0% found this document useful (0 votes)
10 views11 pages

Understanding Knowledge Sources in AI

A Knowledge Source is structured information that Knowledge AI extracts from various content types and provides to AI Agents, with the ability to add metadata and tags for improved usage. There are limitations on file size, metadata pairs, and character counts, and the content is organized using content types and Knowledge Connectors. Users can manage Knowledge Sources through a GUI, API, or CLI, and download them as CTXT files for better flexibility and editing capabilities.

Uploaded by

vkc
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
10 views11 pages

Understanding Knowledge Sources in AI

A Knowledge Source is structured information that Knowledge AI extracts from various content types and provides to AI Agents, with the ability to add metadata and tags for improved usage. There are limitations on file size, metadata pairs, and character counts, and the content is organized using content types and Knowledge Connectors. Users can manage Knowledge Sources through a GUI, API, or CLI, and download them as CTXT files for better flexibility and editing capabilities.

Uploaded by

vkc
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Applicable Knowledge Source

A Knowledge Source is structured, easily accessible


information that Knowledge AI extracts from documents or
external systems and provides to AI Agents. You can create
Knowledge Sources from content types, such as PDF, CTXT, web
pages, or via Knowledge Connectors that link to external
knowledge bases. Knowledge AI breaks content into smaller units
called Knowledge Chunks. You can also add Source
metadata and Knowledge Source Tags to improve how AI
Agents use the content.

Limitations
 You can upload files with up to 10 MB as Knowledge Sources.
 You can add up to 20 Source metadata pairs per Knowledge
Source.
 Source metadata pairs can have up to 1000 characters.

Knowledge Types
Knowledge AI organizes content using content types and
Knowledge Connectors. While both provide information for your AI
Agents, they are independent and use separate parsers.
Content Types

o
Knowledge Connectors

Source Metadata
Source metadata contains information about the Knowledge
Source and is formatted as JSON key-value pairs. The keys refer
to the information the Source metadata holds and the value is the
information, for example, publication: [Link] can store Source
metadata in the Input object or Context object and give your AI
Agents access to the Source metadata through:
 [Link][0].sourceMetadata in the Input object
 [Link][0].sourceMetadata in the Context
object
This way, AI Agents can provide relevant information about the
source of their replies to users.

Knowledge Source

Knowledge Source

Copy page

A Knowledge Source is structured, easily


accessible information that Knowledge AI
extracts from documents or external systems
and provides to AI Agents. You can create
Knowledge Sources from content types, such as
PDF, CTXT, web pages, or via Knowledge
Connectors that link to external knowledge
bases. Knowledge AI breaks content into
smaller units called Knowledge Chunks. You can
also add Source metadata and Knowledge
Source Tags to improve how AI Agents use the
content.
Limitations

 You can upload files with up to 10 MB as


Knowledge Sources.

 You can add up to 20 Source metadata pairs


per Knowledge Source.

 Source metadata pairs can have up to 1000


characters.

Knowledge Types

Knowledge AI organizes content using content


types and Knowledge Connectors. While both
provide information for your AI Agents, they are
independent and use separate parsers.

Content Types


Knowledge Connectors
Source Metadata

Source metadata contains information about


the Knowledge Source and is formatted as JSON
key-value pairs. The keys refer to the
information the Source metadata holds and the
value is the information, for
example, publication: [Link] can store
Source metadata in the Input object or Context
object and give your AI Agents access to the
Source metadata through:

 [Link][0].sourceMeta
data in the Input object

 [Link][0].sourceMe
tadata in the Context object

This way, AI Agents can provide relevant


information about the source of their replies to
users.

Examples

You can find examples of Source metadata in


the following table:
Ke Mandat
y Description ory Example

This key
defines the
document’s
name. If a user
requests the
information
titl title: Cognigy xApps
source, the AI no
e FAQs
Agent can
provide the
document’s
title in the
response
message.

url This key no url:


defines a URL [Link]
as the [Link]
document’s
source. If a
user requests
the
information
source, the AI
Agent can
provide the
link to the
document’s
source in the
Ke Mandat
y Description ory Example

response
message.

This key
defines Knowl
edge Source
Tags. To add
more than
tag Knowledge [cognigy, xapps,
no
s Source Tag, architecture]
use an array.
You can add
up to 10
Knowledge
Source Tags.

You can add any Source metadata to a


Knowledge Source and give AI Agents access to
the Source metadata
through [Link][0].source
MetaData.{key}. For example, if you add the
Source metadata author: Cognigy,
where author is the key, and store it in the
Input object, retrieve this information by
using [Link][0].sourceMe
[Link].
Working with Knowledge Sources

 GUI

 API

 CLI

You can view, create, edit, and delete


Knowledge Sources in Build > Knowledge. Also,
you can copy Knowledge Sources’ Reference ID,
disable and export Knowledge Sources,
and download them as CTXT file.

Download Knowledge Sources as CTXT

You can download Knowledge Sources as a


CTXT file, including Knowledge Sources created
from web pages and other file formats.
Downloading Knowledge Sources as CTXT files
offers more flexibility in managing Knowledge
Sources. With a CTXT file, you can:
 Back up Knowledge Sources more easily
after you have edited the Knowledge
Chunks.

 Use Knowledge Sources across Knowledge


Stores with different embedding vector
dimensions.

 Edit downloaded Knowledge Sources more


efficiently with external tools, such as text
editors, with features like search and
replace, bulk editing, and integration of AI
tools.

More information

 Knowledge Store

 Knowledge Chunk

 Knowledge Source Tags

 Chunk editor

 Input

xamples
You can find examples of Source metadata in the following table:
Key Description Mandatory Example
This key defines the document’s name. If a
titl user requests the information source, the AI title: Cognigy xApps
e
no FAQs
Agent can provide the document’s title in the
response message.
This key defines a URL as the document’s
source. If a user requests the information url:
url source, the AI Agent can provide the link to no [Link]
the document’s source in the response m
message.
This key defines Knowledge Source Tags.
To add more than Knowledge Source Tag, [cognigy, xapps,
tags no architecture]
use an array. You can add up to 10
Knowledge Source Tags.
You can add any Source metadata to a Knowledge Source and
give AI Agents access to the Source metadata
through [Link][0].sourceMetaData.{key}. For
example, if you add the Source metadata author: Cognigy,
where author is the key, and store it in the Input object, retrieve
this information by
using [Link][0].[Link].

Working with Knowledge Sources


 GUI
 API
 CLI

You can view, create, edit, and delete Knowledge Sources


in Build > Knowledge. Also, you can copy Knowledge Sources’
Reference ID, disable and export Knowledge Sources,
and download them as CTXT file.

Download Knowledge Sources as CTXT


You can download Knowledge Sources as a CTXT file, including
Knowledge Sources created from web pages and other file
formats. Downloading Knowledge Sources as CTXT files offers
more flexibility in managing Knowledge Sources. With a CTXT file,
you can:
 Back up Knowledge Sources more easily after you have
edited the Knowledge Chunks.
 Use Knowledge Sources across Knowledge Stores with
different embedding vector dimensions.
 Edit downloaded Knowledge Sources more efficiently with
external tools, such as text editors, with features like search
and replace, bulk editing, and integration of AI tools.

More information
 Knowledge Store
 Knowledge Chunk
 Knowledge Source Tags
 Chunk editor
 Input

You might also like