𝗤𝘂𝗲𝗿𝗶𝗲𝘀 𝗺𝗼𝗱𝗲.

Instead of waiting for a user to know exactly what to ask, the Query Agent can now generate suggested queries for them.

It works in two ways:
1️⃣ 𝗦𝘁𝗮𝗿𝘁𝗶𝗻𝗴 𝗮 𝗰𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻 - surface relevant questions to help users discover what's possible with your data
2️⃣ 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗶𝗻𝗴 𝗮 𝗰𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻 - suggest natural follow-up questions based on the current conversation context

This is a huge quality-of-life improvement for anyone building chat-style applications on top of their data docs.weaviate.io/query-agent/gu…ggest queries mode for the Query Agent: https://t.co/wljGI6wgij

💬3🔄4❤️6👀1062📊6

⚡ Powered by xgo.ing

HTTP 200 isn't where you stop validating an import. A batch can succeed while individual objects fa...

Weaviate AI Database (@weaviate_io) — Tue, 04 Aug 2026 13:20:53 GMT

HTTP 200 isn't where you stop validating an import.

A batch can succeed while individual objects fail due to rate limits, vectorizer errors, or schema mismatches. Those issues are easy to ignore in a prototype but costly at scale.

A more resilient import pipeline should:

• stream data instead of loading everything into memory
• let the server handle batching and backpressure
• use deterministic UUIDs from stable source keys
• retry only failed objects
• checkpoint progress and dead-letter repeated failures

Deterministic IDs make retries idempotent, so reruns update the same objects instead of creating duplicates.

And server-side batching improves pacing, not correctness. We still need proper error handling.

The illustration shows one data import failure mode. The full post also covers data types, media ingestion, blobHash, multimodal vectorisation, and more.

Learn more: weaviate.io/blog/data-impo…

💬1🔄3❤️9👀846📊4

⚡ Powered by xgo.ing

How much creative work gets recreated simply because nobody can find the original? A designer remem...

Weaviate AI Database (@weaviate_io) — Thu, 30 Jul 2026 15:15:27 GMT

How much creative work gets recreated simply because nobody can find the original?

A designer remembers the mood but not the filename. An editor knows the shot exists but not which project folder contains it. A new team member has no way to reconstruct years of creative context.

These are retrieval problems hiding inside everyday creative workflows.

In the first episode of Building Foundry, we explore:

1. Why filenames and folder structures become less reliable as projects grow.
2. How semantic search can find assets by meaning rather than exact words.
3. Why metadata, embeddings, and vector search work better together.

This is an introduction to a different role for AI in creative work: helping teams rediscover and reuse what they have already produced.

Foundry will eventually turn this idea into a working creative-search prototype using Weaviate. This first article establishes the problem we want to solve.

Read Episode 1: weaviate.io/blog/building-…

💬1🔄1❤️4👀810📊2

⚡ Powered by xgo.ing

Query Agent just got 5-10% better at recall@5. Same cost. Same speed. Nothing you did. Query Agent...

Weaviate AI Database (@weaviate_io) — Wed, 29 Jul 2026 15:00:08 GMT

Query Agent just got 5-10% better at recall@5.

Same cost. Same speed. Nothing you did.

Query Agent now uses OpenAI's new 𝗚𝗣𝗧-𝟱.𝟲 𝗟𝘂𝗻𝗮 𝗮𝗻𝗱 𝗧𝗲𝗿𝗿𝗮 models.

Across some BRIGHT datasets, our internal results show a 5% to 10% boost in recall@5 and a 5% to 7% boost on nDCG@10 . This means the Query Agent is now better at giving you the right results.

For Query Agent users, the upgrade is automatic:

- Better retrieval recall
- No additional cost
- Just as fast as usual

Luna is OpenAI's fastest and most affordable GPT-5.6 model, while Terra provides a balance between capability, speed and cost.

Better models provide better filters, search terms and other search parameters based on your natural language input.

Read more about docs.weaviate.io/query-agent?ut…//t.co/AZWd8a5pTF

💬5🔄4❤️10👀1019📊8

⚡ Powered by xgo.ing

Skip the transcript. Embed and retrieve the audio itself. This notebook shows you how to do it with...

Weaviate AI Database (@weaviate_io) — Tue, 28 Jul 2026 15:00:07 GMT

Skip the transcript. Embed and retrieve the audio itself.

This notebook shows you how to do it with Weaviate and @GoogleDeepMind's Gemini in a few simple steps:

• Split raw audio into overlapping chunks
• Create multimodal embeddings with Gemini Embedding 2
• Store and search the audio in Weaviate
• Retrieve relevant clips using a text or audio query
• Generate answers grounded in the retrieved audio with Gemini 3 Flash

The example uses a recording of Robert Frost's "Birches," but the same approach can be applied to podcasts, interviews, lectures, call recordings, and other audio collections.

Explore the notebook:
github.com/weaviate/recip…

💬1🔄6❤️23👀1096📊7

⚡ Powered by xgo.ing

A bigger context window won't fix a broken agentic RAG pipeline. Long contexts can introduce contra...

Weaviate AI Database (@weaviate_io) — Thu, 23 Jul 2026 16:01:42 GMT

A bigger context window won't fix a broken agentic RAG pipeline.

Long contexts can introduce contradictory information, bury relevant tools, and cause later inputs to be ignored. Every retrieved chunk, tool output, instruction, and conversation turn competes for the model's attention.

This is why production agentic RAG is really a 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 problem: controlling what information reaches the model, when, and in what form.

