Text embeddings

# Scenario: When building document vectors for a search engine, you can add an instruction to optimize the vector quality for retrieval.
resp = dashscope.TextEmbedding.call(
  model="text-embedding-v4",
  input="Research papers on machine learning",
  text_type="query",
  instruct="Given a research paper query, retrieve relevant research paper"
)

import dashscope
import numpy as np
from dashscope import TextEmbedding

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

def cosine_similarity(a, b):
  """Calculate cosine similarity"""
  return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

def semantic_search(query, documents, top_k=5):
  """Perform semantic search"""
  # Generate the query vector
  query_resp = TextEmbedding.call(
  model="text-embedding-v4",
  input=query,
  dimension=1024
  )
  query_embedding = query_resp.output['embeddings'][0]['embedding']

  # Generate the document vectors
  doc_resp = TextEmbedding.call(
  model="text-embedding-v4",
  input=documents,
  dimension=1024
  )

  # Calculate similarities
  similarities = []
  for i, doc_emb in enumerate(doc_resp.output['embeddings']):
    similarity = cosine_similarity(query_embedding, doc_emb['embedding'])
    similarities.append((i, similarity))

  # Sort and return the top_k results
  similarities.sort(key=lambda x: x[1], reverse=True)
  return [(documents[i], sim) for i, sim in similarities[:top_k]]

# Example usage
documents = [
  "Artificial intelligence is a branch of computer science",
  "Machine learning is an important method for achieving artificial intelligence",
  "Deep learning is a subfield of machine learning"
]
query = "What is AI?"
results = semantic_search(query, documents, top_k=2)
for doc, sim in results:
  print(f"Similarity: {sim:.3f}, Document: {doc}")

import dashscope
import numpy as np
from dashscope import TextEmbedding

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

def cosine_similarity(a, b):
  """Calculate cosine similarity"""
  return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
def build_recommendation_system(user_history, all_items, top_k=10):
  """Build a recommendation system"""
  # Generate user history vectors
  history_resp = TextEmbedding.call(
  model="text-embedding-v4",
  input=user_history,
  dimension=1024
  )

  # Calculate the user preference vector (by averaging)
  user_embedding = np.mean([
  emb['embedding'] for emb in history_resp.output['embeddings']
  ], axis=0)

  # Generate all item vectors
  items_resp = TextEmbedding.call(
  model="text-embedding-v4",
  input=all_items,
  dimension=1024
  )

  # Calculate recommendation scores
  recommendations = []
  for i, item_emb in enumerate(items_resp.output['embeddings']):
    score = cosine_similarity(user_embedding, item_emb['embedding'])
    recommendations.append((all_items[i], score))

  # Sort and return the recommendation results
  recommendations.sort(key=lambda x: x[1], reverse=True)
  return recommendations[:top_k]

# Example usage
user_history = ["Science Fiction", "Action", "Suspense"]
all_movies = ["Future World", "Space Adventure", "Ancient War", "Romantic Journey", "Superhero"]
recommendations = build_recommendation_system(user_history, all_movies)
for movie, score in recommendations:
  print(f"Recommendation Score: {score:.3f}, Movie: {movie}")

# scikit-learn is required: pip install scikit-learn
import dashscope
import numpy as np
from sklearn.cluster import KMeans

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

def cluster_texts(texts, n_clusters=2):
  """Cluster a set of texts"""
  # 1. Get the vectors for all texts
  resp = dashscope.TextEmbedding.call(
  model="text-embedding-v4",
  input=texts,
  dimension=1024
  )
  embeddings = np.array([item['embedding'] for item in resp.output['embeddings']])

  # 2. Use the KMeans algorithm for clustering
  kmeans = KMeans(n_clusters=n_clusters, random_state=0, n_init='auto').fit(embeddings)

  # 3. Organize and return the results
  clusters = {i: [] for i in range(n_clusters)}
  for i, label in enumerate(kmeans.labels_):
    clusters[label].append(texts[i])
  return clusters


# Example usage
documents_to_cluster = [
  "Mobile phone company A releases a new phone",
  "Search engine company B launches a new system",
  "World Cup final: Argentina vs. France",
  "China wins another gold medal at the Olympics",
  "A company releases its latest AI chip",
  "European Cup match report"
]
clusters = cluster_texts(documents_to_cluster, n_clusters=2)
for cluster_id, docs in clusters.items():
  print(f"--- Cluster {cluster_id} ---")
  for doc in docs:
    print(f"- {doc}")

import dashscope
import numpy as np

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

def cosine_similarity(a, b):
  """Calculate cosine similarity"""
  return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))


def classify_text_zero_shot(text, labels):
  """Perform zero-shot text classification"""
  # 1. Get the vectors for the input text and all labels
  resp = dashscope.TextEmbedding.call(
  model="text-embedding-v4",
  input=[text] + labels,
  dimension=1024
  )
  embeddings = resp.output['embeddings']
  text_embedding = embeddings[0]['embedding']
  label_embeddings = [emb['embedding'] for emb in embeddings[1:]]

  # 2. Calculate the similarity with each label
  scores = [cosine_similarity(text_embedding, label_emb) for label_emb in label_embeddings]

  # 3. Return the label with the highest similarity
  best_match_index = np.argmax(scores)
  return labels[best_match_index], scores[best_match_index]


# Example usage
text_to_classify = "The fabric of this dress is comfortable and the style is nice"
possible_labels = ["Digital Products", "Apparel & Accessories", "Food & Beverage", "Home & Living"]

label, score = classify_text_zero_shot(text_to_classify, possible_labels)
print(f"Input text: '{text_to_classify}'")
print(f"Best matching category: '{label}' (Similarity: {score:.3f})")

import dashscope
import numpy as np


def cosine_similarity(a, b):
  """Calculate cosine similarity"""
  return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))


def detect_anomaly(new_comment, normal_comments, threshold=0.6):
  # 1. Vectorize all normal comments and the new comment
  all_texts = normal_comments + [new_comment]
  resp = dashscope.TextEmbedding.call(
  model="text-embedding-v4",
  input=all_texts,
  dimension=1024
  )
  embeddings = [item['embedding'] for item in resp.output['embeddings']]

  # 2. Calculate the center vector (average value) of the normal comments
  normal_embeddings = np.array(embeddings[:-1])
  normal_center_vector = np.mean(normal_embeddings, axis=0)

  # 3. Calculate the similarity between the new comment and the center vector
  new_comment_embedding = np.array(embeddings[-1])
  similarity = cosine_similarity(new_comment_embedding, normal_center_vector)

  # 4. Determine if it is an anomaly
  is_anomaly = similarity < threshold
  return is_anomaly, similarity


# Example usage
normal_user_comments = [
  "Today's meeting was productive",
  "The project is progressing smoothly",
  "The new version will be released next week",
  "User feedback is positive"
]

test_comments = {
  "Normal comment": "The feature works as expected",
  "Anomaly - meaningless garbled text": "asdfghjkl zxcvbnm"
}

print("--- Anomaly Detection Example ---")
for desc, comment in test_comments.items():
  is_anomaly, score = detect_anomaly(comment, normal_user_comments)
  result = "Yes" if is_anomaly else "No"
  print(f"Comment: '{comment}'")
  print(f"Is anomaly: {result} (Similarity to normal samples: {score:.3f})\n")