docs.cogniflow.ai

DNS Records

Google Analytics

Analytics

Crisp

Support

Services

JSON+LD

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Create and deploy an AI chatbot [No-code]","acceptedAnswer":{"@type":"Answer","text":"<h3 id="createyourcustomchatgpttoanswerquestionsaboutyourdocuments">Create your custom ChatGPT to answer questions about your documents</h3>\n<ol>\n<li>From the dashboard view, let's click on "Create a new experiment".</li>\n<li>Select <strong>Text based</strong>.</li>\n<li>Click on <strong>Ask questions to your documents</strong></li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/createchatbotexperiment_b4u0ro.png" alt="Create Chatbot" /></p>\n<ol start="4">\n<li>Choose a name and click <strong>"Next"</strong></li>\n<li>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: <a href="https://www.youtube.com/watch?v=BUE-icVYRFU">Should You Start A Startup?</a></li>\n</ol>\n<p>|| To transcribe the video we used the Cogniflow transcription model. To learn more read <a href="/en/article/how-to-transcribe-an-audio-with-speaker-recognition-using-cogniflow-api-and-webhooks-dfbt0t/">our tutorial</a></p>\n<p>You can download the file directly from <a href="https://www.dropbox.com/scl/fi/81fjodkx17k7hb3lsqg45/Should_you_start_a_startup.txt?rlkey=4awwqg6onknx8qfzy3drausc2&dl=1">here</a>.</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/uploaddocument_1i53gy8.png" alt="Upload your documents or Knowledge base" /></p>\n<ol start="6">\n<li>Click <strong>Next Step</strong> and <strong>Run and Create Experiment</strong>.</li>\n</ol>\n<p>|| 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.</p>\n<h3 id="tryyourmodel">Try your model</h3>\n<p>Once the model is ready,</p>"}},{"@type":"Question","name":"Create your Info Smart Extractor using AI","acceptedAnswer":{"@type":"Answer","text":"<p>This tutorial explains how to create a <strong>Smart Extractor</strong> in Cogniflow to extract any specific text from images, text, or PDF documents.</p>\n<ol>\n<li>From the dashboard view, click “New Project”</li>\n<li>In this tutorial, select "Image and PDF" to extract from images of PDF documents. Please use <strong>Plain Text</strong> if you are planning to integrate Cogniflow with services that typically use text as input such as Gmail, X, WhatsApp, etc.</li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/selectsmartextractor_m4tyj3.png" alt="Select Smart Extractor project" /></p>\n<ol start="3">\n<li>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"</li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/addentitiesempty_oq2gty.png" alt="Define the entities you want to extract" /></p>\n<ol start="4">\n<li>Then, in the modal that pops up, you have to specify each field.</li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/receiptdateentity_39essh.png" alt="Define entity" /></p>\n<ul>\n<li><strong>Name:</strong> This is the entity or field name you want to extract, and it will be used in the output as the key identifier.</li>\n<li><strong>Description:</strong> 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.</li>\n<li><strong>Output format:</strong> You can use this to convert an e</li>\n</ul>"}},{"@type":"Question","name":"Deploy and share your AI model as a Web App in one click","acceptedAnswer":{"@type":"Answer","text":"<h1 id="shareanyaimodelasawebapporembeditintoyourwebsite">Share any AI model as a Web App or embed it into your website</h1>\n<p>|| <strong>This feature is available from the Starter Plan</strong>.  If you need more information about our plans, please check the <a href="https://www.cogniflow.ai/pricing">Cogniflow pricing page</a>. </p>\n<p>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.</p>\n<p>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.</p>\n<ol>\n<li>Go to our Public experiments and choose <strong>Face Similarity</strong></li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/1_1l6rww2.png" alt="Cogniflow Face Similarity public model" /></p>\n<ol start="2">\n<li>Click on <strong>Use this model!</strong></li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/2_1yup242.png" alt="Face Similarity: use this model" /></p>\n<ol start="3">\n<li>Click on the <strong>Web App</strong> tab, and then press the <strong>Publish</strong> button to create your Web App.