> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lingxilearn.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# Python SDK

> Manage every Agent Server resource with synchronous or asynchronous clients

```bash theme={null}
pip install "lingxigraph[sdk]"
```

## Synchronous client

```python theme={null}
from lingxigraph.sdk import LingxiGraphClient

with LingxiGraphClient(
    "https://agents.example.com",
    token="...",
    timeout=30,
) as client:
    graph = client.graphs.get("production-support")
    assistant = client.assistants.create(
        graph_id=graph["id"],
        graph_version=graph["version"],
        name="support",
    )
    thread = client.threads.create(metadata={"external_id": "ticket-42"})
    run = client.runs.create(
        assistant["id"],
        thread_id=thread["id"],
        input={"request": "reset access", "result": ""},
        max_model_calls=8,
    )

    for event in client.runs.stream(run["id"]):
        print(event["sequence"], event["kind"])

    completed = client.runs.join(run["id"], timeout=120)
    print(completed["output"])
```

Available resource methods:

| Resource     | Methods                                                                                 |
| ------------ | --------------------------------------------------------------------------------------- |
| `graphs`     | `list()`, `get(graph_id)`                                                               |
| `assistants` | `create(**values)`, `list()`, `get()`, `update()`, `delete()`                           |
| `threads`    | `create()`, `list()`, `get()`, `update()`, `state()`, `history()`, `fork()`, `delete()` |
| `runs`       | `create()`, `get()`, `list(thread_id)`, `join()`, `stream()`, `cancel()`, `resume()`    |
| `store`      | `batch(operations)`, `search(namespace, ...)`                                           |
| `schedules`  | `create()`, `list()`, `update()`, `delete()`                                            |

Use `client.request(method, path, **kwargs)` for redrive or an endpoint not yet wrapped by a resource.

## Asynchronous client

```python theme={null}
from lingxigraph.sdk import AsyncLingxiGraphClient

async with AsyncLingxiGraphClient(base_url, token=token) as client:
    thread = await client.threads.create()
    run = await client.runs.create(
        assistant_id,
        thread_id=thread["id"],
        input={"request": "hello"},
    )
    async for event in client.runs.stream(run["id"]):
        print(event)
```

Async resources mirror sync resources. Do not use the synchronous client inside an async event loop.

## Error handling

```python theme={null}
from lingxigraph.sdk import LingxiGraphAPIError

try:
    client.runs.get("missing")
except LingxiGraphAPIError as exc:
    print(exc.status_code, exc.code, exc.request_id)
    if exc.retryable:
        retry_with_backoff()
```

Branch only on `status_code`, stable `code`, and `retryable`. `detail` is diagnostic prose, not a machine protocol. The SDK does not automatically retry run creation. Send a stable `Idempotency-Key` through the underlying `request` method when network retries could enqueue twice.