With particular because of Arkaprabho Ghosh and David Reed.
As AI continues to remodel the enterprise panorama, the problem for giant organizations isn’t simply adopting the know-how—it’s scaling it successfully. At Cisco, we acknowledged that whereas our groups have been keen to construct Retrieval-Augmented Era (RAG) purposes, the method was usually fragmented. Builders have been spending months stitching collectively totally different elements of a RAG pipeline—reminiscent of loaders, splitters, embedding fashions, and vector databases. Every part carried its personal studying curve and operational overhead. The burden of evaluating an amazing variety of open-source instruments and endlessly experimenting with varied configurations to search out the fitting match for particular use circumstances finally led to inconsistent requirements, technical debt, and widespread “know-how fatigue”.
To resolve this, Cisco IT created DRIFT (Doc Retrieval and Ingestion Framework Toolkit), a standardized, scalable platform that helps fast growth and experimentation in RAG workflows with the power to scale to fulfill enterprise-standard workloads.
Simplifying the AI Journey
DRIFT was constructed with a easy premise: utility groups ought to concentrate on constructing AI-first experiences and enterprise logic, not on the heavy lifting of infrastructure. We’re eradicating the boundaries to entry by offering a platform that handles the complexity of knowledge pipeline orchestration, permitting groups to fast-track their AI journey with out the necessity for in depth ramp-up time on underlying, advanced applied sciences.
Whether or not you’re a hard-core developer requiring deep API-level management or a enterprise person on the lookout for an intuitive interface, DRIFT supplies a real end-to-end growth and experimentation atmosphere.
The Cisco-on-Cisco Benefit: Constructed for Scale & Safety
DRIFT is a strong instance of the Cisco-on-Cisco benefit—the place Cisco software program is constructed to run on Cisco’s personal AI infrastructure. Constructed on a cloud-native microservices structure and deployed on Kubernetes, DRIFT is engineered for agility, resilience, and enterprise-scale efficiency. Its asynchronous ingestion and file add structure is designed to deal with massive volumes of enterprise knowledge effectively, enabling high-throughput pipelines with out sacrificing reliability.
On the coronary heart of this basis are Cisco AI PODs powered by Cisco UCS-C885A {hardware}. This offers DRIFT the high-performance compute spine wanted for demanding AI workloads reminiscent of inferencing, embeddings, and reranking. By operating on-premise throughout a number of Cisco Information Facilities, DRIFT combines scale, sturdy safety, excessive availability, and operational management in a approach that meets the wants of enterprise AI.
The result’s greater than only a fashionable AI platform—it’s a clear demonstration of how Cisco AI software program and Cisco AI infrastructure come collectively to ship production-ready efficiency at scale. With DRIFT operating on Cisco AI PODs constructed on UCS-C885A, Cisco is showcasing an end-to-end AI stack that’s scalable, safe, and purpose-built for enterprise innovation.
The DRIFT Methodology: Powering Safe RAG
DRIFT streamlines the trail from uncooked doc to clever assistant by way of a sturdy, modular pipeline structure:
- Doc Preprocessing: We assist various doc sources and codecs, standardizing various enterprise knowledge right into a constant, model-ready format. We even leverage Imaginative and prescient Language Fashions (VLM) to transform photos inside paperwork into textual content representations.
- Clever Splitting and Hybrid Processing: DRIFT helps quite a lot of splitting algorithms, together with the power to protect a doc’s structural formatting in the course of the splitting course of. For paperwork with blended content material, it additionally allows a hybrid method that selectively processes photos—serving as a extremely efficient value optimization method.
- Embedding and Ingestion: Groups can select from a collection of ordinary embedding fashions or carry their very own. We provide seamless integration with each shared multi-tenant in addition to devoted Vector databases to swimsuit quite a lot of enterprise use circumstances. Our platform helps each key phrase and semantic search algorithms, making certain environment friendly ingestion and retrieval that meet enterprise SLAs.
- Retrieval and Reranking: DRIFT permits for configurable hybrid search and metadata filtering, making certain that retrieved knowledge is exact. Our reranking capabilities additional refine outcomes primarily based on relevance, considerably growing accuracy.
- Adaptive Structure: Designed for the long run, DRIFT helps evolving use circumstances, together with Agentic RAG and Graph RAG, making certain enterprise purposes can scale as AI architectures advance.
- Constructed-in Testing and Analysis: Builders can check retrievers in opposition to pattern queries and work together with LLMs instantly throughout the platform to validate generative summaries earlier than deployment.
Why is DRIFT a Recreation-Changer:
- API-First Structure: DRIFT was constructed from the bottom up with an API-first method. We offer complete, ready-to-use APIs for each step of the lifecycle—together with doc add, ingestion, retrieval, and configuration—enabling seamless integration into current enterprise purposes and workflows.
- Full Transparency and Experimentation: We now have moved away from the “black-box” method to a real end-to-end growth and experimentation platform that empowers builders with full visibility. Groups have full management over configuration decisions for all elements of their pipelines, permitting them to fine-tune, check, and optimize for max accuracy.
- Curated, Accountable AI: We remove the guesswork of evaluating open-source libraries. DRIFT supplies fashions which might be already vetted and accepted by Cisco’s Accountable AI (RAI) and governance groups.
- Decreased Expertise Fatigue: By offering a curated suite of industry-standard elements, we save groups from “evaluation paralysis.” We deal with the combination to allow them to concentrate on innovation.
- Flexibility and Scalability: Whereas we offer commonplace, high-quality choices, DRIFT stays absolutely versatile. Groups can combine their very own customized Vector Databases or fine-tuned fashions—reminiscent of these specialised for Cisco-specific monetary or technical terminology.
Driving Actual-World Impression
Since its MVP launch in January 2025, the adoption of DRIFT has been extraordinary. Inside the first 12 months, now we have seen vital adoption with over 600 builders having constructed greater than 1,500 pipelines throughout various enterprise models, together with Finance, Provide Chain, Engineering, Authorized, IT Operations, and Individuals and Communities.
By decreasing the time required to construct a knowledge pipeline from months to minutes, DRIFT has turn into a crucial engine for Cisco’s AI technique, enabling groups to experiment quickly and ship high-accuracy, AI-first options at scale.
Trying Forward
The success of DRIFT is a testomony to the collaborative spirit at Cisco. By working throughout groups—from IT & Operations to our varied enterprise models—now we have created a instrument that not solely powers inside AI assistants (like our company-wide HR assistant) but additionally supplies a basis for future product integrations.
As we proceed to iterate, DRIFT stays dedicated to serving to Cisco groups transfer sooner, experiment extra, and ship the subsequent era of AI-powered options to our staff, prospects and companions.
