#text2cypher
Over the past months, we've been exploring text2cypher agentic flows with @llamaindex.bsky.social . The result? A comprehensive repository featuring multiple @neo4j.bsky.social workflows, a benchmarking framework, and an web UI.

www.llamaindex.ai/blog/buildin...
January 15, 2025 at 6:38 PM
I'm learning @llamaindex.bsky.social workflows by implementing an advanced @neo4j.bsky.social text2cypher agent. I'm quite impressed by the ease of implementing various, optionally concurrent, flows.
December 10, 2024 at 12:52 PM
Fixed this slide 😅 (und danke für den Einblick hinter die text2cypher Kulissen)
November 6, 2024 at 2:35 PM
Have you ever wondered how well #LLMs handle natural language to #Cypher query conversion across different languages?
+
Text2Cypher Across Languages: Evaluating Foundational Models Beyond English - Graph Database & Analytics
Explore how question language affects model performance on the Text2Cypher task using a multilingual test set with shared Cypher queries.
bit.ly
July 25, 2025 at 3:07 PM
Neo4j Text2Cypher: Analyzing Model Struggles and Dataset Improvements
bit.ly/41YXUGO

#Text2Cypher
Neo4j Text2Cypher: Analyzing Model Struggles and Dataset Improvements - Graph Database & Analytics
Check out key areas where Text2Cypher baseline and fine-tuned models struggle and learn about improvements.
bit.ly
March 12, 2025 at 5:44 PM
Try out the @neo4j.bsky.social JDBC driver I wrote that has both an artisanal coded module translating #SQL to #Cypher and a #text2cypher module.

And ofc 1 based indexes 😅
February 8, 2025 at 11:21 AM
#SQL walks into a bar: "Hey #Cypher, can I join you?"
Slides of my talk about the all new #Neo4j #JDCB driver with both optional SQL to cypher and text2cypher ("Something with AI") from #WJAX 2024.

speakerdeck.com/michaelsimon...
November 6, 2024 at 2:05 PM
We introduce NatureKG, the first ontology and instantiated knowledge graph (KG) specifically tailored to nature finance, designed to support financial institutions in systematically assessing environmental risks, impacts, and dependencies.

www.frontiersin.org/journals/art...
Frontiers | NatureKG: an ontology and knowledge graph for nature finance with a Text2Cypher application
IntroductionNature finance involves complex, multi-dimensional challenges that require analytical frameworks to assess risks, impacts, dependencies, and syst...
www.frontiersin.org
December 5, 2025 at 9:12 AM
threadreaderapp.com/thread/16954...

We now have the most comprehensive cookbook on building LLMs with Knowledge Graphs (credits @wey_gu).
✅ Key query techniques: text2cypher, graph RAG
✅ Automated KG construction
✅ vector db RAG vs. KG RAG

docs.llamaindex.ai/en/latest/op...
November 24, 2024 at 4:32 PM

✨Intermediate GraphRAG patterns:
Cypher Templates (catalog)
Dynamic Cypher Generation (catalog)
Text2Cypher (catalog)
GraphRAG Field Guide: Navigating the World of Advanced RAG Patterns
Explore advanced GraphRAG retrieval patterns and how graph structures enhance RAG systems. Learn actionable strategies to implement and optimize GraphRAG.
bit.ly
December 12, 2024 at 5:08 PM
After all this time, what if the XML people were right!?!? There's text2SQL, text2Cypher, even text2SPARQL. Turns out we may need some text2XQuery!
May 3, 2026 at 7:46 PM
Building natural language interfaces on graphs?

The way you represent your schema can make or break your #Text2Cypher performance. ✨

In this detailed guide, Makbule Gulcin Ozsoy shows how smarter schema design boosts query accuracy, reduces token bloat, and cuts LLM costs:

bit.ly/4jPiOPq
The Impact of Schema Representation in the Text2Cypher Task - Graph Database & Analytics
Learn the impact of different schema formats on the Text2Cypher task, how to achieve them, and why they matter.
bit.ly
August 20, 2025 at 8:38 PM
Turn natural language questions into valid #Cypher queries more reliably: even when the first pass fails! The process? A loop of verification + correction, repeated until a correct query emerges.

Explore this process! https://bit.ly/4pYpvlu

#Neo4j
Explore Iterative Refinement for Text2Cypher - Graph Database & Analytics
Explore an iterative verification and correction refinement process aimed at improving Text2Cypher performance.
bit.ly
October 8, 2025 at 2:35 PM
Effortless RAG With Text2CypherRetriever
Excited to introduce the Text2CypherRetriever!
Are you an experienced #Neo4j user or just getting started? Don't worry: the Text2CypherRetriever can significantly streamline your development process.

