Clayton Yochum's starred repositories
haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
fastapi-best-practices
FastAPI Best Practices and Conventions we used at our startup
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
instructor
structured outputs for llms
guardrails
Adding guardrails to large language models.
git-absorb
git commit --fixup, but automatic
faststream
FastStream is a powerful and easy-to-use Python framework for building asynchronous services interacting with event streams such as Apache Kafka, RabbitMQ, NATS and Redis.
fastapi-tips
FastAPI Tips by The FastAPI Expert!
WhisperLive
A nearly-live implementation of OpenAI's Whisper.
whisper_streaming
Whisper realtime streaming for long speech-to-text transcription and translation
prometheus-fastapi-instrumentator
Instrument your FastAPI with Prometheus metrics.
inline-snapshot
create and update inline snapshots in your python tests
how-do-i-locust
A quick overview of Locust, the load testing tool
structlog-gcp
Google Cloud Logging formatter for structlog
locust-httpx-testing
Locust testing using httpx as a client
capture-uvicorn-output
Example how to capture the output from a process in python