In our newest Youtube video, @victorialslocum breaks down the five systems that make up an agentic RAG pipeline:

1️⃣ 𝗤𝘂𝗲𝗿𝘆 𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗮𝘁𝗶𝗼𝗻 - translating vague, misspelled, or multipart human input into something retrieval and downstream tools can actually use

2️⃣ 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 - choosing a chunking strategy that balances precision with enough surrounding context. Small chunks can lose meaning; large chunks consume context and produce noisier embeddings.

3️⃣ 𝗠𝗲𝗺𝗼𝗿𝘆 - separating active short-term context from externally stored long-term memory. Dumping the full conversation history into every request just lets stale details compete with current information.

4️⃣ 𝗧𝗼𝗼𝗹𝘀 - giving the model clear descriptions, schemas, and access to the right tools at the right stage. Many tool failures are actually context engineering failures in disguise.

5️⃣ 𝗔𝗴𝗲𝗻𝘁𝘀 - the decision and orchestration layer connecting everything above. Agents can reformulate queries, select tools, evaluate results, and change strategy, but they also compound every upstream context failure.

A better prompt can't repair irrelevant retrieval, contryoutu.be/sUoNoaatRvU?si…ool the model can't find.

The video: https://t.co/M9I9WKbOjL

💬3🔄2❤️11👀902📊6

⚡ Powered by xgo.ing

𝗙𝗶𝗿𝗲-𝗮𝗻𝗱-𝗳𝗼𝗿𝗴𝗲𝘁 𝗺𝗲𝗺𝗼𝗿𝘆 𝗳𝗼𝗿 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀? No block...

Weaviate AI Database (@weaviate_io) — Wed, 22 Jul 2026 15:01:31 GMT

𝗙𝗶𝗿𝗲-𝗮𝗻𝗱-𝗳𝗼𝗿𝗴𝗲𝘁 𝗺𝗲𝗺𝗼𝗿𝘆 𝗳𝗼𝗿 𝗺𝘂𝗹𝘁𝗶-𝗮𝗴𝗲𝗻𝘁 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀?

No blocking. No duplicates. Just continuous learning that works.

When you add data to Engram, pipelines run in the background to:
1️⃣ 𝗘𝘅𝘁𝗿𝗮𝗰𝘁 relevant memories matching your configured topics
2️⃣ 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺 by retrieving existing memories and reconciling them (deduplication, handling preference changes, updating facts)
3️⃣ 𝗖𝗼𝗺𝗺𝗶𝘁 clean, structured memories to Weaviate

But how do you deal with a mutli-agent pipeline where 𝘢𝘭𝘭 𝘵𝘩𝘦 𝘢𝘨𝘦𝘯𝘵𝘴 are adding context to the memory system?

Take a multi-agent RAG system where a main agent handles conversations and a search agent uses specialized tools. A user asks about comedy movies, but the search agent does a text search on "comedy" instead of filtering by genre.

The agent then sends back feedback: "Comedy is a genre, you should filter on the 'genres' property."

The information needed to learn is spread across multiple agents and context windows:
• Task goal: "User asked for comedy movies" (main agent)
• Actions taken: "Called search with near-text query 'comedy'" (search agent)
• Feedback: "Should filter on genres property" (main agent)

Engram's pipeline:

1. Extracts each piece individually using different 𝘁𝗼𝗽𝗶𝗰𝘀 (task_goal, actions_taken, feedback)
2. 𝗕𝘂𝗳𝗳𝗲𝗿𝘀 collect these memories until all pieces arrive
3. 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺 step combines them into a single actionable memory:

"𝘞𝘩𝘦𝘯 𝘢𝘴𝘬𝘦𝘥 𝘵𝘰 𝘧𝘪𝘯𝘥 𝘮𝘰𝘷𝘪𝘦𝘴 𝘰𝘧 𝘢 𝘱𝘢𝘳𝘵𝘪𝘤𝘶𝘭𝘢𝘳 𝘨𝘦𝘯𝘳𝘦 (𝘦.𝘨., 𝘤𝘰𝘮𝘦𝘥𝘺), 𝘺𝘰𝘶 𝘴𝘩𝘰𝘶𝘭𝘥 𝘧𝘪𝘭𝘵𝘦𝘳 𝘰𝘯 𝘵𝘩𝘦 𝘨𝘦𝘯𝘳𝘦𝘴 𝘱𝘳𝘰𝘱𝘦𝘳𝘵𝘺, 𝘯𝘰𝘵 𝘥𝘰 𝘢 𝘯𝘦𝘢𝘳-𝘵𝘦𝘹𝘵 𝘲𝘶𝘦𝘳𝘺."

This memory is now stored in Weaviate and retrieved when starting similar tasks. The agent has actually learned from experience 🔥

Because pipelines run asynchronously, agents can:
• Learn from feedback over time without blocking
• Combine information spread across multiple conversations
• Build up experience that improves future performance
• Maintain clean, reconciled memories instead of noisy duplicates

With Engram, you can configure memories to be:
• 𝗣𝗿𝗼𝗷𝗲𝗰𝘁-𝘄𝗶𝗱𝗲 𝘀𝗰𝗼𝗽𝗲: Agent learns from all users' feedback (trusted teams)
• 𝗨𝘀𝗲𝗿-𝘀𝗰𝗼𝗽𝗲𝗱: Each user gets their own persondocs.weaviate.io/engram?utm_sou…s from their specific usage

Agents can then 𝗹𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗲𝘅𝗽𝗲𝗿𝗶𝗲𝗻𝗰𝗲 and 𝗶𝗺𝗽𝗿𝗼𝘃𝗲 𝗼𝘃𝗲𝗿 𝘁𝗶𝗺𝗲 both individually and across teams, all kept separate and secure through multi-tenancy.

