llama-cloud-sdk 0.0.5

No project description provided

LlamaIndex Python Library

The LlamaIndex Python library provides convenient access to the LlamaIndex API from Python.

Installation

pip install llama-cloud-sdk

Reference

A full reference for this library is available here.

Usage

Instantiate and use the client with the following:

from llama_index import LlamaCloud

client = LlamaCloud(
    token="YOUR_TOKEN",
)
client.data_sinks.create_data_sink(
    name="name",
    sink_type="PINECONE",
    component={"key": "value"},
)

Async Client

The SDK also exports an async client so that you can make non-blocking calls to our API.

import asyncio

from llama_index import AsyncLlamaCloud

client = AsyncLlamaCloud(
    token="YOUR_TOKEN",
)


async def main() -> None:
    await client.data_sinks.create_data_sink(
        name="name",
        sink_type="PINECONE",
        component={"key": "value"},
    )


asyncio.run(main())

Exception Handling

When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error will be thrown.

from llama_index.core.api_error import ApiError

try:
    client.data_sinks.create_data_sink(...)
except ApiError as e:
    print(e.status_code)
    print(e.body)

Advanced

Retries

The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long as the request is deemed retriable and the number of retry attempts has not grown larger than the configured retry limit (default: 2).

A request is deemed retriable when any of the following HTTP status codes is returned:

• 408 (Timeout)
• 429 (Too Many Requests)
• 5XX (Internal Server Errors)

Use the max_retries request option to configure this behavior.

client.data_sinks.create_data_sink(..., request_options={
    "max_retries": 1
})

Timeouts

The SDK defaults to a 60 second timeout. You can configure this with a timeout option at the client or request level.

from llama_index import LlamaCloud

client = LlamaCloud(
    ...,
    timeout=20.0,
)


# Override timeout for a specific method
client.data_sinks.create_data_sink(..., request_options={
    "timeout_in_seconds": 1
})

Custom Client

You can override the httpx client to customize it for your use-case. Some common use-cases include support for proxies and transports.

import httpx
from llama_index import LlamaCloud

client = LlamaCloud(
    ...,
    httpx_client=httpx.Client(
        proxies="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

On the other hand, contributions to the README are always very welcome!