</li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/3_onx3sb.png" alt="Face Similarity Test model page" /></p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/4_89ychp.png" alt="Publish Face Similarity model" /></p>\n<ol start="4">\n<li>You can then copy this URL and share it with others, who will be</li>\n</ol>"}},{"@type":"Question","name":"How to use our Make integration","acceptedAnswer":{"@type":"Answer","text":"<h1 id="integrateaiwith1000appsusingcogniflowandmake">Integrate AI with 1000+ apps using Cogniflow and Make</h1>\n<p>|| 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 <a href="https://www.make.com">Make website</a> and create a free account.</p>\n<p>This tutorial will explain how to use our Make app integration to automate powerful workflows in Make using Cogniflow AI models.</p>\n<h3 id="addcogniflowtoyourworkspace">Add Cogniflow to Your Workspace</h3>\n<ol>\n<li>Go to the Make platform and log in to your account.</li>\n<li>Click on this <a href="https://www.make.com/en/hq/app-invitation/a31be3e78f67e918824906ba066606e2">link to install our application</a>.</li>\n<li>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.</li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/make1_y74c52.png" alt="Install Make app" /></p>\n<ol start="4">\n<li>Use the search bar to search for the Cogniflow application using its name in your workspace.</li>\n</ol>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/make2_1lkxo78.png" alt="Search Cogniflow App" /></p>\n<ol start="5">\n<li>Once you find our application, click on it to access the application details.</li>\n<li>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</li>\n</ol>"}},{"@type":"Question","name":"Chatbot WhatsApp Integration","acceptedAnswer":{"@type":"Answer","text":"<p>This guide will help you use your Cogniflow Chatbot in WhatsApp.</p>\n<h3 id="1createawhatsappmetaapp">1. Create a WhatsApp Meta App</h3>\n<p>First you need to create a Meta App in Meta for Developers platform. Create or login to your account <a href="https://developers.facebook.com/">here</a></p>\n<p>Go to “My Apps” and click on “Create App”</p>\n<p>Select Other</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/meta-select-other_z1ob8n.png" alt="Create App Other" /></p>\n<p>Select Business</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/screenshot-2024-04-15-at-12340_b6ud0g.png" alt="Business" /></p>\n<p>Name your App, add your email and click on Create app</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/meta-app-create-app-details_16ievzv.png" alt="Meta Create App Details" /></p>\n<p>then scroll down to find <strong>WhatsApp</strong> and click Set up</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/meta-app-whatsapp-setup_1fohy98.png" alt="Meta App WhatsApp Setup" /></p>\n<h3 id="2generatetokentoconnecttocogniflow">2. Generate Token to connect to Cogniflow</h3>\n<p>To continue you need a business Meta account. If you have already one you will see it there to select, if not go to <a href="https://business.facebook.com/">Meta Business Suite</a></p>\n<p>Under your Meta Business Suite, go to Users → <a href="https://business.facebook.com/settings/system-users">System users</a></p>\n<p>Add an new user for example “admin” with the role “Admin”.</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/system-users_14xuxec.png" alt="Meta System Users" /></p>\n<p>After creating the user, click on “Assign Assets”, go </p>"}},{"@type":"Question","name":"How to Create a Dataset for Object Detection using the YOLO Labeling Format","acceptedAnswer":{"@type":"Answer","text":"<p>The <strong>YOLO (You Only Look Once)</strong> 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:</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/image_x3zdo8.png" alt="YOLO text file format" /></p>\n<p>Where:</p>\n<ul>\n<li><p><strong><object-class></strong> 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.</p></li>\n<li><p>**<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].</p></li>\n<li><p><strong><width></strong> and <strong><height></strong> 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].</p></li>\n</ul>\n<p>Here's an example of a YOLO format annotation file for an image containing two objects, <em>a car</em> and a <em>pedestrian</em>:</p>\n<p><img src="https://storage.crisp.chat/users/helpdesk/website/447a0bfe5ea4e800/image_lh3pyz.png" alt="Example of YOLO format annotation" /></p>\n<p>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 </p>"}}]}

(this JSON isn't valid)