RAG with Knowledge Graphs reduces median customer service issue resolution time by 28.6% at LinkedIn
Conventional RAG for customer service treated historical issue tracking tickets as plain text, discarding intra-issue structure and inter-issue relations. Text segmentation further disconnected related content such as a ticket's problem description and its solution, degrading both retrieval accuracy and answer quality.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · KG construction from historical tickets
The system constructs a comprehensive knowledge graph from historical customer service issue tickets, retaining intra-issue structure and inter-issue relations.
Tools used
LLMGPT-4BERTE5QdrantNeo4j
Outcome
The KG-augmented RAG system outperformed the baseline by 77.6% in MRR and by 0.32 in BLEU. Deployed at LinkedIn's customer service team, the system reduced median per-issue resolution time by 28.6%, with mean resolution time dropping from 40 hours to 15 hours.
What failed first
The baseline embedding-based retrieval approach lost structural ticket relationships by compressing documents into plain-text chunks, and text segmentation split tickets such that problem descriptions and their solutions appeared in separate chunks, causing incomplete answers.