Knowledge base: FAQ
Find answers to common questions about how the Knowledge Base works and how to get the best results from your agent with it.
How the Knowledge Base works
Q: How does the Knowledge Base work?
A: The Knowledge Base allows you to store information that your agent can reference when answering customer questions. It’s ideal for large amounts of content that you don’t want to include in the agent’s prompt.
When someone asks a question, the agent searches for the relevant information and retrieves it at that moment to generate a response. It does not memorize the entire knowledge base.
Q: What is RAG?
A: Retrieval-Augmented Generation (RAG) improves AI responses by allowing it to access external custom data.
Instead of relying solely on its pre-trained knowledge, the agent can pull information from the Knowledge Base and use it to generate more accurate responses.
How the agent retrieves information
Q: How does the agent decide which Knowledge Base entry to use?
A: When someone asks them a question, the agent searches the Knowledge Base for the most relevant answer. It does this by analyzing the question and matching it with related content to generate a response.
Q: Does the agent pull exact phrases from the Knowledge Base or summarize?
A: The agent will usually respond with a general answer in its own words. However, if the content is well-structured and clearly written, the agent may use exact phrases when appropriate.
Q: What happens if my Knowledge Base contains conflicting information?
A: If conflicting information exists across multiple documents (e.g., different figures in different files), the agent’s response may be inconsistent, and depend on which document it selects.
To prevent this, you can:
- Remove or update outdated content on a regular basis.
- Ensure consistency across documents.
- Test agent responses to verify accuracy.
Adding and managing Knowledge Base content
Q:How can I add documents to the Knowledge Base?
A: Currently, the Knowledge Base supports uploading PDFs, pulling information from URLs, or creating documents directly in the interface.
Q: Can I add multiple sources to the Knowledge Base?
A: Yes, you can add a mix of PDFs, website URLs, and documents you create in Synthflow. The agent will search through all available documents regardless of the source.
Q: Does the agent scrape my entire website when I add a URL?
A: No. The agent only processes the specific page you provide—it does not crawl or scrape the entire website. If you need multiple pages indexed, you’ll need to add each URL separately.
Q: Will all PDFs work when uploaded?
A: Not always. Structured PDFs (such as those with columns, embedded images, or complex formatting) may not be processed correctly. If you experience issues, consider converting the PDF to plain text before uploading.
Optimizing knowledge base performance
Q: How does the agent handle large documents?
A: The agent cannot read everything at once in long documents. Instead, it searches for the most relevant sections.
To improve information retrieval:
- Use clear headings and subheadings.
- Break up long documents into smaller, topic-specific files.
Q: Can I control what the agent pulls from the Knowledge Base?
A: No, you cannot prioritize certain documents over others. However, to improve accuracy, you can:
- Reword content for clarity.
- Group related topics together.
- Remove unnecessary details to keep responses focused.
Q: What if my agent isn’t using the Knowledge Base correctly?
A: If the agent isn’t pulling the right information, try to:
- Test different phrasing.
- Rewrite sections for clarity.
- Structure your content well with clear headers.