🚀How to use Knowledgebots

This section provides a friendly and easy-to-follow guide on using knowledge bots effectively. Discover how these intelligent assistants can help you quickly find the information you need.

Navigation

At the top of your screen, on the right-hand side you'll find two tabs: "Dashboard" and "Data Management"

Dashboard - Your Starting Point

Your dashboard is the control center for your Knowledge Bots. Here's what you can do:

1. Add Bots: Expand your collection of bots by adding new ones.

2. Search and Select Bots: Quickly find the right bot for your query by searching through your available bots.

3. Start a Conversation: Click on a bot to start a conversation and ask for information.

Dashboard

Data Management

The Data Management section allows you to organize, create, and manage your databases and insights. This guide will walk you through the main features and how to use them effectively.

Managing Databases

Viewing Databases

Upon entering Data Management, you'll see two types of databases:

1. Public databases from your builders

2. Private databases you've created

Accessing Database Contents

To view documents within a database:

1. Locate the desired database in the list

2. Click on the database name

3. Browse through the containing documents

Creating a New Database

1. Click the "New Database" button

2. Fill in the required information:

• Name your database

• Add a description

• Select an embedding model that suits your needs

1. Click "Create" to finalize

Advanced Settings in Databases

In the Advanced Settings you have the following options to edit your database:

1. Access Settings: Set your Database to private or public if you want your coworkers to be able to see and work with your documents.

2. Language: Choose the language of your database.

3. Chunk Size: This parameter determines the amount of text, in characters, that the Al processes in a single chunk from the documents uploaded. A smaller chunk size focuses the Al's analysis on a more narrow segment of text, leading to more precise and directly relevant re-sponses. Conversely, a larger chunk size allows the Al to consider a broader range of informa-tion, potentially capturing more context but also possibly diluting the precision of insights with less directly relevant information.

   Recommended Usage: For inquiries that demand high precision and direct answers, opt for smaller sizes (e.g., 1000-2000 characters). For questions that benefit from a wider exploration of the text or when the context is crucial for un-derstanding, larger sizes (e.g., 3000-4000 char-acters) may be more effective. It's essential to balance the need for detailed information against the risk of including too much peripheral content.

   Important: Chunk Size should be greater than Chunk Overlap

4. Chunk Overlap: This parameter controls the amount of text, in characters, that overlaps between consecutive chunks. An increased overlap ensures better continuity and context retention across chunks, improving the cohesiveness of insights generated by the Al. A lower overlap may result in more disjointed analysis but can increase processing efficiency by reducing re-dundancy.

   Recommended Usage: Smaller overlap values (e.g., 100-200 characters) are typically sufficient for general queries and help to maintain processing speed. For complex analyses where context is critical (especially in nuanced or technical documents) higher overlap values (e.g.,

   300-500 characters) may provide more accurate and contextually rich responses. Adjust this setting based on the need for context continuity versus processing speed.

   Important: Chunk Size should be greater than Chunk Overlap

5. Smart Table Processing: Enable this to automatically detect and convert tables in uploaded PDFs into a structured text format that is readable for LLMs. Note: This will incur additional costs and processing time.

6. Smart Image Processing: Enable this to automatically detect and convert images in uploaded PDFs into a structured text format that is readable for LLMs. Note: This will incur additional costs and processing time.

7. Image Extraction: Enable this feature to extract images from uploaded PDFs. This will allow the bot to retrieve and display the images, enhancing the responses.

Adding Documents to a Database

After creating a database, you can add documents in three ways:

1. Upload from your computer: Click "Upload" and select files from your device

2. Import from the web: Click "Import" and enter the URL of the web content

3. Connect a shared drive: Click "Connect Drive" and follow the prompts to link your shared drive

Managing Insights

Viewing Insights

1. Click on the "Insights" tab in Data Management

2. Browse through your saved insights

Creating New Insights

1. In the Insights section, click "New Insight"

2. Follow the prompts to create and save your new insight

You can directly connect your data to the knowledgebot for easy access and analysis. Remember, this Data Management system is designed to help you organize and utilize your information efficiently. Don't hesitate to explore its features to maximize your productivity!

Chat with a Knowledgebot

1. Getting Started

Upon opening the application, you'll see a three-panel interface:

• Left sidebar for navigation

• Central chat area

• Right sidebar for settings

2. Managing Data Room

1. Locate the "Create Data Room" button in the left sidebar.

2. Click the "+" icon next to it.

3. Name your new data room.

4. Switch between different data rooms by selecting them in the left sidebar.

5. Use separate rooms for different projects or topics.

3. Using the Chat Interface

• The central area displays the chat history.

• At the bottom, you'll find a text input field labeled "Write your message".

• Type your message or use the microphone icon for voice input.

• The bot will respond based on its configured settings and available knowledge. The responses will appear in the chat window above.

• Use the icons in the top bar of the chat area for additional actions (share, copy, rewind etc.).

How to use Agents

Agents are automated assistants that perform routine tasks on your behalf, streamlining your workflow and saving valuable time. Agents help standardize processes while maintaining consistent quality across repetitive tasks.

Agent Templates must be pre-configured by your builder before they become available.

There are two ways to interact with agents:

1. Type your message in the chat interface

2. Use voice commands through speech recognition

Simply select your preferred agent to bypass manual prompt creation and get instant assistance for your specific task.

How to use a Workflow

You can find the workflows in the right panel next to the chat interface:

1. You can find the Bot Settings tab on the right side of your Chat interface

2. Select to the bottom item Workflows

3. Click on the Workflows section

Starting a Workflow

1. Select your desired workflow from the list

2. Click the Play icon ▶️ to the right of the workflow

3. The workflow will run automatically

Workflow Progress

After starting, a process visualization appears in the bottom right corner of your screen:

• Current step: Marked with a loading icon ⚙️

• Completed steps: Highlighted in green ✅

• Pending steps: Shown in neutral state

This visualization allows you to track the workflow's progress in real-time.

The available workflows are pre-configured specifically for your use cases.

Activate Workflow

How to work with Insights

You can save a Chat Message as an Insight for later use or sharing purposes. Here are the steps to save and share your and the Bot's work:

1. Locate the Chat Message you want to save

2. Click the Floppydisc-Icon below the message

3. Edit your Insight if needed

   • Add additional context

   • Modify the content

   • Add tags for better organization

4. Click Save Insight to store your Insight

If you want to Contribute your Insight to a Database, just click the Contribute Insight Button below the message and choose the database to store it to.

To share an already existing Insight, click on Insights, then Contribute Insight and choose a database to store it. If the database is public, your teammates will also be able to use your Insight.

How to Connect Your Data

The Knowledge Management section, located in the right panel next to the chat interface, offers multiple options for connecting and managing your data sources.

1. Databases

• Connect to large databases from the data management tab containing chunked documents

• Ideal for extensive document collections

• Enables efficient processing of large data volumes

2. Files

• Upload individual documents

• Documents are loaded as complete units

• Perfect for maintaining document context integrity

• No chunking applied

3. Insights

• Access previously saved messages and inputs

• Utilize stored knowledge from past interactions

• Quick integration of proven solutions

4. Email Integration

• Currently supports Gmail connection only

• Access emails from your inbox and folders

• Import specific emails as insights into your context

• Note: Other email providers are not supported at this time

5. Additional Context

• Add custom context information

• Enhance your knowledge base with specific details

• Flexible integration of supplementary information

Knowledge Bots Data Flow

Benefits

• Comprehensive data integration

• Flexible access to various knowledge sources

• Seamless context enhancement

• Efficient knowledge management

Note: Choose the connection type that best suits your specific needs and data structure.