Features
Looking for help? Type your search string. Minimum 4 characters are required.
How to train AI with your website data using ChatBot
You can train an OpenAI model with your data using one of the two methods (requires WoowBot Pro Professional or Master License): Fine Tuning GPT Assistant We suggest using GPT Assistant as this is easier, quicker, and more flexible. It basically involves creating a GPT Assistant on the OpenAI platform and uploading your website content. Our […]
How to create OpenAI API Key
The OpenAI API uses API keys for authentication. Visit your API Keys page to retrieve the API key you’ll use in your requests.Remember that your API key is a secret! Do not share it with others or expose it in any client-side code (browsers, apps). Production requests must be routed through your own backend server […]
How can I Fine Tune or Train my own OpenAI?
To train Open AI a. To train or fine tune a model, 1st you need to: Gather the necessary data you want to train with Format the data correctly according to OpenAI API requirements (Download sample data format to see how it works). A dataset should have a at least 500 rows to offer useful […]
Can PDFs be used as a database with AI?
Yes, you can use PDFs to train your AI chatbot. This is possible with GPT Assistant. You can upload up to 20 PDF, TXT, or Word files to your GPT Assistant. GPT Assistant converts your uploaded files to a Vector database and uses the data within to generate relevant responses for the user queries. This […]
Conversational Forms with OpenAI
Now you can use Conversational Forms with OpenAI. You can create a Conversational form with as many fields as you want and add an Instruction for the OpenAI to respond acordingly. The user submitted field data along with your instructions will be sent to OpenAI. The OpenAI’s response will be shown when the user reaches […]
Frequency Penalty
Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.
Getting Started with OpenAI
Once you add the OpenAI API key, it should already start working for generic questions. Open a new browser window in Incognito mode and test by asking “What is the capital of Russia?” Please make sure DialogFlow is Disabled if you want OpenAI to work You can upload your own training date as a […]
How much does OpenAI or AI services cost?
OpenAI API usage exact cost is a little hard to determine as it depends on the required response length and some other factors. However, a very rough estimate would be 2US$/thousand responses if you use the GPT 4o or 4.1 mini model. You can also set the usage limit on the OpenAI platform. It is […]
How to save money and reduce OpenAI API cost for your ChatBot
If your website has a lot of traffic OpenAI API cost can shoot up quickly for your ChatBot trying to answer all your user questions. You can dramatically decrease the OpenAI API cost by using our WoowBot chatbot for WordPress’s default features which are free in combination with OpenAI. How? It is easy. For the […]
How WoowBot ChatBot Free users can Get Customized Results from the ChatBot? How to Train the ChatBot?
WoowBot ChatBot Free and WoowBot Pro Starter license users can Get Customized Results from the ChatBot in multiple ways. When the ChatBot is first activated, only the Site search option will work. The site search feature will show a list of web page links that match the user’s queries. You can create Simple Text Responses […]
My OpenAi does not work
Please check your settings( i.e: Api keys, Max token etc.). Depending on the model (GPT3 was maximum 4000 other is 1,951 ) used, requests can use up to 4097 tokens shared between prompt and completion. If your prompt is 4000 tokens, your completion can be 97 tokens at most. Also check the dialogflow is inactive. […]
OpenAI Settings
There are options for Open AI Settings. The settings are AI Settings, there are the dropdown options to select.
Presence Penalty
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.
