How to implement

Pre-Requisites

Implementation

Content Security Policy

Ecosystem

FireChatbot Engine

Databases

Knowledge Base

Analytics Database

APIs

Chat API

Config APi

Models

How to implement your Chatbot

Pre-Requisites

Start designing your Chatbot directly on the FireChatbot Homepage
Sign Up to FireChatbot - You will then get a Dashboard and the Chatbot you designed on the FireChatbot homepage will be moved into your account

Implementation

Click on the "Implement Bot" Button on the bottom of the navigation bar inside your Dashboard. It will open up a window, that displays a script tag, that contains your Chatbot ID. You copy & paste this script tag to the bottom of the body of every page on your website, that should display the Chatbot.

HTML


                          <html>

                            <head>...</head>

                            <body>

                              ...

                              <script src="https://firechatbot.com/chatbot.js?id=[YOUR CHATBOT ID]">

                            </body>

                          </html>

Implement with Content Security Policy

If you use a Content Security Policy on your website, you have to add the following CSP to your website's HTTP header or tag to allow the Chatbot to work properly:

HTTP


                          Content-Security-Policy:

                              default-src 'self'; script-src 'self' https://firechatbot.com;

                              connect-src 'self' https://firechatbot.com;

                              img-src 'self' https://firechatbot.com;

                              style-src 'self' 'unsafe-inline';

                              font-src 'self' https://firechatbot.com;

The FireChatbot ecosystem

The FireChatbot engine consists of a number of different systems, that allow for it's industry-leading performance, Analytics capabilities and self-maintenance to reduce the operational effort to 0, while delivering maximum performance.

FireChatbot Engine

All systems are located in Frankfurt, Germany.

Databases

Knowledge Base

Stores the knowledge, that your Chatbot uses to answer questions
Activated every time a user asks a question
Stores website texts & custom text documents
Provides infinite storage for every Chatbot

Datapoints

 
              [{

                  id: "Generic ID",

                  type: "website | document",

                  text: "Your website's or document's text",

                  title: "Your website's url or your document's title",

                  lastUpdate: "Last update of your document or website"

              },...]

Analytics Database

Stores quantitative & qualitative Analytics data, that is displayed inside the Dashboard
Activated every time a User visits your website
Stores URL, referer, location of the user and counts visits & chatbot activations
Stores chats along with sentiment analysis
Does not generate any IDs or user profiles

Datapoints


                  Visit Database: 
[{

                      chatbotID: "Your Chatbot ID",

                      visits_[data]_[time]: "Number of visits",

                      visits_[data]_[time]_[country]: "Number of visits per country",

                      visits_[data]_[time]_[url]: "Number of visits per URL"

             
                  },...]

Chat Database: 
[{

                      chatbotID: "Your Chatbot ID",

                      country: "Country of the user",

                      latitude: "Latitude of the user",

                      longitude: "Longitude of the user",

                      date: "Start date of the chat",

                      endtime: "Time of the last message",

                      messages: "[User and bot messages, excluding images]",

                      page: "URL of the page",

                      probability: "Probability of buying the product (AI generated)",

                      sentiment: "Sentiment of the chat (AI generated)",

                      summary: "Summary of the chat (AI generated)",

                      title: "Title of the chat (AI generated)"

                  },...]

APIs

Chat API

Activated every time a user asks your Chatbot a question
Chat history, including latest question, is sent to the API
Knowledge is retrieved from Knowledge Base
Chat history & knowledge are transferred to the AI model
Updated chat history is sent back to client and to Analytics Database (see previous chapter)

API Schema


      Request: 
{

          chatbotID: "Your Chatbot ID",

          messages: "[All messages of the current chat]",

          instructions: "custom instructions to adapt chatbot behavior (optional)"

 
      }

Response: 
[{

          data: {

            message: "Text chunk from response stream",

          }

      },...]

Chat API, Knowledge Base and Analytics DB are located in Frankfurt, Germany.

Config API

Activated every time a user vsits a website, that includes your Chatbot
Sends visit information to the Analytics Database (see previous chapter)
Retrieves your Chatbot's configuration from the Config Database

API Schema


                          Request: 
{

                              chatbotID: "Your Chatbot ID",

                              messages: "[All messages of the current chat]",

                              instructions: "custom instructions to adapt chatbot behavior (optional)"

                     
                          }

Response: 
[{

                              data: {

                                message: "Text chunk from response stream",

                              }

                          },...]

Config API, Config Database and Analytics DB are located in Frankfurt, Germany.

AI Models

AI Model Ecosystem

The FireChatbot engine uses a number of different AI models, depending on the amount of content on your website, the type of content, that is uploaded with a user question and current model availability. These are the models, that are used by FireChatbot:

GPT-4o

Preferred for complex websites and questions
Preferred, if user uploads images to the Chatbot

Gemini 1.5

Preferred for very big websites
Preferred, if user uploads files

LLama 3

Preferred for smaller websites
By far the fastest model

Discover FireChatbot

Fit your Chatbot to your brand identity.

Leverage quantitative and semantic Analytics.

Your new Chatbot is waiting.

How to implement your Chatbot

Pre-Requisites

Implementation

Implement with Content Security Policy

The FireChatbot ecosystem

FireChatbot Engine

Databases

Knowledge Base

Analytics Database

APIs

Chat API

Config API

AI Models

AI Model Ecosystem

GPT-4o

Gemini 1.5

LLama 3

No Credit Card

3 Month Trial

All-in-one Pass

Make it Yours