Pollux handles uploads, shared context, retries, provider differences, and normalized results.
from pollux import run, Config, Source
result = await run(
"Summarize the key findings",
source=Source.from_file("paper.pdf"),
config=Config(
provider="gemini",
model="gemini-2.5-flash-lite",
),
)
print(result.text)
PDFs, images, video, YouTube, arXiv. Use the same entry point for each.
Ask several questions without writing upload and concurrency machinery.
Use one result model without hiding capabilities that genuinely differ.
Read text, structured data, tool calls, usage, and completion state directly.
pip install --upgrade pollux-ai