Find more in the docs: https://t.co/pNyS1JJy0R

💬0🔄0❤️5👀686📊1

⚡ Powered by xgo.ing

A slow search query doesn't 𝘁𝗲𝗹𝗹 𝘆𝗼𝘂 𝘄𝗵𝗮𝘁 𝘁𝗼 𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗲. The latency could be co...

Weaviate AI Database (@weaviate_io) — Tue, 21 Jul 2026 16:00:52 GMT

A slow search query doesn't 𝘁𝗲𝗹𝗹 𝘆𝗼𝘂 𝘄𝗵𝗮𝘁 𝘁𝗼 𝗼𝗽𝘁𝗶𝗺𝗶𝘇𝗲.

The latency could be coming from filter evaluation, HNSW traversal, compressed-vector rescoring, BM25 scoring, or reading final objects from disk. Each points to a completely different fix.

Weaviate now has 𝗽𝗲𝗿-𝗾𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 to make that breakdown concrete.

Set one opt-in flag on a search and the timing profile comes back directly on 'response.query_profile'. The coordinating node collects profiles from every participating shard and node, so you get a cluster-wide view in one response.

No restart, latency threshold, waiting for the query to be slow again, or manually stitching together logs across nodes.

𝗪𝗵𝗮𝘁 𝘁𝗵𝗲 𝗽𝗿𝗼𝗳𝗶𝗹𝗲 𝗰𝗮𝗻 𝘁𝗲𝗹𝗹 𝘆𝗼𝘂:

- objects_took is high: object hydration is disk-bound. Check page-cache misses, result limits, or large payloads.
- filters_build_allow_list_took is high: the where filter is expensive. filters_ids_matched helps separate a broad cardinality problem from disk reads.
- vector_search_took is high: inspect HNSW layer timings. Layer 0 normally dominates, with ef, dimensionality, and filter strategy as the relevant tuning levers.
- knn_search_rescore_took is high: compressed candidates are expensive to rescore, potentially because full-precision vectors are being read from disk.

For example, one profile might show:

• 48.2ms total
• 36.8ms reading objects
• 8.4ms in vector search
• 2.1ms building the filter allow-list

The vector index isn't the bottleneck. Tuning HNSW would be a guess. The profile points toward storage, page cache, result limit, or payload size instead.

Slow query logging is still useful for passively catching regressions across a fleet. But when one specific query is slow, profiling gives you the actualweaviate.io/blog/query-pro…
Read thdocs.weaviate.io/weaviate/searc…orbach: https://t.co/ygpB4Eb2l8

Docs: https://t.co/70FsH62A3G

💬1🔄4❤️9👀793📊4

⚡ Powered by xgo.ing

𝗠𝗮𝗻𝗮𝗴𝗲𝗱 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲 𝗼𝗻 𝗗𝗶𝗴𝗶𝘁𝗮𝗹𝗢𝗰𝗲𝗮𝗻 𝗶𝗻 ...

Weaviate AI Database (@weaviate_io) — Thu, 16 Jul 2026 14:00:29 GMT

𝗠𝗮𝗻𝗮𝗴𝗲𝗱 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲 𝗼𝗻 𝗗𝗶𝗴𝗶𝘁𝗮𝗹𝗢𝗰𝗲𝗮𝗻 𝗶𝗻 𝗽𝘂𝗯𝗹𝗶𝗰 𝗽𝗿𝗲𝘃𝗶𝗲𝘄!

DigitalOcean handles the infrastructure around Weaviate:

• Provisioning and security
• Automated daily backups
• Patching and version upgrades
• High availability and storage autoscaling
• Point-in-time cluster forks
• Performance insights and logs in the DigitalOcean Control Panel

It runs the unmodified open-source Weaviate engine (v1.37.1 at launch), so existing Python, JS/TS, Java, and C# clients remain compatible.

Easily spin up a Weaviate cluster without operating idocs.weaviate.io/deploy/install…s or VMs, and get building!

Docs: https://t.co/2uFELXE5k3

💬2🔄3❤️10👀1199📊4

⚡ Powered by xgo.ing

Most AI agents get 𝗱𝘂𝗺𝗯𝗲𝗿 as they learn more. (There's a better way) We just released a demo...

Weaviate AI Database (@weaviate_io) — Tue, 14 Jul 2026 15:00:34 GMT

Most AI agents get 𝗱𝘂𝗺𝗯𝗲𝗿 as they learn more.

(There's a better way)

We just released a demo of 𝗘𝗻𝗴𝗿𝗮𝗺 that shows exactly how intelligent memory management should work.

Tengram.playground.weaviate.io/?utm_source=x&…o/GwVlXXb7Bo

Most agentic chatbots handle memory in one of two broken ways:
• Dump the 𝗲𝗻𝘁𝗶𝗿𝗲 𝗰𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻 𝗶𝗻𝘁𝗼 𝗰𝗼𝗻𝘁𝗲𝘅𝘁 every time (problems: cost, degraded performance, no consistency across conversations)
• 𝗦𝘁𝗼𝗿𝗲 𝗲𝘃𝗲𝗿𝘆 𝗺𝗲𝘀𝘀𝗮𝗴𝗲 for retrieval (problems: noise, contradictions, and facts that changed over time)

𝗘𝗻𝗴𝗿𝗮𝗺 takes a completely different approach: 𝗮𝗰𝘁𝗶𝘃𝗲𝗹𝘆 𝗺𝗮𝗶𝗻𝘁𝗮𝗶𝗻𝗶𝗻𝗴 𝗺𝗲𝗺𝗼𝗿𝗶𝗲𝘀 instead of just piling them up.