Take a look: bit.ly/3AQEVn3
#Text2Cypher
Effortless RAG With Text2CypherRetriever
Retrieve data from Neo4j using natural language with the Text2CypherRetriever, simplifying query generation for GenAI applications.
bit.ly
December 13, 2024 at 10:10 PM
I'll speak about #Neo4j and AI (well, actually, about #JDBC and an experiment we conducted with natural language to query language, here, #text2cypher) next week at #jaxcon Munich and my dear colleagues even created this card…
October 31, 2024 at 4:46 PM
makes smaller, high-quality datasets essential for reducing costs for the same or better performance. In this paper, we propose five hard-example selection techniques for pruning the Text2Cypher dataset, aiming to preserve or improve performance while [3/4 of https://arxiv.org/abs/2505.05122v1]
May 9, 2025 at 5:55 AM
Исследование Text-to-Cypher: Интеграция Ollama, MCP и Spring AI

Когда подходы "текст в запрос" (в частности, text2cypher) только появились, я был несколько неуверен в их полезности, особенно учитывая, что существующие модели давали неточные результаты. Было бы сложно обосновать…

#ai #llama #ollama
Exploring Text-to-Cypher: Integrating Ollama, MCP, and Spring AI
dzone.com
September 24, 2025 at 6:28 AM
Thread by llama_index: We now have the most comprehensive cookbook on building LLMs with Knowledge Graphs (credits wey_gu); Key query techniques: text2cypher, graph RAG; Automated KG construction; vector db RAG vs. KG RAG; Check out the full 1.5 hour tutorial
threadreaderapp.com/thread/16954...
Thread by @llama_index on Thread Reader App
@llama_index: We now have the most comprehensive cookbook on building LLMs with Knowledge Graphs (credits @wey_gu). ✅ Key query techniques: text2cypher, graph RAG ✅ Automated KG construction ✅ v...
threadreaderapp.com
August 26, 2023 at 5:13 PM
Google Cloud + Neo4j = Powering the next generation of AI and cloud innovation 🤩

We are happy to announce:

+
Google Cloud & Neo4j: Teaming Up at the Intersection of Knowledge Graphs, Agents, MCP, and Natural Language Interfaces - Graph Database & Analytics
We’re thrilled to announce new Text2Cypher models and Google’s MCP Toolbox for Databases from the collaboration between Google Cloud and Neo4j.
bit.ly
April 10, 2025 at 5:25 PM
A great KG-RAG demo. Media supply chain, 53K rights records, Text2Cypher with auto-repair, all local via docker compose. The modeling insight: rights and deliveries as nodes carrying state. The graph as process, not taxonomy.

chuan-zhang.medium.com/knowledge-gr...
Knowledge Graphs in RAG: A Realistic Demo with Neo4j
Retrieval-Augmented Generation (RAG) is one of the most practical ways to make large language model applications more reliable. Instead of…
chuan-zhang.medium.com
July 24, 2026 at 5:00 PM
Exploring Text-to-Cypher: Integrating Ollama, MCP, and Spring AI

When text-to-query approaches (specifically, text2cypher) first entered the scene, I was a bit uncertain how it was useful, especially when existing models were hit-or-miss on result accuracy. It would be hard to …

#ai #llama #ollama
Exploring Text-to-Cypher: Integrating Ollama, MCP, and Spring AI
When text-to-query approaches (specifically, text2cypher) first entered the scene, I was a bit uncertain how it was useful, especially when existing models were hit-or-miss on result accuracy. It would be hard to justify the benefits over a human expert in the domain and query language. However, as technologies have evolved over the last couple of years, I've started to see how a text-to-query approach adds flexibility to rigid applications that could previously only answer a set of pre-defined questions with limited parameters.
dzone.com
September 20, 2025 at 7:59 PM
Makbule Gulcin Ozsoy: Adaptive Test-Time Inference for Text2Cypher with Trace Budgeting and Selective Refinement https://arxiv.org/abs/2609.02324 https://arxiv.org/pdf/2609.02324 https://arxiv.org/html/2609.02324
September 3, 2026 at 6:42 AM
利用大型语言模型优化Text2Cypher输出,助力图谱RAG技术发展

https://qian.cx/posts/0E7B6C81-3B4A-4097-9FB4-AB73B3DA2229
October 28, 2025 at 11:32 AM
Makbule Gulcin Ozsoy and Will Tais analyze this in a blog where they shared a detailed evaluation to understand how the input language affects the quality of the generated Cypher queries- this test was made in English, Spanish, and Turkish, and the results might surprise you...

bit.ly/45mognS
Text2Cypher Across Languages: Evaluating Foundational Models Beyond English - Graph Database & Analytics
Explore how question language affects model performance on the Text2Cypher task using a multilingual test set with shared Cypher queries.
bit.ly
July 25, 2025 at 3:07 PM
2️⃣ A joint collaboration that enhances Google’s MCP Toolbox for Databases, empowering developers to build agentic applications that seamlessly integrate diverse database tools, including those powered by Neo4j.

We are at #GoogleCloudeNext, come to our booth for a conversation and some demos!
Google Cloud & Neo4j: Teaming Up at the Intersection of Knowledge Graphs, Agents, MCP, and Natural Language Interfaces - Graph Database & Analytics
We’re thrilled to announce new Text2Cypher models and Google’s MCP Toolbox for Databases from the collaboration between Google Cloud and Neo4j.
bit.ly
April 10, 2025 at 5:25 PM