# Knowledge base

### **What is ZBrain’s knowledge base?** <a href="#what-is-zbrains-knowledge-base" id="what-is-zbrains-knowledge-base"></a>

The knowledge base is the core of ZBrain, serving as the foundation for building AI applications and agents. This integral component enables seamless integration and management of users' proprietary data, providing them with the flexibility to import or upload various data types effortlessly. Here's an overview of the knowledge base's capabilities:

**Data integration and flexibility**

ZBrain’s Knowledge Base enables seamless data ingestion from a wide range of sources and formats, including documents (PDF, TXT, CSV, JSON, DOCX, PPTX, XLSX), images (BMP, GIF, JPG, PNG), and videos (AVI, FLV, MKV, MOV, MP4, MPEG, MPG, WEBM, WMV). Users can import data from a variety of tools and platforms, including:

* Web URLs
* Google Sheets
* Notion
* MongoDB
* ServiceNow
* Confluence
* JIRA
* PostgreSQL
* AWS RedShift
* SharePoint
* Microsoft Teams
* OneDrive
* Google Drive
* Webhook
* ElasticSearch
* Google Slides
* Google Docs

And

* Flows

This flexibility ensures comprehensive data connectivity, allowing users to build a robust knowledge repository and integrate diverse datasets effortlessly into their AI applications and agents.

**Automated Reasoning**

ZBrain’s Automated Reasoning enhances query processing by extracting rules and variables from the knowledge base and applying logic-driven policies to deliver accurate inferences. It offers an interactive environment where users can test logic with sample queries, observe how variables and rules are applied, and refine them in real-time. This rule-based, data-driven approach ensures more precise, consistent, and explainable responses, making AI outputs more reliable and aligned with business logic.

**Structure and organization**

The knowledge base offers information schema capability to transform unstructured data like PDF and text files into structured information through advanced processing. This structured data is essential for extracting meaningful insights and facilitating decision-making processes. By leveraging Large Language Models (LLMs), the system can effectively analyze and interpret large volumes of data, making it readily available for querying.

**Retrieval and optimization**

ZBrain delivers fast, context-aware retrieval through two complementary retrieval methods.

**Vector store retrieval:** Choose vector search, full-text search, or hybrid search to quickly surface the most relevant documents.

**Knowledge graph retrieval:** It lets you choose how much information to pull in and how deeply to explore connections, depending on your needs. Select from five strategies: naïve, local, global, hybrid, and mix to define how much information is retrieved and how deeply relationships are analyzed.

These options enable you to tailor retrieval for speed, accuracy, or semantic richness, ensuring that queries return the correct information with minimal latency.

Customizable settings, such as Top K results, score thresholds, and search modes, enable you to fine-tune retrieval behavior for optimal performance. Once parameters are configured and the knowledge base is created, users can perform retrieval testing by running sample queries. The system intelligently identifies, ranks, and surfaces the most relevant data chunks based on the selected criteria, ensuring that LLMs deliver precise, high-quality responses aligned with your business context.

***Note:** For more information on vector search, full-text search, hybrid search, Top K results, and score thresholds, please refer to* [*https://docs.zbrain.ai/zbrain-documentation/zbrain-builder/knowledge-base/how-to-create-a-knowledge-base/text-data-refinement/how-to-create-a-knowledge-base-using-vector-store*](https://docs.zbrain.ai/zbrain-documentation/zbrain-builder/knowledge-base/how-to-create-a-knowledge-base/text-data-refinement/how-to-create-a-knowledge-base-using-vector-store)

For further details on knowledge graph strategies, please refer to <https://docs.zbrain.ai/zbrain-documentation/zbrain-builder/knowledge-base/how-to-create-a-knowledge-base/text-data-refinement/how-to-create-a-knowledge-base-using-knowledge-graph>

**Secure and scalable storage**

ZBrain’s Knowledge Base supports multiple vector stores for efficient data indexing and retrieval, providing full flexibility across storage providers. It is storage-agnostic, allowing you to choose from options like Pinecone for scalable vector indexing, Chroma DB for fast, open-source vector search, and Economical (ZBrain’s built-in vector store) for cost-effective management. You can also add your own custom vector store as needed. Additionally, ZBrain leverages secure storage through ZBrain file storage, ensuring safe and efficient data handling while delivering precise retrieval results without any additional token costs.

**Continuous improvement and customization**

The knowledge base allows users to refine and customize their data-handling strategies. Users can configure chunking rules, choose the preferred embedding models, select appropriate vector stores, and set retrieval parameters such as search type, top K results, and score thresholds. These flexible configurations ensure that the knowledge base aligns with specific business needs, thereby enhancing the accuracy and relevance of AI-generated responses.

**Summary and management**

Users can generate summaries of their documents using available models, providing a concise overview of the content. The knowledge base interface allows for easy management of data chunks, including editing, disabling, or adding new chunks. This ensures that the stored information remains relevant and up-to-date.

In summary, the knowledge base in ZBrain is designed to provide a comprehensive and flexible interface for data integration, storage, and retrieval. It underpins the effectiveness of ZBrain's AI applications and agents, ensuring they deliver accurate, relevant, and context-specific responses.

### **Accessing knowledge base documentation** <a href="#accessing-knowledge-base-documentation" id="accessing-knowledge-base-documentation"></a>

ZBrain includes a context-aware documentation panel within the Knowledge module.

* Click the '?' icon in the top-right corner of the Knowledge interface.

<figure><img src="https://3781630280-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIbuSicczDKTyHzwzicar%2Fuploads%2FA8fiTpXnT56mH7w9huhz%2Fimage.png?alt=media&#x26;token=caaaeb24-1aa1-4f42-8489-4b6d9478b368" alt=""><figcaption></figcaption></figure>

* When clicked, it opens a side panel that displays documentation specifically tailored to the Knowledge module, all without navigating away from your current screen.

<figure><img src="https://3781630280-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FIbuSicczDKTyHzwzicar%2Fuploads%2FV5KR8D3rSpcclM6jhrpj%2Fimage.png?alt=media&#x26;token=bd8e2dd5-1878-4ef7-816d-f6a29a830ea4" alt=""><figcaption></figcaption></figure>

This feature ensures you always have relevant documentation at your fingertips, helping you make the most of ZBrain's knowledge ingestion and retrieval capabilities to create an effective Knowledge Base without leaving the module.