pollux-ai 1.0.0rc2

Multimodal orchestration for LLM analysis

Pollux

Multimodal orchestration for LLM APIs.

You describe what to analyze. Pollux handles source patterns, context caching, and multimodal complexity—so you don't.

Originally built for Gemini during Google Summer of Code 2025. Pollux now supports both Gemini and OpenAI with explicit capability differences.

Documentation · Quickstart · Cookbook

Quick Start

import asyncio
from pollux import Config, Source, run

result = asyncio.run(
    run(
        "What are the key findings?",
        source=Source.from_text(
            "Pollux supports fan-out, fan-in, and broadcast source patterns. "
            "It also supports context caching for repeated prompts."
        ),
        config=Config(provider="gemini", model="gemini-2.5-flash-lite"),
    )
)
print(result["answers"][0])

For a full 2-minute walkthrough (install, key setup, success checks), use Quickstart. For local-file analysis, swap to Source.from_file("paper.pdf").

Why Pollux?

• Multimodal-first: PDFs, images, videos, YouTube—same API
• Source patterns: Fan-out (one source → many prompts), fan-in, and broadcast
• Context caching: Upload once, reuse across prompts—save tokens and money
• Production-ready core: async execution, explicit capability checks, clear errors

Installation

pip install pollux-ai

Or download the latest wheel from Releases.

API Key

Get a key from Google AI Studio, then:

export GEMINI_API_KEY="your-key-here"

Usage

Multi-Source Analysis

import asyncio

from pollux import Config, Source, run_many

async def main() -> None:
    config = Config(provider="gemini", model="gemini-2.5-flash-lite")
    sources = [
        Source.from_file("paper1.pdf"),
        Source.from_file("paper2.pdf"),
    ]
    prompts = ["Summarize the main argument.", "List key findings."]

    envelope = await run_many(prompts, sources=sources, config=config)
    for answer in envelope["answers"]:
        print(answer)

asyncio.run(main())

Configuration

from pollux import Config

config = Config(
    provider="gemini",
    model="gemini-2.5-flash-lite",
    enable_caching=True,
)

See the Configuration Guide for details.

Provider Differences

Pollux does not force strict feature parity across providers in v1.0. See the capability matrix: Provider Capabilities.

Documentation

• Quickstart — First result in 2 minutes
• Concepts — Mental model for source patterns and caching
• Sources and Patterns — Source constructors, run/run_many, ResultEnvelope
• Configuration — Providers, models, retries, caching
• API Reference — Entry points and types
• Cookbook — Scenario-driven, ready-to-run recipes

Origins

Pollux was developed as part of Google Summer of Code 2025 with Google DeepMind. Learn more →

Contributing

See CONTRIBUTING and TESTING.md for guidelines.

License

MIT