The Agentic AI data platform. Powered by a breakthrough graph database engine. Data Graphs by @datalanguage
London, UK
Joined January 2021
- Tweets110
- Following221
- Followers340
- Likes70
Data Graphs retweeted
Most "Graph RAG" implementations are vector retrieval with extra steps.
@datagraphs built something different.
Their UK-based knowledge graph platform combines a proprietary graph database engine with Qdrant-powered semantic search, orchestrated by an agentic layer that picks the right retrieval path for each prompt.
The insight from CEO Paul Wilton: vector and graph aren't competitors. They're complementary.
Vector excels at semantic similarity over unstructured content. Graphs excel at empirical queries: negation, date ranges, mathematical operations on connected data. Force one to do the other's job and the system breaks.
What they built:
- Real-time embedding from the graph into Qdrant collections via streaming and queuing
- Schema-first retrieval where the agent pulls the full graph schema before deciding how to query
- Parallel execution across graph queries and vector retrieval, blended for the LLM
- Every answer cited back to source for verifiable provenance
Why Qdrant specifically:
- Hybrid Cloud kept the entire stack inside their own AWS environment
- Payload filtering DSL closely matched their existing OpenSearch patterns, so common metadata structures worked across the graph, OpenSearch, and Qdrant without translation
- Terraform support and infrastructure automation fit their existing CI/CD workflows
18 months in production. Zero significant issues.
The retrieval layer determines the ceiling of your AI's intelligence. Choose the right components. Compose them well.
Full case study: qdrant.tech/blog/case-study-…
Data Graphs retweeted
claude one-shot a UI around a suite of cypher query perf tests - its great for building stuff like this.
It highlighted the comparison with "OtherDB" (industry leading graph db that we measure against 😉) ... made me laugh so i made myself a motivational poster 🏋️♂️
Data Graphs retweeted
Checkout this awesome blog post by @charliefurniss3 on building a Knowledge Graph of Wine from the X-Wines dataset, and using GraphRAG AI to analyse it.
datagraphs.com/blog/explorin…
We ingested 100k wines from 30k global producers into Data Graphs, applying the principles of domain-driven design.
With the AI running over the graph we have created an expert-system for Wine enthusiasts. Astonishing results from Charlie. Many thanks to Rogério Xavier de Azambuja for granting use of his incredible data!
Data Graphs retweeted
A look at the Graph RAG AI in Data Graphs.
Our friends at @w42st use Data Graphs to power their hyperlocal media brand that celebrates Hell’s Kitchen in New York through high-quality data journalism.
This demo shows how we can move from structured, high quality intelligence, to being able to ask questions directly from their knowledge graph using AI.
Data Graphs retweeted
Super excited to announce Donna Esfandiary has joined Data Language as our new Chief Revenue Officer. Donna brings extensive experience scaling SaaS companies, driving global sales and marketing, and building strategic partnerships. Let's go !
datalanguage.com/news/donna-…
Data Graphs retweeted
The new #knowledgegraph query builder in @datagraphs is so easy you can build a Cypher/GQL query with no knowledge of the language. It is so insanely fast results appear in realtime as you go. You can try it yourself with a free trial here:
datagraphs.com?utm_source=tw…
#graphdatabase #gql #cypher
Data Graphs retweeted
A new @datagraphs feature is live and its a game changer!
We recently completely rewrote our Data Graphs Cypher Query engine from the ground up. We threw away the book on graph-querying. A new algorithm for ultra-efficient processing of GQL and Cypher graph queries, and its really fast.
Benchmarked at 110x faster than Neo4j on average and 518x faster on the deepest / most complex benchmark query (1 sec vs 9 mins). More info and full benchmark data in the blog.
Get in touch if you want a demo!
#graphdatabase #knowledgegraph
datalanguage.com/blog/data-g…
Data Graphs retweeted
The Data Language Graph RAG Hack 2024 has kicked off today at our London office!
Over the next few days the whole DL team are exploring building Retrieval Augmented Generative AI directly into our @datagraphs #knowledgegraph
It's going to be mega !
Data Graphs retweeted
We're demo-ing Data Graphs using the new IPTC Sport Model at #KGC2024 today, showing how we remove the biggest pitfalls in knowledge graph project delivery.
Don't let daunting setups, complex data engineering, or difficult frameworks hold you back.
youtube.com/watch?v=PfmoPq44…
Data Graphs retweeted
How to use the new @IPTC Sport Model in Data Graphs - hot off the press from #kgc2024 demo sessions:
datagraphs.com/iptc-sport-mo… #knowledgegraph #sportsdata
Data Graphs retweeted
See how easy it is to load an #RDF #ontology into Data Graphs and start working with it minutes. Here is a quick demo using the Cochrane PICO ontology for evidence-based healthcare.
datagraphs.com?utm_source=tw…
#kgc #kgc24 #knowledgegraph #graphdatabase
Data Graphs retweeted
Data Graphs is a model centric #knowledgegraph. It means you really can't mess it up and create data chaos. Even simple inferencing is dead easy. See how easy it is to make inverseOf property inferences in your graph.
datagraphs.com?utm_source=tw…
#kgc2024 #kgc #linkeddata #graphdatabase
Data Graphs retweeted
We're at #DAMNY, demonstrating how knowledge graphs can increase ROI on video assets, alongside traditional DAM deployments.
datalanguage.com/news/data-l…
#DAMNY #knowledgegraphs
Data Graphs retweeted
Building a Content Graph with @datagraphs now lets you visually create video moments and connect them to your #knowledgegraph metadata.
You can capture key-frames easily, semantically tag the moments, and super-charge your video SERPs
#DAMNY
Data Graphs retweeted
This week we will be demo-ing Content Graphs at @henrystewartdam DAM conference in NYC.
Come and find us at Stand 18 to witness metadata magic.
#DAMNY #contentgraph #knowledgegraph
Data Graphs retweeted
What is the current status of Modigliani's Seated Man with Cane?
The provenance story evolved over time, thanks in part to the journalists investigating the Panama Papers and in part to the lawsuit.
What is known today?
Data Graphs retweeted
Provenances written AFTER restitution of looted artworks are especially valuable.
They give a good picture of the networks of people involved in looting and in laundering the looted artworks through "legitimate" sales.
A mix of Red Flag names and others.
#knowledgegraph #pattern
ALT This painting was taken by agents of the German Embassy in Paris on 10 July 1940 from the apartment of Mrs. Fernand Halphen. The Paris dealer, Raphael Gerard, acquired the painting shortly thereafter and sold it to a German businessman, Waldemar Strenger. In May 1948, thanks to an introduction by Adolf Wuester, Strenger met Otto Gerson in Munich and sold him the painting in May 1948. It arrived in New York shortly after May 18, 1948, and was then sold to the Detroit Institute of Arts. https://www.errproject.org/jeudepaume/card_view.php?CardId=52795
Data Graphs retweeted
Once a false #provenance for a Nazi-looted artwork has been traced back to an author, #KnowledgeGraphs can help link up the OTHER cases of Nazi-looted art where the same author (or dealer) played a similar role. And to flag their unreliability as sources of information.
#methods
Data Graphs retweeted
If you're tired of low quality and inconsistent tagging in your business, get our Auto-Tagging Playbook for FREE by signing up at the link below.
Avoid making costly mistakes by using this playbook which is based on 13 years of experience in Auto-Tagging for clients like BBC, SKY, and the UK Government.
Click here to get your playbook now: tagmatic.io/the-autotagging-…
#autotagging #contentclassification #textclassification #llm #llms #chatgpt
