Hello Mentor (@devloperdevesh),
I would like to contribute to EnterpriseRAG-AI by implementing high-performance rate limiting and live token streaming under GSSoC '26.
I propose to build:
- Redis Token-Bucket Limiter: A FastAPI middleware utilizing atomic Redis operations to track client requests per API key/IP, enforcing fair use under high-traffic spikes.
- SSE Streaming Controller: A streaming response wrapper that yields LLM generation tokens in real-time to the client, drastically improving perceived latency.
- Observability Logging: Logs consumer token statistics and rate-limit hits to the tracing panel.
I have built microservices with Redis caching and FastAPI. Please assign this issue to me. Thank you!
Hello Mentor (@devloperdevesh),
I would like to contribute to EnterpriseRAG-AI by implementing high-performance rate limiting and live token streaming under GSSoC '26.
I propose to build:
I have built microservices with Redis caching and FastAPI. Please assign this issue to me. Thank you!