As conversations happen, Engram runs asynchronous pipelines in the background that:

1. Extract relevant information matching your configured topics
2. Reconcile new memories with existing ones (handling duplicates, preference changes, evolving facts)
3. Store structured, scoped memories in Weaviate for semantic retrieval

This solves the core problem with naive approaches. Rather than cramming ever-growing context into your LLM (causing degradation, latency, and cost issues) or storing raw conversations (which are noisy and contradictory), Engram actively maintains clean, structured memories that can update or be deleted over time.

The result is agentic chatbots that 𝘢𝘤𝘵𝘶𝘢𝘭𝘭𝘺 improve with each interaction, learning from experience without context pollution.

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄3❤️8👀1015📊4

⚡ Powered by xgo.ing

You've typed the perfect search query and gotten completely useless results. Here's what modern pro...

Weaviate AI Database (@weaviate_io) — Thu, 09 Jul 2026 13:50:08 GMT

You've typed the perfect search query and gotten completely useless results.

Here's what modern product discovery looks like when it actually works.

The Weaviate Playground now has an ecommerce demo, and it's a great example of what you can build with vector search.

𝗪𝗲𝗖𝗼𝗺𝗺𝗲𝗿𝗰𝗲 lets you type a keyword, a mood, or even just a vibe - and it routes your query through BM25, semantic vector search, or a hybrid blend automatically. Results come back with real-time faceted filtering by category, brand, and price.

Each product page also surfaces similar items via near-object vector search. That means the same collection is driving both discovery and recommendation - no extra infrastructure needed.

Here's what's going on under the hood:

1. 𝗞𝗲𝘆𝘄𝗼𝗿𝗱 𝗾𝘂𝗲𝗿𝗶𝗲𝘀 → BM25 ranks results by term frequency and relevance
2. 𝗠𝗼𝗼𝗱/𝘃𝗶𝗯𝗲 𝗾𝘂𝗲𝗿𝗶𝗲𝘀 → vector search finds semantically similar products
3. 𝗛𝘆𝗯𝗿𝗶𝗱 → blends both for the best of both worlds
4. 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝗽𝗮𝗴𝗲𝘀 → near-object search pulls similar items automatically

Ready to build your own? Copy the prompt, spin it up on the 𝗳𝗿𝗲𝗲 𝘁𝗶𝗲𝗿 in Weaviate Cloud, and go from ecommerce.playground.weaviate.io/?utm_source=ch…rce search in minutes.
See the demo here: https://t.co/4YI9kC4MyF

Your browser does not support the video tag.

🔗 View on Twitter

💬0🔄1❤️11👀1642📊3

⚡ Powered by xgo.ing

Most developers pick the wrong search method. We built a demo so you can see exactly why. Our keyw...

Weaviate AI Database (@weaviate_io) — Wed, 08 Jul 2026 13:50:26 GMT

Most developers pick the wrong search method.

We built a demo so you can see exactly why.

Our keyword vs vector search demo in the Weaviate Playground lets you explore and compare all three search types side-by-side on real datasets.

Here's what each search type does:

𝗕𝗠𝟮𝟱 (𝗞𝗲𝘆𝘄𝗼𝗿𝗱 𝗦𝗲𝗮𝗿𝗰𝗵)
• Matches exact words and phrases using TF-IDF-style scoring
• Rarer terms that appear frequently score higher
• Perfect for names, specific phrases, and precise queries
• But... it misses synonyms and related concepts

𝗩𝗲𝗰𝘁𝗼𝗿 𝗦𝗲𝗮𝗿𝗰𝗵 (𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝗦𝗲𝗮𝗿𝗰𝗵)
• Uses dense embeddings to capture meaning
• "Car" and "automobile" match even without shared words
• Understands context and semantic relationships
• But... can sometimes underweight exact lexical matches

𝗛𝘆𝗯𝗿𝗶𝗱 𝗦𝗲𝗮𝗿𝗰𝗵
• Runs both searches in parallel and merges results
• Uses reciprocal rank fusion to combine the best of both
• Gets you strong keyword hits PLUS semantic neighbors
• The best of both worlds for most use cases!

The demo includes multiple datasets - landmarks, movies, science, games, and Pokemon - so you can test queries like "where gladiators used to fight" or "ancient city buried under volcanic ash" and see how each search type performs. Or, simply copy the psearch.playground.weaviate.io/?utm_source=ch…r own data!

See the demo here: https://t.co/UmzVxgGggz

Your browser does not support the video tag.

🔗 View on Twitter

💬3🔄7❤️16👀1370📊10

⚡ Powered by xgo.ing

Most vector database demos show you search. This one shows you how information organizes itself. T...

Weaviate AI Database (@weaviate_io) — Tue, 07 Jul 2026 13:36:03 GMT

Most vector database demos show you search.

This one shows you how information organizes itself.

This newspaper-themed demo in Weaviate Playground showcases vector clustering in action - and it updates every 2 hours with real headlines.

