embedding()

def embedding(
    model: str,
    input: Union[str, List[str]] = [],
    # Optional params
    dimensions: Optional[int] = None,
    encoding_format: Optional[str] = None,
    timeout: float = 600,
    # API configuration
    api_base: Optional[str] = None,
    api_version: Optional[str] = None,
    api_key: Optional[str] = None,
    api_type: Optional[str] = None,
    # LiteLLM specific
    caching: bool = False,
    user: Optional[str] = None,
    custom_llm_provider: Optional[str] = None,
    **kwargs
) -> EmbeddingResponse

import litellm

response = litellm.embedding(
    model="text-embedding-3-small",
    input="The quick brown fox jumps over the lazy dog"
)

print(response.data[0].embedding)  # [0.123, -0.456, ...]
print(len(response.data[0].embedding))  # 1536

import litellm

texts = [
    "First document to embed",
    "Second document to embed",
    "Third document to embed"
]

response = litellm.embedding(
    model="text-embedding-3-small",
    input=texts
)

for i, embedding_obj in enumerate(response.data):
    print(f"Document {i}: {len(embedding_obj.embedding)} dimensions")

import litellm
import asyncio

async def main():
    response = await litellm.aembedding(
        model="text-embedding-3-small",
        input="Async embedding example"
    )
    print(response.data[0].embedding)

asyncio.run(main())

import litellm

# Reduce embedding dimensions for smaller storage
response = litellm.embedding(
    model="text-embedding-3-small",
    input="Sample text",
    dimensions=512  # Instead of default 1536
)

print(len(response.data[0].embedding))  # 512

import litellm

# OpenAI
response = litellm.embedding(
    model="text-embedding-3-small",
    input="Hello world"
)

# Cohere
response = litellm.embedding(
    model="embed-english-v3.0",
    input="Hello world"
)

# AWS Bedrock
response = litellm.embedding(
    model="amazon.titan-embed-text-v1",
    input="Hello world"
)

# Azure OpenAI
response = litellm.embedding(
    model="azure/text-embedding-ada-002",
    input="Hello world",
    api_key="your-azure-key",
    api_base="https://your-endpoint.openai.azure.com/",
    api_version="2024-02-01"
)

# Vertex AI
response = litellm.embedding(
    model="textembedding-gecko@003",
    input="Hello world"
)

import litellm
import numpy as np

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

# Documents to search
documents = [
    "Python is a programming language",
    "JavaScript is used for web development",
    "Machine learning is a subset of AI"
]

# Get embeddings for all documents
response = litellm.embedding(
    model="text-embedding-3-small",
    input=documents
)

doc_embeddings = [item.embedding for item in response.data]

# Query
query = "What is Python?"
query_response = litellm.embedding(
    model="text-embedding-3-small",
    input=query
)
query_embedding = query_response.data[0].embedding

# Find most similar document
similarities = [
    cosine_similarity(query_embedding, doc_emb) 
    for doc_emb in doc_embeddings
]

most_similar_idx = np.argmax(similarities)
print(f"Most similar: {documents[most_similar_idx]}")
print(f"Similarity: {similarities[most_similar_idx]:.4f}")

import litellm

response = litellm.embedding(
    model="embed-english-v3.0",
    input="Sample text",
    input_type="search_document"  # or "search_query", "classification"
)

import litellm

response = litellm.embedding(
    model="multimodalembedding@001",
    input="Sample text"
)

import litellm
from litellm import AuthenticationError, RateLimitError

try:
    response = litellm.embedding(
        model="text-embedding-3-small",
        input="Sample text"
    )
except AuthenticationError as e:
    print(f"Authentication failed: {e}")
except RateLimitError as e:
    print(f"Rate limit exceeded: {e}")
except Exception as e:
    print(f"An error occurred: {e}")