Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt

Use this file to discover all available pages before exploring further.

Without a Knowledge Base, your agent only knows what the LLM was trained on. With a Knowledge Base, it can search your actual documents (company policies, product docs, FAQs, spreadsheets) and ground its answers in real information. This is Retrieval-Augmented Generation (RAG). When a user asks a question, Xpander searches your uploaded documents for relevant chunks and injects them into the agent’s context before it responds. The result: fewer hallucinations, more accurate answers, and the ability to cite sources. Knowledge Bases page showing list of knowledge bases This page covers:

​
Create a Knowledge Base

1

Open the Knowledge Bases page

Go to Knowledge Bases from the left sidebar. You’ll see all Knowledge Bases in your organization.
2

Click + Create New

Click + Create New in the top right.
Create Knowledge Base dialog with name and description fields
Enter a name and optional description. Use a name that describes the content (e.g., “Product Documentation,” “HR Policies,” “Sales Playbook”).
Already have a vector database? You can bring a compatible one and expose it to your agent as a tool. Contact Xpander to set this up.
3

Upload documents

Inside your new Knowledge Base, click Upload File. Drag and drop files or use the upload dialog. Maximum file size is 50 MB.
Upload dialog with drag and drop area
Xpander accepts a wide range of file types:
CategoryFormats
DocumentsPDF, DOCX, TXT, MD, RTF
SpreadsheetsXLSX, CSV
PresentationsPPTX
Web & DataHTML, JSON, YAML, XML
4

Wait for processing

Xpander processes each document through a pipeline: extract text, chunk into segments, generate vector embeddings, and index in the vector database. This typically takes 10–60 seconds per document.
Knowledge Base detail page showing uploaded documents
Once processing completes, your documents are searchable.
You can also click + Add external on the Knowledge Bases page to connect an external vector database instead of using Xpander’s built-in one.

​
Attach to Your Agent

Creating a Knowledge Base doesn’t automatically make it available to an agent. You need to attach it.
1

Open your agent's General tab

In the Agent Studio, click the gear icon and go to the General tab. Scroll down to the Knowledge Bases section.
2

Select a toolkit

Choose the Knowledge bases toolkit. This determines the vector database used for search. The default is Xpander built-in vector database.
3

Add a Knowledge Base

Under Add knowledge base, select your Knowledge Base from the dropdown and click Add.
Agent General tab showing Knowledge Bases section with toolkit selection and attached Knowledge Base
4

Publish

Click Publish to push the changes live. Your agent now automatically searches this Knowledge Base when answering questions.
You can attach multiple Knowledge Bases to the same agent. The agent searches across all of them when retrieving context.

​
How Search Works at Runtime

When a user asks a question, the agent doesn’t scan every document line by line. It uses semantic search:
  1. The user’s query is converted into a vector embedding
  2. Xpander compares it against all document chunks in the Knowledge Base
  3. The closest-matching chunks are injected into the agent’s context
  4. The agent generates a response grounded in the retrieved content
The agent uses a built-in search_knowledge_base tool automatically. You don’t need to configure this.

​
Tuning Relevance

Two settings control the quality of search results. Configure these in the Knowledge Base settings.
SettingWhat it doesDefault
Top KHow many document chunks to retrieve per query. Higher values give the agent more context but use more tokens.5
Similarity ThresholdHow closely a chunk must match the query to be included. Scale of 0.0 (match anything) to 1.0 (exact match only).0.7
If the agent is missing relevant information, increase Top K or lower the threshold. If it’s pulling in irrelevant content, raise the threshold or reduce Top K.

​
Best Practices

  • Write for search, not just for humans. Semantic search works best when documents have clear headings, self-contained sections, and explicit language. A section titled “Refund Policy” that says “Customers can request a refund within 30 days” will surface much better than one buried in a 50-page PDF with no headings.
  • Keep documents focused. One well-organized document per topic outperforms one massive document covering everything. Split large files into logical sections before uploading.
  • Use descriptive names. Clear Knowledge Base names help you understand which one to query when you have multiple attached to an agent.
  • Update regularly. Knowledge Bases aren’t set-and-forget. When your source documents change, re-upload them so the agent stays current.

​
Next Steps

Memory & State

How your agent remembers across conversations

Tools & Connectors

Give your agent actions beyond conversation

Testing & Chat

Test Knowledge Base retrieval in the chat

Knowledge Base API

REST API for programmatic access