Embeddings

Embeddings are numerical representations of text strings that measure their relationships. Text embeddings measure the degree of similarity between text strings and are often used for the following tasks:

• Search (results are sorted by relevance to the query)
• Clustering (grouping text strings by similarity)
• Recommendations (recommending items with similar text strings)
• Anomaly detection (finding items that differ significantly from others)
• Diversity measurement (analyzing similarity distribution)
• Classification (classifying text strings based on their similarity to labels)

An embedding is a vector (list) of numbers. The distance between two vectors measures their degree of similarity: a small distance indicates high similarity, and a large distance indicates low similarity.

Creating Embeddings for Single and Multiple Text Objects

Python (OpenAI клиент)

#pip install langchain-openai - if you don't have this package yet


from langchain_openai import OpenAIEmbeddings

embeddings_model = OpenAIEmbeddings(
     model="CompressaEmbeddings",
     base_url="http://localhost:5000/v1", 
     api_key="Your_API_key_Compressa", 
     )


# Create embedding for a single query
query_embedding = embeddings.embed_query("How to cook borscht?")

# Create embeddings for multiple documents
docs_embeddings = embeddings.embed_documents([
    "Borscht is a traditional Slavic soup",
    "Beets are needed to make borscht",
    "Borscht is usually served with sour cream",
    "Meat is often added to borscht",
    "Borscht has a characteristic red color"
])

Python (OpenAI клиент)

# from openai import OpenAI - if you don't have this package yet

client = OpenAI(
    api_key = "Your_API_key_Compressa", 
    base_url = "http://localhost:5000/v1" 
)

# Create embedding for a single query
embedding = client.embeddings.create(
    model="Compressa-Embedding",
    input="How to cook borscht?",
    encoding_format="float",
)

# Create embeddings for multiple documents
docs = [
    "Borscht is a traditional Slavic soup",
    "Beets are needed to make borscht",
    "Borscht is usually served with sour cream",
    "Meat is often added to borscht",
    "Borscht has a characteristic red color"
]

embeddings = client.embeddings.create(
    model="Compressa-Embedding",
    input=docs,
    encoding_format="float",
)

cURL

curl -X 'POST' \
  'http://localhost:5000/v1/embeddings' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer Your_API_key_Compressa' \
  -d '{
  "model": "Compressa-Embedding",
  "input": ["text_one", "text_two"]
}'