Here's how it works:

𝟭. 𝗛𝗲𝗮𝗱𝗹𝗶𝗻𝗲𝘀 𝗚𝗮𝘁𝗵𝗲𝗿𝗲𝗱
Six news topics polled every 2 hours: general, world, business, technology, sports, and health.

𝟮. 𝗘𝗮𝗰𝗵 𝗦𝘁𝗼𝗿𝘆 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗼𝗼𝗱
Every headline becomes a 1,536-dimensional vector capturing its meaning, not just its words.

𝟯. 𝗦𝘁𝗼𝗿𝗲𝗱 𝗶𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲
Vectors land in a Weaviate collection, searchable by meaning, keyword, or both (hybrid search).

𝟰. 𝗖𝗹𝘂𝘀𝘁𝗲𝗿𝘀 𝗙𝗼𝗿𝗺 & 𝗚𝗲𝘁 𝗡𝗮𝗺𝗲𝗱
The 𝗟𝗲𝗶𝗱𝗲𝗻 𝗮𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺 groups similar headlines into communities - these become the actual "stories" underneath. Then an LLM writes a natural label for each cluster.

𝟱. 𝗗𝗲𝗹𝗶𝘃𝗲𝗿𝗲𝗱 𝘁𝗼 𝘁𝗵𝗲 𝗥𝗲𝗮𝗱𝗲𝗿
One card per story. Readers can tune between semantic and keyword search to explore different angles.

This demo combines vector embeddings, hybrid similarity, and graph-based community detection to automatically discover which headlines are really about the same underlying story.

Plus, the demo includes a copy prompt so you can build it yourself 🔥

This is what vector databases were built for: taking unstructured data (news headlines), understanding meaning (embeddings),chronicles.playground.weaviate.io/?utm_source=ch…tering), and making it searchable (hybrid search).

Check it out in Weaviate Playground 💙
https://t.co/gYhQRlvzRq

💬2🔄4❤️12👀1163📊6

⚡ Powered by xgo.ing

Fraud detection used to be slow, rigid, and blind to novel patterns. Here's what conversational dat...

Weaviate AI Database (@weaviate_io) — Thu, 02 Jul 2026 15:00:15 GMT

Fraud detection used to be slow, rigid, and blind to novel patterns.

Here's what conversational data exploration looks like instead.

Powered by the 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, our fraud detection demo inside the Weaviate Playground shows how natural language questions get turned into structured database queries, complete with filters and aggregations across multiple collections.

Here's what happens under the hood:

1. You ask a plain-English question (e.g., "Which customers have flagged transactions with mismatched shipping addresses?")
2. The Query Agent analyzes your question and determines the exact queries to run
3. It searches across 𝘁𝗵𝗿𝗲𝗲 𝗰𝗼𝗻𝗻𝗲𝗰𝘁𝗲𝗱 𝗰𝗼𝗹𝗹𝗲𝗰𝘁𝗶𝗼𝗻𝘀 simultaneously — Transactions, Customers, and PhoneProducts
4. It applies filters, aggregations, and cross-collection lookups automatically
5. The answer streams back to you in real time

In the demo, you can see the exact queries the Query Agent constructed behind the scenes, and watch how it handles multipart questions that would normally require several manual query steps.

Some of the fraud patterns it surfaces:
• Flagged customers and their transaction history
• Suspicious payment methods
• Mismatched billing and shipping addresses
• Brand-level fraud rates across PhoneProducts

Traditional fraud detection relies on slow, rule-based systems that struggle with novel patterns. This approach lets you explore your data convfrauddetection.playground.weaviate.io/?utm_source=ch…

Try it yourself 👇
https://t.co/pBEiukFD2t

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄5❤️9👀1219📊5

⚡ Powered by xgo.ing

Sometimes the best way to understand search algorithms is to see them in action on the same data. W...

Weaviate AI Database (@weaviate_io) — Wed, 01 Jul 2026 15:00:06 GMT

Sometimes the best way to understand search algorithms is to see them in action on the same data.

We built an interactive demo in the Weaviate Playground to help you explore the differences between 𝗸𝗲𝘆𝘄𝗼𝗿𝗱, 𝘃𝗲𝗰𝘁𝗼𝗿, and 𝗵𝘆𝗯𝗿𝗶𝗱 𝘀𝗲𝗮𝗿𝗰𝗵 - and actually see how each one returns different results!

Here's what makes each unique:

𝗕𝗠𝟮𝟱 (𝗸𝗲𝘆𝘄𝗼𝗿𝗱) 𝘀𝗲𝗮𝗿𝗰𝗵 matches on exact words and phrases using TF-IDF-style scoring. Rarer terms that appear often score higher. It's excellent for names and precise phrases but misses synonyms.

𝗩𝗲𝗰𝘁𝗼𝗿 (𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰) 𝘀𝗲𝗮𝗿𝗰𝗵 uses dense embeddings where similar meanings sit close in high-dimensional space. However, it can underweight exact lexical matches.

𝗛𝘆𝗯𝗿𝗶𝗱 𝘀𝗲𝗮𝗿𝗰𝗵 runs both approaches in parallel and merges the result lists using reciprocal rank fusion or weighted combination. You get strong keyword hits PLUS semantic neighbors in one result set.

The demo gives you different datasets - landmarks, movies, science, games, pokemon - so you can compare all three search types on the same queries and see what each returns.

Or, you search.playground.weaviate.io/?utm_source=ch…t and try it on your own data!

