Explain Python Code (official example)
Prefilling the response with an open bracket can help. Add “Do not output preamble or explanations.” and it follows it pretty well.
Tag: user-prompt
Schema definition
openapi: 3.0.1
info:
title: TODO Action
description: An action that allows the user to create and manage a TODO list using a GPT.
version: ‘v1’
servers:
– url: https://example.com
paths:
/to
Consequential flag
paths:
/todo:
get:
operationId: getTODOs
description: Fetches items in a TODO list from the API.
security: []
post:
operationId: updateTODOs
description: Mutate
URL option
[
“https://example.com/f/dca89f18-16d4-4a65-8ea2-ededced01646”,
“https://example.com/f/01fad6b0-635b-4803-a583-0f678b2e6153”
]
OpenAPI Example
/createWidget:
post:
operationId: createWidget
summary: Creates a widget based on an image.
description: Uploads a file reference using its file id. This file should be an image
Get more referrals using AI ideas
Analyze [product] and generate 10 unique ideas on how to encourage customers to refer others. The ideas should focus on adding value to existing customers as a reward for their referrals.
product = [
How can I tell how many tokens a string has before I embed it?
import tiktoken
def num_tokens_from_string(string: str, encoding_name: str) -> int:
“””Returns the number of tokens in a text string.”””
encoding = tiktoken.get_encoding(encoding_name)
nu
Obtaining the embeddings
from openai import OpenAI
client = OpenAI()
def get_embedding(text, model=”text-embedding-3-small”):
text = text.replace(“\n”, ” “)
return client.embeddings.create(input = [text], model=model).
Step 1: Set up curl
export OPENAI_API_KEY=’your-api-key-here’
Building a question answer system with your embeddings
import numpy as np
from openai.embeddings_utils import distances_from_embeddings
df=pd.read_csv(‘processed/embeddings.csv’, index_col=0)
df[’embeddings’] = df[’embeddings’].apply(eval).apply(np.array