> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/agent-builder/build/rag-knowledge-pipeline.md). # RAG Knowledge Pipeline **The platform allows teams to:** * Connect enterprise knowledge sources * Organize and process documents * Enable AI-powered semantic search * Reuse knowledge across apps and agents * Build grounded AI experiences using enterprise data **QORE structures the RAG workflow into reusable components:** * Knowledge Pipelines * Data Stores * Vector Stores This documentation explains how each component works and how to configure them within the platform. **A Knowledge Pipeline combines:** * Data Sources * Data Storage * AI Search Indexing * Retrieval & Generation This allows agents and applications to answer questions using enterprise knowledge instead of relying only on the base LLM. *** ## RAG Architecture QORE follows a modular RAG architecture that separates: * Knowledge ingestion * Knowledge processing * AI indexing * Retrieval orchestration ``` Data Sources ↓ Data Store ↓ Vector Store ↓ Knowledge Pipeline ↓ Apps & Agents ``` ## How the RAG Flow Works QORE follows a simple 4-step knowledge flow: ### 1. Add Knowledge Connect files, cloud drives, or enterprise systems. Supported sources include: * Upload Files * Google Drive * OneDrive * SharePoint ### 2. Organize & Secure Documents are stored, processed, chunked, and optionally protected using PII masking. During this stage: * Files are extracted * Text is normalized * Metadata is processed * Sensitive information can be masked * Knowledge is prepared for indexing ### 3. Enable AI Search The processed knowledge is converted into embeddings using an embedding model. This creates an AI-searchable index that helps retrieve the most relevant information for a user query. QORE supports: * Configurable embedding models * Vector indexing * Similarity search * Retrieval tuning ### 4. Use in Apps & Agents Once the pipeline is active: * Agents can retrieve contextual knowledge * Apps can power AI search experiences * Responses become grounded in enterprise data *** ## Core Components ### [Knowledge Pipeline](#knowledge-pipeline) A Knowledge Pipeline is the primary RAG orchestration layer. It connects: * Data Stores * Vector Stores * Retrieval settings * Generation models A pipeline controls how knowledge is retrieved and used during AI conversations. *** ### [Data Store](#data-store) A Data Store is responsible for storing and processing connected knowledge. Capabilities: * Document ingestion * Chunking * Metadata extraction * PII masking * Source synchronization Data Stores can connect to one or more external sources. *** ### [Vector Store](#vector-store) A Vector Store creates AI-searchable embeddings from processed documents. Capabilities: * Embedding generation * Similarity search * Semantic retrieval * Search indexing Vector Stores are connected to a Data Store. *** ## Navigation Access the RAG module from: Sidebar → RAG The RAG module contains: * Knowledge Pipelines * Vector Stores * Data Stores *** ## Using Knowledge Pipelines with Agents Knowledge Pipelines can be attached to agents to provide contextual retrieval during conversations. Agents can: * Retrieve enterprise knowledge * Answer questions using indexed documents * Ground responses in connected data sources * Access organization-specific information Knowledge Pipelines are reusable across multiple apps and agents. ## Common Use Cases ### Customer Support Agents Enable AI agents to answer questions using: * SOPs * FAQs * Product documentation * Help center content *** ### Internal Enterprise Search Search across: * policies * contracts * knowledge bases * operational documentation *** ### Compliance & Audit Assistance Ground AI responses using: * compliance frameworks * policy documents * internal procedures * regulatory references *** ### Financial Services Workflows Power retrieval for: * underwriting * onboarding * collections * risk assessment * loan operations *** ## Key Benefits QORE’s RAG framework enables: * Context-aware AI responses * Enterprise knowledge grounding * Improved answer accuracy * Retrieval transparency * Secure enterprise AI workflows * Reusable knowledge infrastructure across apps and agents --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.uptiq.ai/agent-builder/build/rag-knowledge-pipeline.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.