See the demo here: https://t.co/3I6m3y1K38

💬2🔄3❤️25👀868📊8

⚡ Powered by xgo.ing

You searched "cozy fall vibes." The store returned zero results. We built a demo that shows exactly...

Weaviate AI Database (@weaviate_io) — Tue, 30 Jun 2026 15:00:11 GMT

You searched "cozy fall vibes." The store returned zero results.

We built a demo that shows exactly what good search looks like in ecommerce.

It's not just a search bar. Real product discovery needs keywords, semantics, filters, and recommendations all working together.

We built 𝗪𝗲𝗖𝗼𝗺𝗺𝗲𝗿𝗰𝗲 in the Weaviate Playground to show exactly that 🔥

Type a keyword, a mood, or a vibe and it routes your query through:

- 𝗕𝗠𝟮𝟱 keyword search for exact matches
- 𝗩𝗲𝗰𝘁𝗼𝗿 𝘀𝗲𝗮𝗿𝗰𝗵 for semantic, meaning-based results
- 𝗛𝘆𝗯𝗿𝗶𝗱 𝘀𝗲𝗮𝗿𝗰𝗵 for everything in between

Real-time faceted filtering lets you slice results by category, brand, and price instantly. And on every product page, near-object vector search surfaces similar items automatically.

One Weaviate collection powers all of it — search 𝘢𝘯𝘥 recommendations, no extra infrastructure needed.

We have a copy-paste prompt for Cursor, Claude Code, or whatever else you use in our Weaviate Playground so you can easplayground.weaviate.io/?utm_source=ch…Check it out here: https:/ecommerce.playground.weaviate.io/?utm_source=ch…iew the live demo: https://t.co/4YI9kC4MyF

💬2🔄3❤️9👀737📊4

⚡ Powered by xgo.ing

We are so excited to welcome Harneet to our team today! 🎉 Harneet Singh is joining us from Canada ...

Weaviate AI Database (@weaviate_io) — Tue, 30 Jun 2026 11:01:25 GMT

We are so excited to welcome Harneet to our team today! 🎉

Harneet Singh is joining us from Canada as a Security & IT Operations Lead 🧑‍💻

Welcome to Weaviate! 💚

💬2🔄0❤️12👀795📊4

⚡ Powered by xgo.ing

🚀 Weaviate 1.38 is here! Two big capabilities reach general availability in this release — plus a ...

Weaviate AI Database (@weaviate_io) — Thu, 25 Jun 2026 15:00:34 GMT

🚀 Weaviate 1.38 is here!

Two big capabilities reach general availability in this release — plus a faster, simpler path to running replicated clusters at scale.

🧠 HFresh (GA) — our disk-based vector index for billion-scale, constantly-changing data. Low memory, predictable latency, and no periodic full rebuilds.

🤖 MCP Server (GA) — connect LLMs, IDEs, and AI agents directly to Weaviate. In 1.38 you can flip the server (and write access) on or off at runtime — no restart.

🔁 Async replication, everywhere — re-architected to run cluster-wide from a single scheduler, and now on by default for every replicated collection.

⚡ Boost API (preview) — gently promote or demote results at query time, without filtering anything out.

🔎 Nested Object Filtering (preview) — filter on nested object fields with a simple dotted path like cars.make.

…and more: production-ready replica movement, server-side usage guardrails, a new text2vec-digitalocean module, fractional BM25 boosts, and faster startup. 🛠️

👉 Read the full reweaviate.io/blog/weaviate-…vi#Weaviatee#VectorDatabasea#AIa#AIAgentsI#RAGt#MCPA#OpenSourcen#MachineLearningearning

💬3🔄7❤️27👀1796📊9

⚡ Powered by xgo.ing

What happens when your AI remembers you as an engineer, then learns you're CEO? Most systems just s...

Weaviate AI Database (@weaviate_io) — Wed, 24 Jun 2026 14:00:26 GMT

What happens when your AI remembers you as an engineer, then learns you're CEO?

Most systems just store both. Engram does something smarter:

When new information arrives, Engram doesn't just pile it on top of existing memories. It actively reconciles them.

Here's what happens in this case:

1. Engram extracts the new fact: "User has been promoted to CEO"
2. It retrieves related memories from Weaviate, finding "User works as a machine learning engineer"
3. Using an LLM tool call, it determines the appropriate action:
- Rewrite the existing memory: "The user used to work as a machine learning engineer, but has now been promoted to CEO"
- Delete the duplicate new memory to prevent redundancy

The result: no duplicate memories, history is maintained, and the context stays clean.

This is memory as infrastructure. Not just storage, but active maintenance that prevents the ever-growing pile of contradictory facts that would otherwise pollute your agent's context.

Read more about how Engram handles memory reconciliation: weaviate.io/blog/engram-de…

Or get started in the docs: docs.weaviate.io/engram?utm_sou…

💬3🔄2❤️7👀749📊6

⚡ Powered by xgo.ing

Ask "𝘴𝘩𝘰𝘸 𝘮𝘦 𝘤𝘶𝘴𝘵𝘰𝘮𝘦𝘳𝘴 𝘸𝘪𝘵𝘩 𝘮𝘪𝘴𝘮𝘢𝘵𝘤𝘩𝘦𝘥 𝘣𝘪𝘭𝘭𝘪𝘯𝘨 𝘢𝘯𝘥 ...

