【HELP!】I want to build a chatbot that knows everything about me!

Documentation
1

Hello community members.

I am looking to create a chatbot that will read my information into GPT-3 and output my personal information.

I want to give that QR code to every businessman I meet!
Because it’s so current and cool!!!

So I want to run the following program in GOOGLE COLAB, but although it reads the data, it only outputs what GPT-3 has learned from the beginning.

What do you think the problem is?

I’d love to borrow some of your genius brains!

!pip install openai

import openai
import csv

API

openai.api_key = “xxxxx”

input CSV

questions =
answers =

with open(“xxx.csv”, “r”) as f:
reader = csv.reader(f)
for row in reader:
questions.append(row[0])
answers.append(row[1])

def generate_answer(prompt):
completions = openai.Completion.create(
engine=“text-davinci-002”,
prompt=prompt,
max_tokens=1000,
n=1,
stop=None,
temperature=0.5,
)

message = completions.choices[0].text
return message.strip()

input

for i in range(len(questions)):
prompt = questions[i]
answer = generate_answer(prompt)

print(f"question: {prompt}")
print(f"answer: {answer}")
print()
2

Welcome to the community!

Have you read the Docs on the API, particularly on fine-tuning?

The language models cannot “remember” anything other than the prompt they’re fed which is why fine-tuning is popular among some.

Hope this helps.