AI & ML Showcase

a natural language agent that connects to a SQL database, learns schema + domain context, and answers questions using a ReAct SQL loop.

It can: - Connect to any SQL database supported by SQLAlchemy - Introspect table/column schema automatically - Bootstrap a domain YAML from natural language description - Route tables/metrics and reason iteratively with grounded SQL evidence - Enforce read-only SQL validation before query execution

Production-grade AI agent framework built by the Pydantic team

PydanticAI is a Python framework for building production AI agents with type-safe structured outputs, dependency injection, streamed responses, and seamless integration with popular LLM APIs.

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.

The open-source AI-native embedding database

Chroma is an open-source, AI-native vector database designed for building LLM applications. It supports embedding storage and retrieval with first-class Python and JavaScript SDKs, and runs in-process for local development or as a hosted service.

Microsoft's framework for multi-agent AI conversation and automation

AutoGen (by Microsoft) enables developers to create LLM applications using multiple agents that can converse, delegate tasks, and collaborate. It supports complex agent topologies including human proxy agents and code-executing agents.

Build stateful, multi-actor AI agent applications with graph-based workflows

LangGraph is an open-source framework for building stateful, multi-actor applications using LLMs. It models agent workflows as directed graphs, enabling complex control flows, human-in-the-loop patterns, and persistent state for production agents.

Microsoft's SDK for integrating LLMs into apps with plugins and planners

Semantic Kernel is an open-source SDK from Microsoft that orchestrates AI models with native code, enabling developers to build AI applications that combine functions, plugins, memory, and planners in C#, Python, and Java.

Cloud-native open-source vector database built for scale

Milvus is an open-source cloud-native vector database built for billion-scale similarity search. It supports multiple index types, GPU acceleration, and a distributed architecture for enterprise-grade AI retrieval workloads.

Programming framework for algorithmically optimizing LM prompts

DSPy is a Stanford research framework that replaces manual prompt engineering with programmatic optimization. It treats prompts and LM calls as declarative modules and automatically optimizes them using optimizers like BootstrapFewShot and MIPRO.

Generate massive amounts of realistic fake data for testing and AI

Faker is the most widely used open-source library for generating realistic synthetic data. Available for Python, JavaScript, Go, and more, it generates names, addresses, dates, financial data, and 200+ data types for testing AI pipelines and training data.

Add validation, correction, and guardrails to LLM outputs

Guardrails AI is an open-source Python framework for specifying and enforcing structural, type, and quality constraints on LLM outputs. It provides a declarative way to validate, retry, and correct AI responses in production.

Production-ready LLM framework for building RAG and search pipelines

Haystack by deepset is an open-source Python framework for building production NLP and LLM applications. It provides a pipeline abstraction for RAG, document search, question answering, and conversational AI with 60+ integrations.