Search AI & ML Showcase

Graph-based RAG that extracts knowledge graphs for better retrieval

GraphRAG is an open-source framework from Microsoft Research that uses LLMs to extract entities and relationships into a knowledge graph, enabling global reasoning over large document corpora that traditional RAG cannot handle.

The most widely adopted framework for building LLM-powered applications

LangChain is an open-source framework for building applications powered by large language models. It provides composable building blocks for chains, agents, memory, RAG pipelines, and tool integrations across 50+ LLM providers.

OpenTelemetry-compatible tracing standard for AI/LLM applications

OpenInference is an open standard for capturing AI model observability data using OpenTelemetry. It enables vendor-neutral tracing of LLM calls, embeddings, and retrieval operations across any observability backend.

High-performance vector database with rich filtering for production AI

Qdrant is an open-source vector similarity search engine built in Rust. It supports dense and sparse vectors, rich payload filtering, named vectors, and advanced quantization — designed for high-throughput production AI workloads.

Open-source MLOps platform for the full ML lifecycle

MLflow is an open-source platform for managing the complete machine learning lifecycle including experiment tracking, model packaging, model registry, and deployment. Widely adopted across data science and ML engineering teams.

Open-source AI observability and evaluation for LLMs and ML models

Phoenix by Arize is an open-source AI observability platform that provides real-time tracing, evaluation datasets, and retrieval analysis for LLM and ML applications. Runs locally or on cloud infrastructure.

Modern workflow orchestration for data and ML pipelines

Prefect is an open-source workflow orchestration platform for data engineering and ML pipelines. It provides observability, scheduling, and retry logic for Python workflows with a hybrid execution model.

Git for data — version control for ML data, models, and pipelines

DVC (Data Version Control) is an open-source ML experiment and data versioning tool built on top of Git. It enables reproducible ML pipelines, tracks datasets and models alongside code, and integrates with all major cloud storage providers.

Streamlined fine-tuning for LLMs with LoRA, QLoRA, and full fine-tune

Axolotl is an open-source fine-tuning framework that simplifies training LLMs with LoRA, QLoRA, FSDP, and DeepSpeed. It supports a wide range of base models and dataset formats with a single YAML config.

Up to 5x faster, 80% less memory LLM fine-tuning

Unsloth makes LLM fine-tuning up to 5× faster and uses up to 80% less GPU memory by using custom CUDA kernels and optimized training paths. Compatible with Hugging Face ecosystem, LoRA, QLoRA, and popular base models.

Open-source LLM evaluation framework for CI/CD pipelines

DeepEval is an open-source evaluation framework for testing and monitoring LLM applications. It provides 14+ evaluation metrics, integrates with pytest, and enables continuous LLM quality testing in CI/CD workflows.

The standard library for working with pretrained ML models

Transformers by Hugging Face is the most widely used open-source library for working with pretrained models across NLP, vision, audio, and multimodal tasks. Supports PyTorch, TensorFlow, and JAX with 500k+ models on the Hub.