With particular due to Arkaprabho Ghosh and David Reed.
As AI continues to rework 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 had been keen to construct Retrieval-Augmented Era (RAG) functions, the method was usually fragmented. Builders had been spending months stitching collectively completely different parts of a RAG pipeline—resembling 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 numerous configurations to seek out the best match for particular use instances in the end 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 give attention to 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 information pipeline orchestration, permitting groups to fast-track their AI journey with out the necessity for intensive ramp-up time on underlying, complicated applied sciences.
Whether or not you’re a hard-core developer requiring deep API-level management or a enterprise consumer on the lookout for an intuitive interface, DRIFT offers a real end-to-end growth and experimentation surroundings.
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 information 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 resembling inferencing, embeddings, and reranking. By working on-premise throughout a number of Cisco Information Facilities, DRIFT combines scale, robust safety, excessive availability, and operational management in a means that meets the wants of enterprise AI.
The result’s greater than only a trendy 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 working 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 via a strong, modular pipeline structure:
- Doc Preprocessing: We assist numerous doc sources and codecs, standardizing numerous enterprise information right into a constant, model-ready format. We even leverage Imaginative and prescient Language Fashions (VLM) to transform pictures 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 through the splitting course of. For paperwork with blended content material, it additionally allows a hybrid method that selectively processes pictures—serving as a extremely efficient price optimization approach.
- Embedding and Ingestion: Groups can select from a set of ordinary embedding fashions or convey their very own. We provide seamless integration with each shared multi-tenant in addition to devoted Vector databases to go well with quite a lot of enterprise use instances. Our platform helps each key phrase and semantic search algorithms, guaranteeing environment friendly ingestion and retrieval that meet enterprise SLAs.
- Retrieval and Reranking: DRIFT permits for configurable hybrid search and metadata filtering, guaranteeing that retrieved information is exact. Our reranking capabilities additional refine outcomes based mostly on relevance, considerably rising accuracy.
- Adaptive Structure: Designed for the longer term, DRIFT helps evolving use instances, together with Agentic RAG and Graph RAG, guaranteeing enterprise functions 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 straight throughout the platform to validate generative summaries earlier than deployment.
Why is DRIFT a Sport-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 functions and workflows.
- Full Transparency and Experimentation: Now we 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 parts of their pipelines, permitting them to fine-tune, check, and optimize for max accuracy.
- Curated, Accountable AI: We eradicate the guesswork of evaluating open-source libraries. DRIFT offers fashions which are already vetted and accepted by Cisco’s Accountable AI (RAI) and governance groups.
- Diminished Expertise Fatigue: By offering a curated suite of industry-standard parts, we save groups from “evaluation paralysis.” We deal with the mixing to allow them to give attention to innovation.
- Flexibility and Scalability: Whereas we offer normal, high-quality choices, DRIFT stays absolutely versatile. Groups can combine their very own customized Vector Databases or fine-tuned fashions—resembling these specialised for Cisco-specific monetary or technical terminology.
Driving Actual-World Influence
Since its MVP launch in January 2025, the adoption of DRIFT has been extraordinary. Throughout the first 12 months, we have now seen vital adoption with over 600 builders having constructed greater than 1,500 pipelines throughout numerous enterprise items, together with Finance, Provide Chain, Engineering, Authorized, IT Operations, and Individuals and Communities.
By lowering the time required to construct an information pipeline from months to minutes, DRIFT has grow to be a important engine for Cisco’s AI technique, enabling groups to experiment quickly and ship high-accuracy, AI-first options at scale.
Wanting Forward
The success of DRIFT is a testomony to the collaborative spirit at Cisco. By working throughout groups—from IT & Operations to our numerous enterprise items—we have now created a instrument that not solely powers inner AI assistants (like our company-wide HR assistant) but additionally offers 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 following era of AI-powered options to our workers, clients and companions.
