Documentation Index
Fetch the complete documentation index at: https://mintlify.com/reductoai/reducto-python-sdk/llms.txt
Use this file to discover all available pages before exploring further.
Overview
You can directly override the httpx client to customize it for your use case, including:
Basic Configuration
Customize the HTTP client when instantiating the Reducto client:
import httpx
from reducto import Reducto, DefaultHttpxClient
client = Reducto(
# Or use the `REDUCTO_BASE_URL` env var
base_url="http://my.test.server.example.com:8083",
http_client=DefaultHttpxClient(
proxy="http://my.test.proxy.example.com",
transport=httpx.HTTPTransport(local_address="0.0.0.0"),
),
)
Per-Request Customization
You can also customize the client on a per-request basis by using with_options():
from reducto import Reducto, DefaultHttpxClient
client = Reducto()
# Use custom HTTP client for specific requests
client.with_options(
http_client=DefaultHttpxClient(
proxy="http://my.proxy.example.com",
)
).parse.run(
input="https://pdfobject.com/pdf/sample.pdf",
)
Using aiohttp for Async Clients
By default, the async client uses httpx for HTTP requests. However, for improved concurrency performance you may also use aiohttp as the HTTP backend.
Installation
Install the aiohttp extra:
pip install reductoai[aiohttp]
Configuration
Enable aiohttp by instantiating the client with http_client=DefaultAioHttpClient():
import os
import asyncio
from reducto import DefaultAioHttpClient
from reducto import AsyncReducto
async def main() -> None:
async with AsyncReducto(
api_key=os.environ.get("REDUCTO_API_KEY"),
http_client=DefaultAioHttpClient(),
) as client:
response = await client.parse.run(
input="https://pdfobject.com/pdf/sample.pdf",
)
asyncio.run(main())
Using aiohttp instead of httpx can provide better concurrency performance for async applications with high request volumes.
Managing HTTP Resources
By default, the library closes underlying HTTP connections whenever the client is garbage collected. You can manually close the client using the .close() method if desired, or with a context manager that closes when exiting.
from reducto import Reducto
with Reducto() as client:
# make requests here
response = client.parse.run(
input="https://pdfobject.com/pdf/sample.pdf",
)
# HTTP client is now closed
Using a context manager ensures that HTTP connections are properly closed, which is especially important in long-running applications or when making many requests.
Proxy Configuration
Configure proxy settings through the HTTP client:
import httpx
from reducto import Reducto, DefaultHttpxClient
client = Reducto(
http_client=DefaultHttpxClient(
proxy="http://my.proxy.example.com:8080",
),
)
Custom Transports
Use custom transports for advanced networking requirements:
import httpx
from reducto import Reducto, DefaultHttpxClient
client = Reducto(
http_client=DefaultHttpxClient(
transport=httpx.HTTPTransport(
local_address="0.0.0.0",
retries=3,
),
),
)