The GPT-3 based OpenAI Language API is a text-in-text out API. It is not a chatbot development framework.
A chatbot development development framework demands the existence of seven elements which constitutes fine-tuning (there can be more).
- Forms & Slots
- Natural Language Generation (NLG)
- Dialog Management
The OpenAI API allows for basic training with a few lines of example utterances, giving the API a basic gist of your application.
Fine tuning is available, but again this is a way of influencing the text-out portion. And not comprehensive fine-tuning per se.
Fine-tuning in OpenAI Language API based on GPT-3 is currently in beta and might change considerably in the near future.
The OpenAI API is impressive none the less; but implementation scenarios currently is limited. Some implementation scenarios:
- A standalone general chatbot for general conversation. Or a question-and-answer Wikipedia-like chatbot.
- The second implementation is a Support API for a conventional Chatbot implementation. These can cover:
- Grammar Correction
- Text Summarization
- Parse Unstructured Data
- Extract Contact Information
- Summarize For A Second Grader
However, this is not the case with Codex…
There are a few definite use-cases for Codex as an API, ready for implementation.
Some of these use scenarios can include:
- As a general AI Assistant for general code questions by a company’s development team/s.
- A real use-case is having Codex as a bot within a Slack or Teams environment and coders can pose general questions to the Codex interface.
- As a code QA bot. This process can be automated where code is run against the Codex API and reports are generated on vulnerabilities or errors.
- Solving coding challenge and problems in certain routines.
- Establishing best practice.
- Explaining code
- Interactive Learning
- Crafting code based on Natural Language Input for developers to try out.
- Converting code from one language to another.
pip install openai
openai.api_key = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"response = openai.Completion.create(
You can see the typos in the user input, but it does not cause any fallback proliferation.
Below is the JSON response…
var arr1 = [1, 2, 3];\n
var arr2 = [4, 5, 6];\n
var arr3 = arr1.concat(arr2);\n
Codex is exceptionally good at explaining code and debugging code. Creating an application using natural language input demands that the user to break down their requirement for larger application, into smaller modules or segments.
This approach does take some time to build the application layer by layer, but allows for neat and predictable outputs.
Something small I found interesting I each segment of code is very well described with comments. The Natural Language Generation (NLG) of these comments is extremely well formed, cohered and natural sounding.
This is testament to the astute NLG capabilities of OpenAI Language API.
Subscribe to my newsletter.
NLP/NLU, Chatbots, Voice, Conversational UI/UX, CX Designer, Developer, Ubiquitous User Interfaces, Ambient…
Cobus Greyling - Medium
Read writing from Cobus Greyling on Medium. NLP/NLU, Chatbots, Voice, Conversational UI/UX, CX Designer, Developer…
OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits…
We've created an improved version of OpenAI Codex, our AI system that translates natural language to code, and we are…
OpenAI Codex: The Next Step In Conversational UI
Using Chatbots To Create Applications & Interfaces
OpenAI Codex & Conversational AI
Creating Code Using Natural Language Understanding