Skip to main content

​
EmbeddingAgent

Defined in the embedding_agent module.
A specialized agent for generating text embeddings. Provides:
  • Single text embedding
  • Batch text embedding
  • Similarity calculation between texts
Supported Providers:
  • OpenAI: text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002
  • Azure: azure/text-embedding-3-small
  • Cohere: cohere/embed-english-v3.0, cohere/embed-multilingual-v3.0
  • Voyage: voyage/voyage-3, voyage/voyage-3-lite
  • Mistral: mistral/mistral-embed

​
Constructor

​
name
Optional
No description available.
​
instructions
Optional
No description available.
​
llm
Optional
No description available.
​
model
Optional
No description available.
​
base_url
Optional
No description available.
​
api_key
Optional
No description available.
​
embedding
Optional
No description available.
​
verbose
Union
default:"True"
No description available.

​
Methods

console()

Lazily initialize Rich Console.

litellm()

Lazy load litellm module when needed.

embed()

Generate embedding for a single text.

embed_batch()

Generate embeddings for multiple texts.

similarity()

Calculate cosine similarity between two texts.

find_most_similar()

Find the most similar texts to a query.

aembed()

Async version of embed().

aembed_batch()

Async version of embed_batch().

asimilarity()

Async version of similarity().

​
Usage

from praisonaiagents import EmbeddingAgent
    
    # Simple usage
    agent = EmbeddingAgent()
    embedding = agent.embed("Hello world")
    print(f"Embedding dimension: {len(embedding)}")
    
    # Batch embedding
    embeddings = agent.embed_batch([
        "First text",
        "Second text",
        "Third text"
    ])
    
    # Calculate similarity
    score = agent.similarity("Hello", "Hi there")
    print(f"Similarity: {score:.2f}")