Integrate Knowledge within Apps

Connect Knowledge Bases with ClickAI applications so AI responds based on your business data.

Table of Contents

· [Create an Application with Knowledge](#create-an-application-with-knowledge)

· [Retrieval Setting](#retrieval-setting)

· [Metadata Filtering](#metadata-filtering)

· [Integrate in Chatflow/Workflow](#integrate-in-chatflowworkflow)

· [Integrate in Chatbot](#integrate-in-chatbot)

· [View Linked Applications](#view-linked-applications)

· [FAQ](#faq)

Create an Application with Knowledge

Quick workflow:

1. Go to Knowledge — Create Knowledge — Upload file

2. Go to Studio — Create Application — Select Chatbot

3. Open Context, click Add, select the created Knowledge Base

4. Use Metadata Filtering to refine document search

5. In Context Settings > Retrieval Setting, configure retrieval method

6. Enable Citation and Attribution in Add Features

7. Test in Debug and Preview

8. Click Publish to launch the application

Retrieval Setting

Configure how the application retrieves information from Knowledge Base:

Weight Settings

Mode	Description
Semantic = 1	Semantic search only. Searches by contextual meaning, supports multilingual
Keyword = 1	Keyword search only. Exact keyword matching, resource-efficient
Custom Weights	Combines semantic + keyword at custom ratio

Retrieval Parameters

Parameter	Description	Default
Top K	Maximum chunks to return	3
Score Threshold	Minimum similarity score	0.5

Metadata Filtering

In Chatflow/Workflow

Use the Knowledge Retrieval node with Metadata Filter:

Select Filter Mode:

Mode	Description
Disabled (Default)	No metadata filtering
Automatic	Filters auto-configure from query variables
Manual	Configure filters manually

Manual Mode Configuration:

9. Click Conditions to open the configuration panel

10. Click +Add Condition — select metadata fields

11. Configure filter conditions:

Data Type	Supported Operators
String	is, is not, is empty, is not empty, contains, not contains, starts with, ends with
Number	=, ≠, >, <, ≥, ≤, is empty, is not empty
Date	is, before, after, is empty, is not empty

12. Add filter values:

· Variable: Select from Chatflow/Workflow variables

· Constant: Enter fixed values

13. Set logic operators: AND (match all) or OR (match any)

📝 NOTE: Automatic Mode requires model selection for document retrieval. When multiple Knowledge Bases are selected, only common metadata fields appear.

Integrate in Chatflow/Workflow

14. Drag the Knowledge Retrieval node onto the canvas

15. Select the Knowledge Base to connect

16. Configure query variable (usually {{sys.query}})

17. (Optional) Configure Metadata Filter

18. Connect output to an LLM node as context

Integrate in Chatbot

19. Open the Chatbot application in Studio

20. In the Context section, click + Add

21. Select the Knowledge Base

22. Configure Retrieval Settings

23. Enable Citation and Attribution if needed

View Linked Applications

In any Knowledge Base, you can view a list of all applications currently using it. This helps assess the impact when modifying content.

FAQ

How should I choose Rerank settings in multi-recall mode?

When using multiple knowledge bases, enable a Rerank model to sort results from all sources.

Can't find the "Weight Score" option?

Weight Score is only available when using the High Quality index method. Check the index method in Knowledge Base Settings.

Error adjusting Weight Score with multiple Knowledge Bases?

When referencing multiple knowledge bases, Weight Score may be restricted. Configure a Rerank model instead.

📖 Previous: [Test Retrieval](./11-test-retrieval.md)