Do you know the best chatbot for your website?Last updated by Chloe Lin [SSW] 20 days ago.See history
A chatbot is a computer program that uses artificial intelligence to engage in text or voice conversations with users, often to answer questions, provide assistance, or automate tasks. In the age of Generative AI, good chatbots have become a necessary part of the User Experience.
Choosing the right chatbot service for your website can be a challenging task. With so many options available it's essential to find the one that best fits your needs and provides a good experience for your users. But what distinguishes a good chatbot from a great one? Here are some factors to consider.
Custom Built vs 3rd Party Service
- Control vs Effort: Custom built provides more control but incurs high development effort & cost
- Cost per message: may be lower in custom built solutions for high volume of traffic
- Responses: Smooth and natural responses that answer questions while understanding context.
- Visual Design: Aligns with brand aesthetics.
- Content Tailoring: Adapts responses to fit brand voice.
- Pre-built Templates: Speeds up deployment.
- Drag-and-Drop Builders: Simplifies creation without coding.
- Documentation & Support: Assists in development.
Ease of Access
- Multi-Platform: Seamless functionality on desktop and mobile.
- Messaging App Integration: Works with apps like WhatsApp, Messenger.
- Language Support: Multilingual for global reach.
Research and Training
- API Support: API integration for third-party applications.
- Data Syncing: Real-time synchronization for up-to-date responses.
- Traffic Management: Handles varying user traffic levels.
- Data Storage: Manages increasing user data.
- Adaptive Responses: Adjusts to unexpected user inputs.
- Feedback Loop: Improves from past interactions.
- Human Agent Referral: Transfers smoothly to a human if needed.
Resilience to Trick Questions
- Response Filtering: Identifies misleading questions.
- Learning from Mistakes: Improves trick question handling.
The first decision is to choose between using a 3rd party chatbot service such as ChatBase/Botpress vs developing your own from scratch using the OpenAI API. The table below gives a summary of how these two options compare.
|Development effort and cost
|Cost to Train
|Knowledge Base Limits
|Limited but Sufficient
|Cost per Message
Before delving deeper into the comparison it would help to first understand the steps involved in building chatbots using either technology.
Steps to create chatbot using a 3rd Party service
For e.g. in Chatbase you would:
- Train the bot by providing links to your web pages or by uploading docs
- Craft a pointed prompt to give it instructions on how to respond to the user. For e.g. you can ask it to share URLs to your web pages when appropriate
- Choose a GPT model – GPT-4 highly recommended
- Configure the chatbot for features such as a greeting msg, company logo, chat bubble colours, etc.
Steps to create chatbot using the OpenAI API
The following provides a very high level description of creating a chatbot from scratch using the OpenAI API. For a more in-depth explanation please watch:Video: Exploring the Capabilities of ChatGPT | Calum Simpson | User Group (132 mins)
- Convert your knowledge base into embeddings
- Store embeddings and their corresponding text content in a vector database
Setup a server that can do the following
- Convert user query into an embedding
- Lookup vector database to find embeddings that are closest to the embedding created out of user query
- Insert the content corresponding to the matching embeddings into the OpenAI System message
- Pass recent user chat history to the OpenAI API
- Wait for OpenAI to generate a response. Present the response to the user.
- Create a chatbot front-end widget
As you can see, developing a chatbot from scratch using the OpenAI API requires significant development effort and expertise. 3rd party chatbots on the other hand are much easier to program, embed on your website, and integrate with the Generative AI backend. As a rough estimate assume it will take a developer 20 days to build a custom chatbot from the ground up. If the developer costs $1000/day, this totals to $20K up front cost. Assuming a $399/month subscription of Chatbase on the other hand, it would take the custom solution over 4 years just to break even.
However, custom built chatbots provide a lot more control in how you train the AI model, what content you match the user query with, and what system message you provide the GPT engine to respond to a user’s query. You don’t get this level of control with 3rd party chatbots. The backend of custom built solutions can also be leveraged to serve multiple chatbots supporting completely different use cases. For e.g. one chatbot could provide basic company info to visitor’s on the company website, while a second chatbot could help employees find info on the company Intranet.
Cost to train the chatbot on your knowledge base is very inexpensive in both options. For example, you can train a chatbot on ~3000 pages for less than $1 USD using the OpenAI Embeddings model. Another factor is any limits on the size of the knowledge base. While there’s a limit on this in 3rd party chatbots the size should normally be more than enough. For e.g., Chatbase provides you 11M characters, which roughly equates to ~3500 pages of text of 600 words each.
The cost per message is generally much higher in 3rd party services. For e.g., as of Sep 2023, the highest paid plan in Chatbase that uses GPT-4 only gives you 2000 msgs/month for $399. If you exceed this limit, it gives you the option to use your OpenAI API key, but doesn’t disclose if this will cost exactly the same as what OpenAI charges. So for very high volumes of chatbot traffic, it’s worthwhile to evaluate creating your own chatbot using OpenAI API.
|❌ Traditional style of workflow and steep learning curve
|✅ Wide range of integrations
|✅ Free to start
|✅ Does everything with prompt engineering
|✅ Easy customization
|❌ Limited free plan options
Making the right choice
While both platforms offer unique features, Chatbase stands out as the superior choice in most instances. Here's why:
- Chatbase allows easy customization and integration with various tools
- Chatbase's user-friendly interface makes it accessible to a wide range of users. A prompt engineer can setup, tweak and improve the system. No development required
- Botpress lacks the intuitive interface of Chatbase, and is more prone non-sequeter conversation without extensive workflow development and testing