AI IntegrationRAG / Knowledge System4-month engagement

RAG-Based Engineering Knowledge Assistant Connected to Windchill Document Library

An industrial OEM had 12 years of engineering documentation in Windchill that nobody could search. Engineers spent hours looking for past decisions and often redid work that already existed.

Problème

Windchill full-text search returned only metadata matches. The actual content of 600K+ PDF and Office documents was inaccessible. Engineers queried colleagues instead of the system, creating knowledge bottlenecks around senior staff.

Solution

Built a RAG pipeline that indexes Windchill document content into a vector database via the Windchill REST API and Apache Tika for document parsing. Engineers query in natural language and receive answers with citations linking back to source documents in Windchill.

Technologie

Windchill REST API, Apache Tika, OpenAI GPT-4o, text-embedding-3-large, Pinecone vector database, FastAPI backend, React frontend, SAML SSO integration

600K+

Documents indexed

45m→5m

Average document search time

92%

Answer relevance score (UAT)

4 mo

Proposal to production

Discuter d'un projet similaire

Vous travaillez sur quelque chose de similaire ?

Décrivez-nous ce que vous avez. En 30 minutes, nous pouvons vous dire si cela nous correspond et ce que cela impliquerait.

Discuter de votre projet