500+ hours of books you can question

A conversational assistant over books, podcasts and documents that answers with its sources and speaks in the author's voice.

Client
Oracle Knowledge
Industry
Publishing & Media
What we built
RAG-Powered Knowledge Assistant
Timeline
14 weeks
Team
2 engineers
500+
Hours of Content in the Knowledge Base
50+
Questions Answered per Day
Virtual Persona
Voice & Communication Style
6
Content Agents
RAG-Powered Knowledge Assistant for Oracle Knowledge

The challenge

Conversational AI assistant that processes books, podcasts, and documents to provide intelligent knowledge retrieval and content generation.

  • Processing diverse content formats (books, podcasts, documents)
  • Building conversational interface for knowledge retrieval
  • Implementing RAG system for accurate responses
  • Creating content generation workflows

What we built

RAG-Powered Knowledge Assistant.

  • Built 6 specialized content processing agents
  • Implemented advanced RAG with semantic search
  • Created a complete virtual persona matching the author's communication style, with audio responses
  • Developed content generation with source attribution

Built with

  • Python
  • FastAPI
  • React
  • LangGraph
  • OpenAI
  • Pinecone

Start with one process.

The report your team dreads building, or the approval that sits in an inbox for days. Tell us about it and a senior engineer tells you whether it can be automated and what it would take.

Email social@deepbluecoding.com
We reply within one working day.