Catsu

Catsu — Unified Embedding API Client

Catsu provides a single, consistent interface for generating embeddings across 11 providers and 35+ models. Built-in retry logic, cost tracking, and model discovery eliminate the need for provider-specific SDKs.

When to Use This Skill

Use this skill when users want to:

• Generate embeddings from any provider through a unified API
• Compare embedding models across providers (cost, quality, dimensions)
• Add embeddings to a RAG pipeline, search system, or recommendation engine
• Switch between providers without changing application code
• Track token usage and costs across embedding calls
• Use Matryoshka embeddings (reduced dimensions) for storage optimization

Installation

# Python
pip install catsu
# Requires Python 3.10+

# Rust
# Add to Cargo.toml:
# [dependencies]
# catsu = "0.1"
# tokio = { version = "1", features = ["full"] }

Setup — API Keys

Set environment variables for the providers you use:

export OPENAI_API_KEY=<your-openai-key>
export VOYAGE_API_KEY=<your-voyage-key>
export COHERE_API_KEY=<your-cohere-key>
export JINA_API_KEY=<your-jina-key>
export MISTRAL_API_KEY=<your-mistral-key>
export GOOGLE_API_KEY=<your-google-key>        # or GEMINI_API_KEY
export TOGETHER_API_KEY=<your-together-key>
export MIXEDBREAD_API_KEY=<your-mixedbread-key>
export NOMIC_API_KEY=<your-nomic-key>
export DEEPINFRA_API_KEY=<your-deepinfra-key>
export CLOUDFLARE_API_TOKEN=<your-cloudflare-token>  # + CLOUDFLARE_ACCOUNT_ID

Only the keys for providers you actually call are required.

Basic Usage

Python

from catsu import Client

client = Client()

# Embed text — provider:model format
response = client.embed(
    model="openai:text-embedding-3-small",
    input=["Hello, world!", "How are you?"]
)

print(response.embeddings)       # [[0.012, -0.034, ...], [...]]
print(response.dimensions)       # 1536
print(response.usage.tokens)     # 10
print(response.usage.cost)       # 0.000002
print(response.latency_ms)       # 142.5

Rust

use catsu::Client;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::new()?;

    let response = client.embed(
        "openai:text-embedding-3-small",
        vec!["Hello, world!".to_string()],
    ).await?;

    println!("Dimensions: {}", response.dimensions);
    println!("Cost: ${}", response.usage.cost.unwrap_or(0.0));
    Ok(())
}

Model Specification

Three ways to specify which model to use:

client = Client()

# 1. Provider prefix (recommended)
response = client.embed(model="voyageai:voyage-3", input="hello")

# 2. Explicit provider parameter
response = client.embed(provider="voyageai", model="voyage-3", input="hello")

# 3. Auto-detection (if model name is unique across providers)
response = client.embed(model="voyage-3", input="hello")

Input Types — Query vs Document

Many providers optimize embeddings differently for search queries vs stored documents:

# For search queries (short, question-like)
response = client.embed(
    model="voyageai:voyage-3",
    input=["what is attention?"],
    input_type="query",
)

# For documents being indexed (longer content)
response = client.embed(
    model="voyageai:voyage-3",
    input=["The attention mechanism allows models to..."],
    input_type="document",
)

Providers that support input types: VoyageAI, Cohere (required for v3+), Jina, Mistral, Gemini, Nomic.

Custom Dimensions (Matryoshka Embeddings)

Reduce embedding dimensions for storage/speed at slight quality cost:

# OpenAI: 1536 → 256 dimensions
response = client.embed(
    model="openai:text-embedding-3-small",
    input=["hello"],
    dimensions=256,
)
print(response.dimensions)  # 256

Providers supporting custom dimensions: OpenAI, VoyageAI, Cohere, Jina, Mistral, Gemini, Nomic.

Supported Providers & Models

Model Discovery

from catsu import Client

# List all available models
all_models = Client.list_models()

# Filter by provider
openai_models = Client.list_models("openai")
for m in openai_models:
    print(f"{m.name}: {m.dimensions}d, ${m.cost_per_million_tokens}/M tokens")

# Get specific model info
model = Client.get_model("openai", "text-embedding-3-small")
print(f"Max tokens: {model.max_tokens}")
print(f"Supports dimensions: {model.supports_dimensions}")

# Find model by name (auto-detect provider)
model = Client.find_model_by_name("voyage-3")
print(f"Provider: {model.provider}")

Model Selection Guide

See references/model_comparison.md for detailed benchmarks and cost analysis.

Retry & Error Handling

Catsu handles transient failures automatically:

client = Client(
    max_retries=5,              # Default: 3
    timeout=60,                 # Default: 30 seconds
)

# Retries automatically on: 429, 408, 409, 500, 502, 503, 504
# Uses exponential backoff with jitter
# Respects Retry-After headers

Explicit error handling

from catsu.utils.errors import (
    RateLimitError,
    AuthenticationError,
    ModelNotFoundError,
    MissingApiKeyError,
)

try:
    response = client.embed(model="voyage-3", input="hello")
except RateLimitError as e:
    print(f"Rate limited. Retry after {e.retry_after}s")
except AuthenticationError:
    print("Invalid API key")
except ModelNotFoundError as e:
    print(f"Unknown model: {e}")
except MissingApiKeyError as e:
    print(f"Set {e.provider} API key")

Advanced Configuration

Per-request API key override

import os

response = client.embed(
    model="openai:text-embedding-3-small",
    input="hello",
    api_key=os.environ["ALTERNATE_OPENAI_KEY"],
)

HTTP proxy and custom CA

# Python
client = Client(proxy="http://proxy:8080")

# Rust
let config = HttpConfig {
    proxy: Some("http://proxy:8080".to_string()),
    ca_cert_pem: Some(cert_pem_string),
    ..Default::default()
};
let client = Client::with_config(config)?;

Context managers for cleanup

# Sync
with Client() as client:
    response = client.embed("voyage-3", "hello")

# Async
async with Client() as client:
    response = await client.aembed("voyage-3", "hello")

NumPy conversion

response = client.embed("voyage-3", ["text1", "text2"])
arr = response.to_numpy()   # shape: (2, 1024)

Async Support

import asyncio
from catsu import Client

async def embed_batch():
    async with Client() as client:
        response = await client.aembed(
            model="openai:text-embedding-3-small",
            input=["text1", "text2", "text3"],
        )
        return response.embeddings

embeddings = asyncio.run(embed_batch())

Integration with Chonkie

Catsu works as an embedding provider for Chonkie's RAG pipelines:

pip install "chonkie[catsu]"

from chonkie import Pipeline

# Use catsu as the embedding backend
docs = (Pipeline()
    .chunk_with("recursive", chunk_size=512)
    .refine_with("embeddings", embedding_model="catsu:voyage-3")
    .store_in("qdrant", url="http://localhost:6333", collection="docs")
    .run(texts=documents)
)

Or use Catsu's embeddings directly with Chonkie's AutoEmbeddings:

from chonkie import AutoEmbeddings

embed = AutoEmbeddings.get_embeddings("catsu:openai:text-embedding-3-small")
vectors = embed.embed_batch(["text1", "text2"])