Watch this 60-second video to see how Data Graphs can transform scattered knowledge into structured intelligence. Ask questions of your business information using AI, without compromising your data security. Get in touch here for a demo!
https://t.co/pR4qTcweT6
Why deep graph traversal breaks most engines. How Data Graphs runs deep queries orders of magnitude faster than Neo4j, in a fraction of the memory, and with higher throughput
https://t.co/NSzvFl7q0E
Netflix just published how they built multimodal video intelligence at scale.
Years of work. A dedicated ML organization.
Infrastructure most media companies will never have.
So here’s the better question: do you actually need to build it?
@bitmovin + @datagraphs now deliver this as a managed platform: scene-level AI connected to your rights, talent, and editorial data. Deployable in weeks, not years.
The Netflix gap has defined this industry for a decade. It doesn’t have to anymore.
Full breakdown below.
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: https://t.co/ffyuxltK9b
Most RAG systems use Vector retrieval.
Vector only does half the job.
@qdrant_engine just published a case study on the hybrid Graph RAG architecture we built at Data Graphs.
The agent reads the schema first, then routes:
→ Graph for empirical and relational questions
→ Vector (via Qdrant) for semantic similarity
→ Both in parallel when the prompt demands it
Every answer traces back to its source. No black-box retrieval.
Thanks to our partner Qdrant.
Case study below.
Last week at the @HowieLongShort Spring Huddle, Burke Magnus, Andrew Yaffe, and Alex Michael had a thoughtful conversation about where sports and media are heading.
AI is reshaping how content reaches fans. But it opens a different problem around context, ownership, and commercial intelligence.
That gap is what the industry needs to talk about next.
Data Graphs exists because of this problem.
Book a demo and see it in action.
Context wins.
Not more data. Not another dashboard. Not higher reach.
Context.
When AI actually understands your business - the relationships between your content, your fans, your sponsorships, your rights - everything shifts.
→ Sponsorship becomes provable.
→ Fan experiences become personal.
→ Media becomes reusable.
Our CRO, Donna Esfandiary, is speaking at the invitation-only JohnWallStreet Spring Sports & Media Huddle on April 22nd in NYC - alongside some of the sharpest minds in sports and media:
- Burke Magnus, President of Content at @espn
- Andrew Yaffe, CEO of @DudePerfect
- Alex Michael, Managing Director at LionTree
If you're in the room, come find us. If you're not - let's talk anyway.
#JohnWallStreet #SportsBusiness
Vector search finds what's similar, Knowledge Graphs find what's true. The most powerful private-data AI systems know when to use each.
Read why >
https://t.co/2faiQozmix
See how our AI-powered multi-modal knowledge graph can unlock the full value of sports media by unifying video, sports data, and Agentic AI within a single semantic framework.
Using the IPTC Sports Schema and real Premier League and Champions League footage, it shows how structured sports data, AI video analysis, true hybrid GraphRAG, and contextual rendered views transform raw match footage into an intelligent, explorable knowledge hub.
The result is faster analysis, richer storytelling, deeper fan engagement, and more powerful performance and editorial workflows across any sport.
https://t.co/CnQ5MqDroQ
💥 𝗨𝗻𝗹𝗼𝗰𝗸𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗔𝗜 𝘄𝗶𝘁𝗵 𝗞𝗻𝗼���𝗹𝗲𝗱𝗴𝗲 𝗚𝗿𝗮𝗽𝗵𝘀 If you want to scale your organization’s knowledge with Agentic AI, the killer feature is a cohesive, well-defined knowledge graph schema.
https://t.co/2CbRTIYp8t
Join Data Graphs for a discussion of the @IPTC Sports Schema—developed with key contributions from our team—tomorrow, Thursday, May 15, at the IPTC Spring Meeting 2025 in Juan-les-Pins, in the south of France! @pwilton , Donna Esfandiary, and Silver Oliver will showcase Data Graphs for sports utilizing IPTC standards: a football content graph enriched with action metadata and powered by our GraphRAG AI. See you there!
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 🏋️♂️
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.
https://t.co/QNjVJLyG8k
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!
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.
https://t.co/QNjVJLyG8k
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!