customer_support · workflow
Assembled improves RAG results with Hybrid Search and Reciprocal Rank Fusion
Vector-only search failed to return relevant results for specific keyword queries in customer support, particularly when knowledge bases were uncurated and queries contained short or ambiguous keywords.
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 · Support query submitted
A customer support query arrives and is routed to the issue resolution engine.
Tools used
Retrieval Augmented Generation (RAG)PineconeAlgoliaPostgreSQLS3
Outcome
Hybrid search combining vector and keyword search, merged via Reciprocal Rank Fusion, consistently outperformed more complex methods and enhanced the accuracy and relevance of search outcomes across a diverse customer base.
What failed first
A weighting-based fusion approach was tried first but proved unworkable because similarity score distributions varied widely across customers, making it impossible to determine universal weights.
Results
Volumeenhanced the accuracy and relevance of search outcomes
Source
https://www.assembled.com/blog/better-rag-results-with-reciprocal-rank-fusion-and-hybrid-search
Grounding & classification
Source type: technical build writeup
20 fields verified against source quotes.
knowledge searchragsupport agentknowledge basesupport ticketbuilder submittedfailure mode describedtools describedworkflow describedsoftwareaccuracy improvementtechnical build writeupcustomer supportrag answering