krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-06 11:28:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update case-study-lettria-v2.md

Browse Source
This commit is contained in:
daniel-azoulai
2025-06-16 20:37:43 -07:00
parent 46a9acd942
commit 55493e2be1
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/blog/case-study-lettria-v2.md
+2 -2
View File
@@ -1,6 +1,6 @@
---
draft: false
title: "Scaled Vector + Graph Retrieval: How Lettria Unlocked 20% Accuracy Gains with Qdrant and Neo4j"
title: "Scaled Vector & Graph Retrieval: How Lettria Unlocked 20% Accuracy Gains with Qdrant and Neo4j"
short_description: "Lettria sees 20% accuracy increase by blending Qdrant's vector search and Neo4j's knowledge graphs."
description: "Discover how Lettria combined Qdrant and Neo4j to overcome the accuracy limitations of traditional vector-only RAG systems, significantly boosting precision, explainability, and performance in regulated industries like pharma, legal, and aerospace."
preview_image: /blog/case-study-lettria/social_preview_partnership-lettria.jpg
@@ -67,7 +67,7 @@ The challenge arises in concurrent environments where multiple ingest processes
*Pseudocode example: ingest_graph_attempt*
```py
def ingest_graph_attempt(graph_data, qdrant, neo4j):
def ing est_graph_attempt(graph_data, qdrant, neo4j):
"""
Attempts to ingest graph data into Qdrant and Neo4j consistently.
If Neo4j write fails, Qdrant changes are rolled back.