向量嵌入 (Vector embeddings)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
from openai import OpenAI
import numpy as np

client = OpenAI()

def normalize_l2(x):
    x = np.array(x)
    if x.ndim == 1:
        norm = np.linalg.norm(x)
        if norm == 0:
            return x
        return x / norm
    else:
        norm = np.linalg.norm(x, 2, axis=1, keepdims=True)
        return np.where(norm == 0, x, x / norm)


response = client.embeddings.create(
    model="text-embedding-3-small", input="Testing 123", encoding_format="float"
)

cut_dim = response.data[0].embedding[:256]
norm_dim = normalize_l2(cut_dim)

print(norm_dim)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
query = f"""Use the below article on the 2022 Winter Olympics to answer the subsequent question. If the answer cannot be found, write "I don't know."

Article:
\"\"\"
{wikipedia_article_on_curling}
\"\"\"

Question: Which athletes won the gold medal in curling at the 2022 Winter Olympics?"""

response = client.chat.completions.create(
    messages=[
        {'role': 'system', 'content': 'You answer questions about the 2022 Winter Olympics.'},
        {'role': 'user', 'content': query},
    ],
    model=GPT_MODEL,
    temperature=0,
)

print(response.choices[0].message.content)

1
2
3
4
5
6
7
8
9
from openai.embeddings_utils import get_embedding, cosine_similarity

def search_reviews(df, product_description, n=3, pprint=True):
    embedding = get_embedding(product_description, model='text-embedding-3-small')
    df['similarities'] = df.ada_embedding.apply(lambda x: cosine_similarity(x, embedding))
    res = df.sort_values('similarities', ascending=False).head(n)
    return res

res = search_reviews(df, 'delicious beans', n=3)

1
2
3
4
5
6
7
8
9
10
11
12
from openai.embeddings_utils import get_embedding, cosine_similarity

df['code_embedding'] = df['code'].apply(lambda x: get_embedding(x, model='text-embedding-3-small'))

def search_functions(df, code_query, n=3, pprint=True, n_lines=7):
    embedding = get_embedding(code_query, model='text-embedding-3-small')
    df['similarities'] = df.code_embedding.apply(lambda x: cosine_similarity(x, embedding))

    res = df.sort_values('similarities', ascending=False).head(n)
    return res

res = search_functions(df, 'Completions API tests', n=3)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
def recommendations_from_strings(
    strings: List[str],
    index_of_source_string: int,
    model="text-embedding-3-small",
) -> List[int]:
    """Return nearest neighbors of a given string."""

    # get embeddings for all strings
    embeddings = [embedding_from_string(string, model=model) for string in strings]

    # get the embedding of the source string
    query_embedding = embeddings[index_of_source_string]

    # get distances between the source embedding and other embeddings (function from embeddings_utils.py)
    distances = distances_from_embeddings(query_embedding, embeddings, distance_metric="cosine")

    # get indices of nearest neighbors (function from embeddings_utils.py)
    indices_of_nearest_neighbors = indices_of_nearest_neighbors_from_distances(distances)
    return indices_of_nearest_neighbors

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
import pandas as pd
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
import matplotlib

df = pd.read_csv('output/embedded_1k_reviews.csv')
matrix = df.ada_embedding.apply(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)

colors = ["red", "darkorange", "gold", "turquiose", "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)
plt.title("Amazon ratings visualized in language using t-SNE")

1
2
3
4
5
6
7
8
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(
    list(df.ada_embedding.values),
    df.Score,
    test_size = 0.2,
    random_state=42
)

1
2
3
4
5
from sklearn.ensemble import RandomForestRegressor

rfr = RandomForestRegressor(n_estimators=100)
rfr.fit(X_train, y_train)
preds = rfr.predict(X_test)

1
2
3
4
5
6
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, accuracy_score

clf = RandomForestClassifier(n_estimators=100)
clf.fit(X_train, y_train)
preds = clf.predict(X_test)

1
2
3
4
5
6
7
8
9
10
11
12
from openai.embeddings_utils import cosine_similarity, get_embedding

df= df[df.Score!=3]
df['sentiment'] = df.Score.replace({1:'negative', 2:'negative', 4:'positive', 5:'positive'})

labels = ['negative', 'positive']
label_embeddings = [get_embedding(label, model=model) for label in labels]

def label_score(review_embedding, label_embeddings):
    return cosine_similarity(review_embedding, label_embeddings[1]) - cosine_similarity(review_embedding, label_embeddings[0])

prediction = 'positive' if label_score('Sample Review', label_embeddings) > 0 else 'negative'

user_embeddings = df.groupby('UserId').ada_embedding.apply(np.mean)
prod_embeddings = df.groupby('ProductId').ada_embedding.apply(np.mean)

1
2
3
4
5
6
7
8
9
import numpy as np
from sklearn.cluster import KMeans

matrix = np.vstack(df.ada_embedding.values)
n_clusters = 4

kmeans = KMeans(n_clusters = n_clusters, init='k-means++', random_state=42)
kmeans.fit(matrix)
df['Cluster'] = kmeans.labels_