Skip to main content
A Knowledge Base is a database made to provide relevant and specific information for an LLM to use. Knowledge can include any amount of important data that models need to retrieve. This is particularly useful when embedding domain-specific or business-specific information, ensuring that the details are both correct and accurate.

Why use a Knowledge Base?

The primary purpose of a Knowledge Base is to provide a reliable source of information that an LLM can access. By querying a Knowledge Base, an LLM can retrieve relevant data to answer questions or solve problems more accurately. This integration ensures that the information provided is both relevant and precise, enhancing the overall effectiveness of the model.

Use cases

  1. Reduced Hallucination: By relying on a well-structured Knowledge Base, the likelihood of the LLM generating incorrect or fabricated information (hallucinations) is significantly decreased.
  2. Specific Context: A Knowledge Base allows for the inclusion of domain-specific or context-specific information, ensuring that the responses generated by the LLM are more aligned with the intended context.
  3. Up-to-Date Information: Unlike static models, a Knowledge Base can be continuously updated with the latest information, providing the LLM with current and accurate data.

Internal vs External Knowledge Base

Orq lets you either manage directly your knowledge base on the platform, by uploading documents and building chunks internally, or lets you integrate external knowledge base seamlessly. Feature Comparison
FeatureInternal KnowledgeExternal Knowledge
Data StorageStored in orq.aiStored externally
EmbeddingsManaged by orq.aiManaged externally
Document Upload✅ Supported❌ Managed externally
Search ConfigFull controlDelegated to API
Reranking✅ Via orq.ai✅ Post-processing
Agentic RAG✅ Supported✅ Supported
Metadata Filtering✅ Full supportDepends on API

Getting started

Internal Knowledge Base: External Knowledge Base: Usage