Friendli Python SDK

Introduction

The Friendli Python SDK provides a powerful and flexible way to interact with FriendliAI services, including Model APIs, Dedicated Endpoints, and Container. You can easily integrate your Python applications with FriendliAI.

Installation

You can install the SDK with either pip or poetry:

# Using pip
pip install friendli

# Using poetry
poetry add friendli

Authentication

Authenticate using a Personal API key, which you can generate from Friendli Suite > Personal Settings > API Keys:

import os
from friendli import SyncFriendli

with SyncFriendli(
    token=os.environ["API_KEY"],
) as friendli:
    # Your code here

For detailed instructions on generating an API key, see the Manage Your FriendliAI API Keys guide.

Chat Completions

The SDK supports chat completions across all deployment types. Choose the deployment option that best fits your needs.

import os
from friendli import SyncFriendli

with SyncFriendli(
    token=os.environ["API_KEY"],
) as friendli:
    res = friendli.serverless.chat.complete(
        messages=[
            {
                "content": "You are a helpful assistant.",
                "role": "system",
            },
            {
                "content": "Hello!",
                "role": "user",
            },
        ],
        model="zai-org/GLM-5.3",
        max_tokens=200,
    )

    print(res)

import os
from friendli import SyncFriendli

with SyncFriendli(
    token=os.environ["API_KEY"],
) as friendli:
    res = friendli.dedicated.chat.complete(
        messages=[
            {
                "content": "You are a helpful assistant.",
                "role": "system",
            },
            {
                "content": "Hello!",
                "role": "user",
            },
        ],
        model="YOUR_ENDPOINT_ID",
        max_tokens=200,
    )

    print(res)

from friendli import SyncFriendli

with SyncFriendli() as friendli:
    res = friendli.container.chat.complete(
        messages=[
            {
                "content": "You are a helpful assistant.",
                "role": "system",
            },
            {
                "content": "Hello!",
                "role": "user",
            },
        ],
        max_tokens=200,
    )

    print(res)

Asynchronous Chat Completions

import asyncio
import os
from friendli import AsyncFriendli

async def main():
    async with AsyncFriendli(
        token=os.environ["API_KEY"],
    ) as friendli:
        res = await friendli.serverless.chat.complete(
            messages=[
                {
                    "content": "You are a helpful assistant.",
                    "role": "system",
                },
                {
                    "content": "Hello!",
                    "role": "user",
                },
            ],
            model="zai-org/GLM-5.3",
            max_tokens=200,
        )

        print(res)

asyncio.run(main())

import asyncio
import os
from friendli import AsyncFriendli

async def main():
    async with AsyncFriendli(
        token=os.environ["API_KEY"],
    ) as friendli:
        res = await friendli.dedicated.chat.complete(
            messages=[
                {
                    "content": "You are a helpful assistant.",
                    "role": "system",
                },
                {
                    "content": "Hello!",
                    "role": "user",
                },
            ],
            model="YOUR_ENDPOINT_ID",
            max_tokens=200,
        )

        print(res)

asyncio.run(main())

import asyncio
from friendli import AsyncFriendli

async def main():
    async with AsyncFriendli() as friendli:
        res = await friendli.container.chat.complete(
            messages=[
                {
                    "content": "You are a helpful assistant.",
                    "role": "system",
                },
                {
                    "content": "Hello!",
                    "role": "user",
                },
            ],
            max_tokens=200,
        )

        print(res)

asyncio.run(main())

Advanced Features

Streaming Responses

The SDK supports streaming responses using server-sent events, which you can consume using a simple for loop:

import os
from friendli import SyncFriendli

with SyncFriendli(
    token=os.environ["API_KEY"],
) as friendli:
    res = friendli.serverless.chat.stream(
        messages=[
            {
                "content": "You are a helpful assistant.",
                "role": "system",
            },
            {
                "content": "Hello!",
                "role": "user",
            },
        ],
        model="zai-org/GLM-5.3",
        max_tokens=200,
    )

    with res as event_stream:
        for event in event_stream:
            # Process each chunk as it arrives
            print(event, flush=True)

Custom Retry Strategy

You can customize retry behavior for operations that support retries:

import os
from friendli import SyncFriendli
from friendli.utils import BackoffStrategy, RetryConfig

with SyncFriendli(
    token=os.environ["API_KEY"],
) as friendli:
    res = friendli.serverless.chat.complete(
        messages=[
            {
                "content": "You are a helpful assistant.",
                "role": "system",
            },
            {
                "content": "Hello!",
                "role": "user",
            },
        ],
        model="zai-org/GLM-5.3",
        max_tokens=200,
        retries=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
    )

    # Handle response
    print(res)

Error Handling

The SDK provides comprehensive error handling with detailed exception information:

import os
from friendli import SyncFriendli, models

with SyncFriendli(
    token=os.environ["API_KEY"],
) as friendli:
    try:
        res = friendli.dedicated.endpoint.create(
            advanced={
                "tokenizer_add_special_tokens": True,
                "tokenizer_skip_special_tokens": False,
            },
            hf_model_repo="<value>",
            instance_option_id="<id>",
            name="<value>",
            project_id="<id>",
        )

        # Handle response
        print(res)

    except models.HTTPValidationError as e:
        # Handle validation errors
        print(f"Validation error: {e.data}")
    except models.SDKError as e:
        # Handle general SDK errors
        print(f"Error {e.status_code}: {e.message}")

Custom Logging

You can pass your own logger to the client class to help troubleshoot and diagnose issues during API interactions. This is especially useful when you encounter unexpected behavior or errors.

import logging
import os

from friendli import SyncFriendli

# Configure your custom logger, for example:
logger = logging.getLogger(__name__)
logging.basicConfig(
    format="[%(filename)s:%(lineno)s - %(funcName)s()] %(message)s",
    level=logging.INFO,
    handlers=[logging.StreamHandler()],
)

with SyncFriendli(
    server_url=SERVER_URL,
    token=TOKEN,
    debug_logger=logger,  # Pass your logger here
) as friendli:
    # Your code here
    pass

Further Resources

For complete API documentation, advanced usage examples, and detailed reference information, visit the Friendli Python SDK GitHub repository.

API Reference

Model APIs

Dedicated

Container

Administration

Friendli SDK

Introduction

Installation

Authentication

Chat Completions

Asynchronous Chat Completions

Advanced Features

Streaming Responses

Custom Retry Strategy

Error Handling

Custom Logging

Further Resources

​Introduction

​Installation

​Authentication

​Chat Completions

​Asynchronous Chat Completions

​Advanced Features

​Streaming Responses

​Custom Retry Strategy

​Error Handling

​Custom Logging

​Further Resources

Introduction

Installation

Authentication

Chat Completions

Asynchronous Chat Completions

Advanced Features

Streaming Responses

Custom Retry Strategy

Error Handling

Custom Logging

Further Resources