Weaviate AI Database (@weaviate_io) — Tue, 23 Jun 2026 15:00:44 GMT

Ask "𝘴𝘩𝘰𝘸 𝘮𝘦 𝘤𝘶𝘴𝘵𝘰𝘮𝘦𝘳𝘴 𝘸𝘪𝘵𝘩 𝘮𝘪𝘴𝘮𝘢𝘵𝘤𝘩𝘦𝘥 𝘣𝘪𝘭𝘭𝘪𝘯𝘨 𝘢𝘯𝘥 𝘴𝘩𝘪𝘱𝘱𝘪𝘯𝘨 𝘢𝘥𝘥𝘳𝘦𝘴𝘴𝘦𝘴."

Watch an AI agent write the query, run it, and stream the results back, instantly.

That's exactly what this fraud detection demo in the 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗣𝗹𝗮𝘆𝗴𝗿𝗼𝘂𝗻𝗱 shows.

Using the 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, you ask a plain-English question and it automatically translates it into structured queries with filters and aggregations across three different data collections:

- 🗂 𝗧𝗿𝗮𝗻𝘀𝗮𝗰𝘁𝗶𝗼𝗻𝘀
- 👤 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿𝘀
- 📱 𝗣𝗵𝗼𝗻𝗲𝗣𝗿𝗼𝗱𝘂𝗰𝘁𝘀

No SQL. No query builder. Just natural language.

In the demo you'll see:

1. 𝗙𝗹𝗮𝗴𝗴𝗲𝗱 𝗰𝘂𝘀𝘁𝗼𝗺𝗲𝗿𝘀 𝗮𝗻𝗱 𝘀𝘂𝘀𝗽𝗶𝗰𝗶𝗼𝘂𝘀 𝗽𝗮𝘆𝗺𝗲𝗻𝘁 𝗺𝗲𝘁𝗵𝗼𝗱𝘀 identified instantly
2. 𝗠𝗶𝘀𝗺𝗮𝘁𝗰𝗵𝗲𝗱 𝗮𝗱𝗱𝗿𝗲𝘀𝘀𝗲𝘀 and brand-level fraud rates surfaced automatically
3. 𝗠𝘂𝗹𝘁𝗶𝗽𝗮𝗿𝘁 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀 handled across collections in a single query
4. The exact queries the agent constructed, fully transparent
5. Real-time streamed responses as the agent works

The Query Agent analyses your collection and property descriptions to understand your data, then autonomously determines what to search, what filters to apply and how to aggregate it. It handles multipart questions too. Ask about transactifrauddetection.playground.weaviate.io/?utm_source=ch…uct categories in the same prompt, and the agent breaks it down, runs the appropriate sub-queries, and synthesizes a single coherent response.

Try it yourself in the Weaviate Playground 🔽
https://t.co/AvBmvUMC0J

💬2🔄1❤️7👀733📊4

⚡ Powered by xgo.ing

Most vector database pilots struggle with data ingestion before they even get to search. You build ...

Weaviate AI Database (@weaviate_io) — Thu, 18 Jun 2026 15:00:31 GMT

Most vector database pilots struggle with data ingestion before they even get to search. 
You build a slick retrieval pipeline, it works fine on 1,000 docs… then someone hands you a few million more and you start seeing errors on all sides.

So we decided to cover some of the best practices that could save you a headache or two:

• 𝗦𝗲𝗿𝘃𝗲𝗿-𝘀𝗶𝗱𝗲 �collection.batch.stream://t.co/Fj7K0ObVaM() sets the rate for you; no batch-size tuning, the server handles the import size dynamically. 
• 𝗜𝗱𝗲𝗺𝗽𝗼𝘁𝗲𝗻𝘁 𝗿𝗲𝘁𝗿𝗶𝗲𝘀 — deterministic UUIDs so re-runs never duplicate or double-bill
• 𝗯𝗹𝗼𝗯𝗛𝗮𝘀𝗵 — keep the object embeddings, drop the oversized objects which you are already storing somewhere else (10 TB → a few GB, same search quality)
• 𝗣𝗗𝗙𝘀, 𝗻𝗼 𝗢𝗖𝗥 — just embed the page images with a multimodal model
• 𝗧𝗲𝘅𝘁, 𝗶𝗺𝗮𝗴𝗲, 𝗮𝘂𝗱𝗶𝗼 & 𝘃𝗶𝗱𝗲𝗼 — one collection, one query

Rewritteweaviate.io/blog/data-impo…ree times this quarter? This one's for you 👇

🔗 https://t.co/939ia66tzM

💬0🔄2❤️8👀620📊3

⚡ Powered by xgo.ing

The most requested feature from our community is finally here: Weaviate Cloud access, free ...

Weaviate AI Database (@weaviate_io) — Wed, 17 Jun 2026 16:00:42 GMT

The most requested feature from our community is finally here: Weaviate Cloud access, free 𝘧𝘰𝘳𝘦𝘷𝘦𝘳.

No trial period. No ticking clock. Just full access to Weaviate's vector database, query agent, and memory capabilities, no credit card required.

Whether you're:

- Hacking away on a side project
- Building a proof-of-concept
- Launching a brand-new startup

You can now get started with Weaviate completely free!

A massive thank you to our community for your constant feedback and support. We build for you, and we can't wait to see what you create 💙

Sign uweaviate.io/go/console?utm…BCiRbTGr
Learn more in this blog by @bobvaweaviate.io/blog/weaviate-…67lU19IZ

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄6❤️32👀2873📊11

⚡ Powered by xgo.ing

Everyone talks about RAG and semantic search. But nobody's showing you how to use 𝗴𝗿𝗮𝗽𝗵 ...

