Demo Building Dynamic Context with Custom Data Part 1

pip install pandas numpy openai

import os
import pandas as pd
import numpy as np
import openai

# Load API key
openai.api_key = os.getenv("OPENAI_API_KEY")

def text_embedding(text) -> list[float]:
    """
    Generate embeddings using OpenAI.
    """
    response = openai.Embedding.create(
        model="text-embedding-ada-002",
        input=text
    )
    return response["data"][0]["embedding"]

def get_word_completion(prompt: str) -> str:
    """
    Query GPT-3.5 Turbo for Oscar-related questions.
    """
    messages = [
        {"role": "system", "content": "You answer questions about the 95th Oscar awards."},
        {"role": "user",   "content": prompt},
    ]
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=messages,
        max_tokens=3000,
        n=1
    )
    return response.choices[0].message.content

# Load the dataset
df = pd.read_csv("data/oscars.csv")
df.head()

# 1. Keep only the 2023 ceremony
df = df[df["year_ceremony"] == 2023]

# 2. Remove entries with no film listed
df = df.dropna(subset=["film"])

# 3. Convert category names to lowercase
df["category"] = df["category"].str.lower()

print(df.shape)  # Expect (121, 7)

def make_context(row) -> str:
    status = "and won the award" if row["winner"] else "but did not win"
    return (
        f"{row['name']} got nominated under the category {row['category']} "
        f"for the film {row['film']} {status}"
    )

df["text"] = df.apply(make_context, axis=1)
df.head(3)

# Example entry #12
print(df["text"].iloc[11])
# Ana de Armas got nominated under the category actress in a leading role
# Example entry #101
print(df["text"].iloc[100])
# Viktor Prášil, Frank Kruse, Markus Stemler, Lars Ginzel and Stefan Korte
# got nominated under the category sound for the film All Quiet on the Western Front
# but did not win