Question 1

Create and deploy an AI chatbot [No-code]

Accepted Answer

Create your custom ChatGPT to answer questions about your documents

From the dashboard view, let's click on "Create a new experiment".
Select Text based.
Click on Ask questions to your documents

Create Chatbot

Choose a name and click "Next"
Upload your documents. We currently support PDF, Word or txt files. you can drag and drop directly from your computer or a zip file containing all your documents. In this tutorial we will use a document which is the transcription of the YC Startup School video: Should You Start A Startup?

|| To transcribe the video we used the Cogniflow transcription model. To learn more read our tutorial

You can download the file directly from here.

Upload your documents or Knowledge base

Click Next Step and Run and Create Experiment.

|| Note: It takes around 3 mins to set up everything and be ready to use it. If you want to be notified when the model is ready remember to mark the check.

Try your model

Once the model is ready,

Question 2

How to use our Make integration

Accepted Answer

Integrate AI with 1000+ apps using Cogniflow and Make

Q: How to Create a Dataset for Object Detection using the YOLO Labeling Format

The YOLO (You Only Look Once) format is a specific format for annotating object bounding boxes in images for object detection tasks. In this format, each image in the dataset should have a corresponding text file with the same name as the image, containing the bounding box annotations for that image. The text file should have the following format: <img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/image_x3zdo8.png" alt="YOLO text file format" /> Where: <ul> <li><object-class> is an integer representing the class of the object. The class index should start from 0 and increase by 1 for each unique class in the dataset.</li> <li>**<x-center> **and **<y-center> **are the coordinates of the center of the bounding box, normalized by the width and height of the image, respectively. The values should be in the range of [0, 1].</li> <li><width> and <height> are the width and height of the bounding box, normalized by the width and height of the image, respectively. The values should be in the range of [0, 1].</li> </ul> Here's an example of a YOLO format annotation file for an image containing two objects, a car and a pedestrian: <img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/image_lh3pyz.png" alt="Example of YOLO format annotation" /> This means that there is a car (class 0) with its center at (0.45 x image width, 0.6 x image height), and a width and height of 0.1 x image width and 0.2 x image height, respectively. There is also a pedestrian (class 1) with its

|| Make (previously Integromat) is a no-code workflow automation platform that connects with over 1400 apps to build powerful workflows to automate any work.. Visit Make website and create a free account.

This tutorial will explain how to use our Make app integration to automate powerful workflows in Make using Cogniflow AI models.

Add Cogniflow to Your Workspace

Go to the Make platform and log in to your account.
Click on this link to install our application.
Once you're on the page, click the "Install" button, and then select the organization where you want to install the application. Once the installation is complete, a message will be displayed indicating a successful installation.

Install Make app

Use the search bar to search for the Cogniflow application using its name in your workspace.

Search Cogniflow App

Once you find our application, click on it to access the application details.
Inside the application, you will find our different modules, such as OCR English, OCR Multilingual, Text Classification, Image Classification, Audio Classification, Speech Recognition, Face Similarity, Named Entity Recognition, and

Question 3

Deploy and share your AI model as a Web App in one click

Accepted Answer

Share any AI model as a Web App or embed it into your website

|| This feature is available from the Starter Plan. If you need more information about our plans, please check the Cogniflow pricing page.

This feature allows users to create a web application (Web App) for any AI model the user has access. Users can quickly deploy their AI models as a Web App and share them with others without requiring them to have a Cogniflow account. In this article, we will provide a step-by-step guide on how to create and share a Web App.

Let's start by choosing the model you want to share. In this tutorial, we will use our "Face Similarity" model, which allows us to compare two photos and predict if it is the same person.

Go to our Public experiments and choose Face Similarity

Cogniflow Face Similarity public model

Click on Use this model!

Face Similarity: use this model

Click on the Web App tab, and then press the Publish button to create your Web App.

Face Similarity Test model page

Publish Face Similarity model

You can then copy this URL and share it with others, who will be

Question 4

Create a custom extractor

Accepted Answer

This tutorial explains how to create a Smart Extractor in Cogniflow to extract any specific text from images, text, or PDF documents.

From the dashboard view, click “Create new experiment”
In this tutorial, we will use an Image smart extractor to extract from images of PDF documents, so click on "Image based". You can use Text if you are integrating Cogniflow and getting the info from an external service like email, Twitter, WhatsApp, etc.

Image Smart Extractor

Choose a title and click “Next step”.
In this step, you have to specify the entities that you want to use as extraction criteria. For this example, let’s say we want to extract information from a receipt that you have taken a photo with your cell phone. Click on "Add manually"

Add Entity

Then, in the modal that pops up, you have to specify each field.

Define entity

Name: This is the entity or field name you want to extract, and it will be used in the output as the key identifier.
Description: This is optional, but it could be very helpful to give extra instructions to be more effective in identifying an entity that is not a common type like a date, number, or currency.
Output format: Yo

Question 5

How to Create a Dataset for Object Detection using the YOLO Labeling Format

Accepted Answer

The YOLO (You Only Look Once) format is a specific format for annotating object bounding boxes in images for object detection tasks. In this format, each image in the dataset should have a corresponding text file with the same name as the image, containing the bounding box annotations for that image. The text file should have the following format:

YOLO text file format

Where:

is an integer representing the class of the object. The class index should start from 0 and increase by 1 for each unique class in the dataset.
** **and ** **are the coordinates of the center of the bounding box, normalized by the width and height of the image, respectively. The values should be in the range of [0, 1].
and are the width and height of the bounding box, normalized by the width and height of the image, respectively. The values should be in the range of [0, 1].

Here's an example of a YOLO format annotation file for an image containing two objects, a car and a pedestrian:

Example of YOLO format annotation

This means that there is a car (class 0) with its center at (0.45 x image width, 0.6 x image height), and a width and height of 0.1 x image width and 0.2 x image height, respectively. There is also a pedestrian (class 1) with its

Question 6

How to Create an AI Service for Image Recognition

Accepted Answer

${color}[#ea5e5f]( How to Create an AI Service for Image Recognition:)

${color}[#ea5e5f](1. Login)

Make sure to visit: app.cogniflow.ai
Then log in to the platform with user and password

If you don’t have a user account please create one for free here: Sign Up

${color}[#ea5e5f](2. Dashboard)

Home page shows all the experiments that you have created. You can filter by experiment type (image, text, audio) and search

${color}[#ea5e5f](3. Create experiment I)

To create the new experiment, you have to click in the "Create new experiment" button and then select the experiment type.

${color}[#ea5e5f](4. Create experiment II)

Once you've selected the type of experiment, choose the task you need your model to develop.

In this example select "Image Classification"

${color}[#ea5e5f](5. Create experiment III)

Then you define a name and description for your experiment. Optionally, you can upload an image (E.g. company logo) for your experiment

${color}[#ea5e5f](6. Create experiment IV)

Now, it’s time t

Featured & Frequently Read Articles

Browse All Categories