Weaviate AI Database (@weaviate_io) — Tue, 16 Jun 2026 15:00:51 GMT

Everyone talks about RAG and semantic search.

But nobody's showing you how to use 𝗴𝗿𝗮𝗽𝗵 𝗮𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀 + 𝘃𝗲𝗰𝘁𝗼𝗿 𝗲𝗺𝗯𝗲𝗱𝗱𝗶𝗻𝗴𝘀 to cluster real-time data streams:

𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 𝗖𝗵𝗿𝗼𝗻𝗶𝗰𝗹𝗲𝘀 is our live newspaper-themed demo in the Weaviate Playground that showcases the power of vector clustering in action!

Every 2 hours, fresh headlines flood into the Weaview Chronicle. Then, the system automatically clusters them into the underlying stories - articles about a policy change, a tech announcement, or a global event all end up together.

The demo fetches reports, embeds them as vectors, then clusters them using:

- 𝗛𝘆𝗯𝗿𝗶𝗱 𝘀𝗲𝗺𝗮𝗻𝘁𝗶𝗰 𝘀𝗲𝗮𝗿𝗰𝗵 - understanding meaning, not just keywords
- 𝗖𝗵𝗮𝗿𝗮𝗰𝘁𝗲𝗿 𝗻-𝗴𝗿𝗮𝗺 𝘀𝗶𝗺𝗶𝗹𝗮𝗿𝗶𝘁𝘆 - catching textual patterns
- 𝗟𝗲𝗶𝗱𝗲𝗻 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆 𝗱𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 - a graph algorithm that identifies clusters of densely interconnected nodes (the reports that belong to the same underlying story)

Vector embeddings can do more than just search. The same techniques powering this demo can cluster customer feedback, organize research papers, group support tickets, or structure any stream of unstructured data.

𝗧𝗿𝘆 𝗶𝘁 𝘆𝗼𝘂𝗿𝘀𝗲𝗹𝗳:
The demo includes a 𝗰𝗼𝗽𝘆 𝗽𝗿𝗼𝗺𝗽𝘁 𝗳𝗲𝗮chronicles.playground.weaviate.io/?utm_source=ch…ld your own version! And with Weaviate Cloud's new 𝗳𝗿𝗲𝗲 𝗳𝗼𝗿𝗲𝘃𝗲𝗿 𝘁𝗶𝗲𝗿, there's no barrier to experimenting 💙

View the demo: https://t.co/En6xZZetih

Your browser does not support the video tag.

🔗 View on Twitter

💬7🔄4❤️35👀2048📊16

⚡ Powered by xgo.ing

𝟳 𝘄𝗼𝗿𝗸𝗶𝗻𝗴 𝗱𝗲𝗺𝗼𝘀. From AI memory to fraud detection - all powered by Weaviate. 𝗢𝘂𝗿 ...

Weaviate AI Database (@weaviate_io) — Thu, 11 Jun 2026 12:55:16 GMT

𝟳 𝘄𝗼𝗿𝗸𝗶𝗻𝗴 𝗱𝗲𝗺𝗼𝘀.

From AI memory to fraud detection - all powered by Weaviate.

𝗢𝘂𝗿 𝗻𝗲𝘄 𝗽𝗹𝗮𝘆𝗴𝗿𝗼𝘂𝗻𝗱 𝗶𝘀 𝗻𝗼𝘄 𝗹𝗶𝘃𝗲, with example projects showcasing everything from search, RAG, agents, memory, and more. Every demo comes with copy-paste prompts so you can start building right out of the box!

𝟭. 𝗘𝗻𝗴𝗿𝗮𝗺 - Persistent memory for AI agents. Watch how facts and summaries are extracted in the background and recalled across conversations.

𝟮. 𝗙𝗿𝗮𝘂𝗱 𝗗𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁 - Ask questions about transactions and products. The Query Agent translates them into structured queries across multiple collections to surface fraud patterns.

𝟯. 𝗪𝗲𝗖𝗼𝗺𝗺𝗲𝗿𝗰𝗲 - Browse, search, and discover products powered by keyword, vector, and hybrid search with real-time faceted filtering and recommendations.

𝟰. 𝗪𝗲𝗮𝘃𝗶𝗲𝘄 𝗖𝗵𝗿𝗼𝗻𝗶𝗰𝗹𝗲𝘀 - A newspaper-themed clustering demo. Reports are embedded and clustered using hybrid semantic search, character n-gram similarity, and Leiden community detection.

𝟱. 𝗩𝗲𝗰𝘁𝗼𝗿 𝗦𝗲𝗮𝗿𝗰𝗵 𝘃𝘀 𝗞𝗲𝘆𝘄𝗼𝗿𝗱 𝗦𝗲𝗮𝗿𝗰𝗵 - Learn the differences between vector and keyword search, and how they compare to hybrid search.

𝟲. 𝗚𝗹𝗼𝘄𝗲 - Skincare recommendation app demonstrating how domain knowledge agents, custom embedding strategies, and vector search create intelligent product recommendations.
playground.weaviate.io/?utm_source=ch…ision-tree agent that picks which tools to run on the fly to query and reason over your Weaviate dweaviate.io/go/console?utm…https://t.co/m3QiEdbI6w
Plus, our new tier means you can starting building FREE forever on Weaviate Cloud. Sign up here: https://t.co/5Hrd8hqkXf

Your browser does not support the video tag.

🔗 View on Twitter

💬1🔄4❤️23👀1159📊8