Download
GenAI Processors is a lightweight Python library for building modular, asynchronous, and composable AI pipelines around Gemini. Its central abstraction is the Processor, a unit of work that consumes an asynchronous stream of parts (text, images, audio, JSON) and produces another stream, making it natural to chain operations and keep everything streaming end-to-end. Processors can be composed sequentially (to build multi-step flows) or in parallel (to fan-out work and merge results), which makes sophisticated agent behaviors easy to express with simple operators. The library offers built-in processors for classic turn-based Gemini calls as well as Live API streaming, so you can mix “batch” and real-time interactions in the same graph. It leans on Python’s asyncio to coordinate concurrency, handle network I/O, and juggle background compute threads without blocking.
Features
- Processor abstraction with async streams for text, image, audio, and JSON
- Easy composition with sequential chain and parallel fan-out operators
- Built-in processors for Gemini REST and Live API interactions
- Rich content parts with metadata, roles, and MIME information
- Stream utilities for splitting, concatenation, and merging
- Examples for research agents, real-time audio bots, and live commentary
Project Samples
