History

Russell Ballestrini 60b61b5a7e fix build failures: haskell streaming with withResponse, java-openai 4.3.0 with proper API, go-openai fixes, mojo real container		2025-10-15 18:09:13 -04:00
..
Dockerfile	fix build failures: haskell streaming with withResponse, java-openai 4.3.0 with proper API, go-openai fixes, mojo real container	2025-10-15 18:09:13 -04:00
hermes_nonstreaming.mojo	fix Docker builds: go-http missing files, go-openai go.sum, csharp-openai SDK API, D language JSONValue syntax	2025-10-15 16:53:15 -04:00
qwen_nonstreaming.mojo	fix Docker builds: go-http missing files, go-openai go.sum, csharp-openai SDK API, D language JSONValue syntax	2025-10-15 16:53:15 -04:00
README.md	fix Docker builds: go-http missing files, go-openai go.sum, csharp-openai SDK API, D language JSONValue syntax	2025-10-15 16:53:15 -04:00

README.md

Mojo Language Examples

⚠️ STREAMING NOT YET IMPLEMENTED

The Mojo programming language is an AI-focused systems language from Modular. While Lightbug HTTP client exists, streaming support for Server-Sent Events (SSE) is not yet available in the Lightbug library as of 2025-10-15.

Current Status

✅ Non-streaming examples: Implemented for Hermes and Qwen ❌ Streaming examples: NOT IMPLEMENTED (waiting for Lightbug SSE support) ❌ TTS example: NOT IMPLEMENTED (binary response handling not ready)

Available Examples

# Run Hermes non-streaming example
magic run mojo hermes_nonstreaming.mojo

# Run Qwen non-streaming example
magic run mojo qwen_nonstreaming.mojo

Why Mojo?

Mojo is a new language designed for AI/ML workloads with:

Performance comparable to C/C++
Python-like syntax
Zero-cost abstractions
Built for AI infrastructure

Future Work

Once Lightbug HTTP adds streaming support, we will implement:

Hermes streaming example
Qwen streaming example
TTS speech generation example