import openai

embedding = openai.Embedding.create(
    input="Your text goes here", model="text-embedding-3-small"
)["data"][0]["embedding"]
len(embedding)

# Negative example (slow and rate-limited)
import openai

num_embeddings = 10000 # Some large number
for i in range(num_embeddings):
    embedding = openai.Embedding.create(
        input="Your text goes here", model="text-embedding-3-small"
    )["data"][0]["embedding"]
    print(len(embedding))


# Best practice
import openai
from tenacity import retry, wait_random_exponential, stop_after_attempt

# Retry up to 6 times with exponential backoff, starting at 1 second and maxing out at 20 seconds delay
@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))
def get_embedding(text: str, model="text-embedding-3-small") -> list[float]:
    return openai.Embedding.create(input=[text], model=model)["data"][0]["embedding"]

embedding = get_embedding("Your text goes here", model="text-embedding-3-small")
print(len(embedding))

import pandas as pd
from sklearn.manifold import TSNE
import numpy as np
from ast import literal_eval

# Load the embeddings
datafile_path = "data/fine_food_reviews_with_embeddings_1k.csv"
df = pd.read_csv(datafile_path)

# Convert to a list of lists of floats
matrix = np.array(df.embedding.apply(literal_eval).to_list())

# Create a t-SNE model and transform the data
tsne = TSNE(n_components=2, perplexity=15, random_state=42, init='random', learning_rate=200)
vis_dims = tsne.fit_transform(matrix)
vis_dims.shape

import matplotlib.pyplot as plt
import matplotlib
import numpy as np

colors = ["red", "darkorange", "gold", "turquoise", "darkgreen"]
x = [x for x,y in vis_dims]
y = [y for x,y in vis_dims]
color_indices = df.Score.values - 1

colormap = matplotlib.colors.ListedColormap(colors)
plt.scatter(x, y, c=color_indices, cmap=colormap, alpha=0.3)
for score in [0,1,2,3,4]:
    avg_x = np.array(x)[df.Score-1==score].mean()
    avg_y = np.array(y)[df.Score-1==score].mean()
    color = colors[score]
    plt.scatter(avg_x, avg_y, marker='x', color=color, s=100)

plt.title("Amazon ratings visualized in language using t-SNE")

# Load the dataset and query embeddings
import pandas as pd
samples = pd.read_json("data/dbpedia_samples.jsonl", lines=True)
categories = sorted(samples["category"].unique())
print("Categories of DBpedia samples:", samples["category"].value_counts())

from utils.embeddings_utils import get_embeddings
# NOTE: The following code will send a query of batch size 200 to /embeddings
matrix = get_embeddings(samples["text"].to_list(), model="text-embedding-3-small")

# Reduce the embedding dimensionality
from sklearn.decomposition import PCA
pca = PCA(n_components=3)
vis_dims = pca.fit_transform(matrix)
samples["embed_vis"] = vis_dims.tolist()

# Plot the embeddings of lower dimensionality
%matplotlib widget
import matplotlib.pyplot as plt
import numpy as np

fig = plt.figure(figsize=(10, 5))
ax = fig.add_subplot(projection='3d')
cmap = plt.get_cmap("tab20")

# Plot each sample category individually such that we can set label name.
for i, cat in enumerate(categories):
    sub_matrix = np.array(samples[samples["category"] == cat]["embed_vis"].to_list())
    x=sub_matrix[:, 0]
    y=sub_matrix[:, 1]
    z=sub_matrix[:, 2]
    colors = [cmap(i/len(categories))] * len(sub_matrix)
    ax.scatter(x, y, zs=z, zdir='z', c=colors, label=cat)

ax.set_xlabel('x')
ax.set_ylabel('y')
ax.set_zlabel('z')
ax.legend(bbox_to_anchor=(1.1, 1))