yachay 0.1.3

Python SDK for Yachay — Condor Models inference API (OpenAI-compatible)

Yachay Python SDK

Python client for Yachay — Condor Models inference API. Designed to feel like the OpenAI SDK so migrating existing code takes minutes.

Install

pip install yachay

Requires Python 3.9+.

Quickstart

import yachay

client = yachay.Client()  # reads YACHAY_API_KEY from environment

response = client.chat.completions.create(
    model="llama-3.1-8b",
    messages=[{"role": "user", "content": "Explain gradient descent in one paragraph."}],
)
print(response.choices[0].message.content)

Authentication

Create a customer API key in the Yachay dashboard. Keys are prefixed yck_.

Recommended — environment variable:

export YACHAY_API_KEY="yck_your_key_here"

Or pass directly:

client = yachay.Client(api_key="yck_your_key_here")

Available models

Run the CLI or call the SDK to see the current catalog (the list changes as new models are added):

yachay models list

models = client.models.list()
for model in models.data:
    print(model.id, model.display_name)

CLI

The yachay command ships with the package and covers the full developer workflow — authentication, fine-tuning jobs, inference, datasets, endpoints, and account management.

Authentication

# Sign in via browser (credentials saved to the OS keychain; auto-refreshed)
yachay login

# Check who you're signed in as
yachay auth status

# CI/non-interactive: pass a key directly (or set YACHAY_API_KEY)
YACHAY_API_KEY=yck_... yachay jobs list

Command groups

Group	Example	Description
auth	yachay auth status	Sign in/out and check credentials
models	yachay models list	List available inference models
jobs	yachay jobs submit --model llama-3.1-8b --model-name my-bot --dataset train.jsonl --agreed-max-usd 10	Submit and manage fine-tuning jobs
jobs	yachay jobs list, yachay jobs status <id>, yachay jobs download <id>	Track and retrieve jobs
jobs	yachay jobs estimate --model llama-3.1-8b --dataset-size-mb 5	Cost/ETA estimate before submitting
jobs	yachay jobs cancel <id>, yachay jobs metrics <id>, yachay jobs extend-storage <id>	Manage active jobs
datasets	yachay datasets generate --task-type chat --source "..."	AI-assisted dataset generation
datasets	yachay datasets upload <file.jsonl> --model llama-3.1-8b --model-name my-bot --agreed-max-usd 10	Upload a BYO dataset
infer	yachay infer playground --model llama-3.1-8b --prompt "Hello"	Run a prompt through the inference playground
endpoints	yachay endpoints deploy --job-id <id> --name my-endpoint	Deploy a fine-tuned adapter to hosted inference
account	yachay account me, yachay account prefs	Account summary and notification preferences
billing	yachay billing	Show billing summary
chat	yachay chat --model llama-3.1-8b --prompt "Hi"	One-shot or interactive chat REPL

Useful flags

Flag	Effect
--json	Machine-readable JSON output on stdout (errors on stderr)
--yes / -y	Skip confirmation prompts (CI/scripted use)
--api-key KEY	Override stored credentials (also YACHAY_API_KEY env var)

Credential storage

Login credentials (refresh token) are stored in the OS keychain (macOS Keychain, Linux Secret Service, Windows Credential Manager). Run yachay logout to remove them.

Chat completions

response = client.chat.completions.create(
    model="deepseek-r1-distill-llama-8b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of Peru?"},
    ],
    max_tokens=256,
    temperature=0.7,
)

# Access the generated text
print(response.choices[0].message.content)

# Access token usage
print(f"Tokens used: {response.usage.total_tokens}")

Context manager

with yachay.Client() as client:
    response = client.chat.completions.create(
        model="llama-3.1-8b",
        messages=[{"role": "user", "content": "Hello!"}],
    )
    print(response.choices[0].message.content)
# HTTP connection pool is closed automatically

Migrating from OpenAI

The client mirrors the OpenAI SDK's nested-namespace pattern. Replace:

# Before
import openai
client = openai.OpenAI(api_key="sk-...")
response = client.chat.completions.create(model="gpt-4o", messages=[...])

with:

# After
import yachay
client = yachay.Client(api_key="yck_...")
response = client.chat.completions.create(model="llama-3.1-8b", messages=[...])

Response objects share the same shape: .choices[0].message.content, .usage.total_tokens, etc.

Error handling

from yachay import AuthError, RateLimitError, APIError

try:
    response = client.chat.completions.create(...)
except AuthError:
    print("Invalid API key")
except RateLimitError:
    print("Slow down — you are being rate-limited")
except APIError as e:
    print(f"API error {e.status}: {e.body}")

All errors are subclasses of yachay.YachayError.

Custom base URL and timeout

client = yachay.Client(
    api_key="yck_...",
    base_url="https://api.yachaymodels.com/v1",  # default; override for testing
    timeout=30.0,  # seconds
)

What v1 does NOT include

• Streaming — stream=True is not yet supported in the Python client. Passing stream=True raises an APIError with a clear message. Submit a feature request at yachaymodels.com/support.
• SDK-native fine-tuning methods — client.jobs.* and client.datasets.* are not exposed on the Client object in v1. Use the yachay CLI (see the CLI section above) for the full fine-tuning and dataset workflow.
• Embeddings — not available in v1.

Documentation

Full API reference and guides at yachaymodels.com/docs.

License

MIT — see LICENSE for details.