Knowledge

Knowledge is a solution to extract and generate context-sensitive answers from knowledge sources uploaded to the platform. 


It boosts the understanding of user queries by tapping into different content sources. This enables the agent to provide more contextualized and assertive answers. This feature transforms how information is stored, retrieved, and utilized by implementing Retrieval-Augmented Generation (RAG) to bridge AI capabilities with structured content.

Our solution is built on two key components that work together to deliver intelligent information retrieval:

Sources: Upload various knowledge sources types including PDFs, TXT files, and more to come. These become valuable information repositories that your agent can reference when answering user queries. With improved management, you can update, transfer, and organize your sources while maintaining all existing questions connections.

Collections: Intuitive topic-based repositories for your knowledge sources. This new grouping system optimizes training performance, enhances response accuracy through intelligent filtering, and allows you to scale your knowledge base without compromising on quality or speed. Each collection can be individually customized with advanced search settings for maximum relevance.

Together, these capabilities create a powerful knowledge management system that helps your agent deliver more accurate, contextual, and valuable responses to your users.

Important: When enabling Kowledge you are subject to the terms of a third-party service and you agree to share information in the sources with the Generative AI model provider to which you are connecting.

How it works

In short, Knowledge:

• Finds an answer to the user's question in one or multiple sources

• Has a QnA functionality for sources by registering pairs of questions and answers. Those are brief and accurate.

• Serves as a secondary cognitive engine, independent of your primary knowledge base's.

• Is multilanguage

• Has the ability to identify if there is no answer to a question, given the context of the source

• Can read images with text, but not graphic images.

How image reading works (OCR)

OCR stands for Optical Character Recognition, an AI model designed to identify text characters in images. It can read images with text but doesn't interpret graphic images.

Applying OCR is essential to avoid losing relevant information contained in images within PDF files. This ensures that all textual content is utilized, even if it's an image.

When do we use OCR in Knowledge AI?

OCR is used during the training in the following scenarios:

• TXT: OCR is not applied as these files only contain pure text.

• PDF: All pages of the PDF are converted into images, after that the resolution of these images is improved, and then processed by the OCR model to extract the text.

When the user interacts with the agent, the system arranges knowledge in a hierarchical manner to ensure a precise answer delivery. The hierarchical structures are as described below.

1. First search for an intent that starts a flow

2. If it doesn't find a match, it will search for an intent that has an even answer, i.e. an FAQ flow.

3. If once again there is no match, the intelligence searches in a source in Knowledge AI (the functionality must be enabled, otherwise it goes straight to the next step).

4. Finally, if none of the previous cases apply, the user falls into a Not Expected flow.

Layered Knowledge base in Syntphony CAI

Enable Feature

Go to the Advanced Resources page to enable it, as it comes disabled by default. Click the switch of the corresponding card.

Important: Enabling this feature may result in additional costs for each new request.

You will be asked to set the number of previous user inputs you want to consider as context when generating a response.

The following sections will guide you through creating, managing, and maximizing the potential of your Collections ans Sources.