👏 Bagrat Ter-Akopyan, Carmen Heger and team. Congrats and thanks for the nice technical write-up.

👏 Bagrat Ter-Akopyan, Carmen Heger and team. Congrats and thanks for the nice technical write-up. It’s amazing to see how you continue to innovate on behalf of your customers. I love the outcome.

📖 What stands out for me from your technical report is your description of the why and how you moved away from your own, already very good, initial RAG implementation. Citing from the report:

“𝘖𝘯𝘦 𝘰𝘧 𝘰𝘶𝘳 𝘭𝘦𝘢𝘳𝘯𝘪𝘯𝘨𝘴 𝘧𝘳𝘰𝘮 𝘵𝘩𝘦 𝘭𝘢𝘴𝘵 𝘣𝘪𝘨 𝘙𝘈𝘎 𝘱𝘳𝘰𝘫𝘦𝘤𝘵 𝘸𝘢𝘴 𝘵𝘩𝘢𝘵 𝘸𝘦 𝘯𝘦𝘦𝘥𝘦𝘥 𝘵𝘰 𝘴𝘱𝘦𝘦𝘥 𝘶𝘱 𝘰𝘶𝘳 𝘦𝘹𝘱𝘦𝘳𝘪𝘮𝘦𝘯𝘵𝘢𝘵𝘪𝘰𝘯 𝘤𝘺𝘤𝘭𝘦𝘴. 𝘖𝘯 𝘵𝘩𝘦 𝘵𝘦𝘤𝘩𝘯𝘪𝘤𝘢𝘭 𝘴𝘪𝘥𝘦, 𝘵𝘩𝘢𝘵 𝘮𝘦𝘢𝘯𝘵 𝘶𝘴𝘪𝘯𝘨 𝘮𝘰𝘳𝘦 𝘰𝘧𝘧-𝘵𝘩𝘦-𝘴𝘩𝘦𝘭𝘧 𝘴𝘰𝘭𝘶𝘵𝘪𝘰𝘯𝘴 𝘧𝘰𝘳 𝘙𝘈𝘎 𝘢𝘳𝘤𝘩𝘪𝘵𝘦𝘤𝘵𝘶𝘳𝘦𝘴 𝘵𝘩𝘢𝘵 𝘩𝘢𝘷𝘦 𝘣𝘦𝘤𝘰𝘮𝘦 𝘢𝘷𝘢𝘪𝘭𝘢𝘣𝘭𝘦 𝘢𝘯𝘥 𝘳𝘦-𝘶𝘴𝘪𝘯𝘨 𝘰𝘶𝘳 𝘰𝘸𝘯 𝘦𝘹𝘪𝘴𝘵𝘪𝘯𝘨 𝘴𝘰𝘭𝘶𝘵𝘪𝘰𝘯𝘴.” and “𝘛𝘰 𝘮𝘢𝘬𝘦 𝘵𝘩𝘦 𝘥𝘰𝘤𝘶𝘮𝘦𝘯𝘵𝘴 𝘴𝘦𝘢𝘳𝘤𝘩𝘢𝘣𝘭𝘦 𝘧𝘰𝘳 𝘰𝘶𝘳 𝘙𝘈𝘎 𝘴𝘺𝘴𝘵𝘦𝘮, 𝘸𝘦 𝘶𝘴𝘦𝘥 𝘈𝘞𝘚 𝘬𝘯𝘰𝘸𝘭𝘦𝘥𝘨𝘦 𝘣𝘢𝘴𝘦𝘴. 𝘛𝘩𝘪𝘴 𝘨𝘢𝘷𝘦 𝘶𝘴 𝘴𝘭𝘪𝘨𝘩𝘵𝘭𝘺 𝘧𝘦𝘸𝘦𝘳 𝘤𝘰𝘯𝘧𝘪𝘨𝘶𝘳𝘢𝘵𝘪𝘰𝘯 𝘰𝘱𝘵𝘪𝘰𝘯𝘴 𝘵𝘩𝘢𝘯 𝘢 𝘤𝘶𝘴𝘵𝘰𝘮 𝘣𝘶𝘪𝘭𝘥 𝘦𝘢𝘳𝘭𝘪𝘦𝘳 𝘴𝘰𝘭𝘶𝘵𝘪𝘰𝘯 𝘣𝘶𝘵 𝘴𝘱𝘦𝘥 𝘶𝘱 𝘪𝘯𝘨𝘦𝘴𝘵𝘪𝘰𝘯 𝘣𝘺 𝘴𝘦𝘷𝘦𝘳𝘢𝘭 𝘮𝘢𝘨𝘯𝘪𝘵𝘶𝘥𝘦𝘴 𝘸𝘩𝘪𝘤𝘩 𝘢𝘭𝘭𝘰𝘸𝘦𝘥 𝘶𝘴 𝘵𝘰 𝘪𝘵𝘦𝘳𝘢𝘵𝘦 𝘱𝘳𝘦-𝘱𝘳𝘰𝘤𝘦𝘴𝘴𝘪𝘯𝘨 𝘮𝘶𝘤𝘩 𝘧𝘢𝘴𝘵𝘦𝘳.”

🚀As RAG continues to be one of the key architecture patterns for productionizing GenAI use cases that need to ground answers in your own documents, it pays to avoid undifferentiated heavy lifting, where possible, and focus on the actual product or service development—the tradeoff the team describes above, a few configuration options in exchange for magnitudes-faster ingestion, is exactly that. So if you have a Use Case at hand which would be build on RAG architecture, I highly recommend to give Amazon Bedrock Knowledge Bases. The technical report gives you a great starting point: https://medium.com/s%C3%BCddeutsche-zeitung-digitale-medien/ai-assistant-for-eu-election-q-a-e8e4b62c2751

Can’t wait to see what you build :)