RAG Knowledge Pipeline

QORE’s RAG (Retrieval-Augmented Generation) framework enables apps and agents to retrieve relevant information from connected knowledge sources before generating responses.

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

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

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

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