Open-source alternatives to Pgai

This project is a retrieval augmented generation framework designed to build pipelines that connect unstructured data and knowledge graphs with large language models. It functions as a vector database orchestrator for indexing text and multimodal content, as well as a system for translating natural language queries into structured database commands. The framework integrates a hybrid retrieval engine that combines dense vector search with sparse keyword matching to increase the precision of retrieved contexts. It further enhances reasoning and relationship mapping through a graph-augmented ret

RavenDB is a multi-model NoSQL document database designed for high-performance, ACID-compliant data storage. It persists structured information as schema-flexible JSON documents and utilizes a unit-of-work session pattern to track entity changes and batch modifications into atomic transactions. The platform is built on a distributed architecture that supports horizontal scaling through sharding and ensures high availability via multi-node, master-to-master cluster replication. The database distinguishes itself through a self-optimizing query engine that automatically creates and maintains ind

This project is a reference implementation and application template for Retrieval-Augmented Generation (RAG). It integrates Azure OpenAI with Azure AI Search to enable conversational chat interfaces that provide grounded responses based on private enterprise data. The system is distinguished by its multimodal AI interface, allowing it to process and reason over combined text, image, and PDF content. It employs a hybrid search architecture that combines vector and keyword retrieval with semantic reranking to prioritize the most relevant documents for prompt augmentation. The project covers a

QAnything is a retrieval-augmented generation application framework and self-hosted AI interface. It functions as a system that combines a vector database knowledge base, a document parsing service, and a hybrid search engine to generate answers based on private user data. The project features a modular pipeline architecture that allows users to independently replace components such as parsers, embedding models, and reranking engines. It supports local-first model deployment and offline operation to ensure data privacy, and includes a two-stage retrieval pipeline that merges dense vector embe

LanceDB is a vector database and columnar data store designed to function as a versioned dataset manager and vector search engine. It serves as a high-performance backend for indexing and retrieving high-dimensional embeddings, providing the foundation for machine learning data pipelines. The system distinguishes itself through a combination of cloud-native object storage and immutable version tracking, allowing for data time-travel and reproducible AI experiments. It integrates hybrid search capabilities, merging dense vector similarity with BM25 full-text search and SQL-like scalar filters

This project is a LangChain-based framework for building retrieval-augmented generation systems, autonomous agents, and multimodal chatbots. It functions as an open-source orchestrator that connects local inference engines and online APIs to manage various large language model deployments. The system distinguishes itself by providing specialized interfaces for local knowledge bases, allowing the loading and vectorization of private documents to create context-aware assistants. It also supports multimodal capabilities, enabling the processing of both text and image inputs through vision-capabl

AdalFlow is an autonomous AI agent framework and LLM application library designed for building modular workflows. It serves as a model-agnostic interface and RAG pipeline orchestrator, allowing users to develop ReAct agents that utilize iterative reasoning and external tool execution to solve complex tasks. The project distinguishes itself through a prompt optimization system that uses textual gradient descent to automatically refine prompt templates and few-shot examples. It treats model feedback as a differentiable signal, enabling a form of LLM backpropagation to iteratively improve output

This project is a collection of educational resources and technical guides focused on the development and implementation of large language models. It provides a comprehensive curriculum covering transformer architectures, training methods, and deployment strategies. The materials provide detailed instructions for building autonomous agents using reasoning loops and tool integration, as well as guides for fine-tuning models through supervised learning and preference optimization. It also includes tutorials for constructing retrieval augmented generation pipelines and implementing transformer m

Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

PostgresML is a machine learning database extension for PostgreSQL that integrates model training and inference directly into the database. It functions as an in-database AI platform and vector database, enabling the execution of large language models and natural language processing tasks on stored records without exporting data to external services. The system distinguishes itself by utilizing GPU acceleration to minimize latency during model predictions and employing a hybrid storage engine that maintains relational data alongside high-dimensional vectors. It allows for the building and fin

SuperduperDB is an AI agent orchestrator and database-integrated machine learning platform. It serves as a framework for building stateful AI agents and retrieval-augmented generation applications by integrating large language models directly with database backends. The project enables the deployment of self-hosted AI infrastructure and the management of language models on private hardware using local checkpoints. It distinguishes itself by allowing users to attach AI components directly to data fields, triggering model execution and automated transformations based on database insertions and

Cactus is an on-device AI inference engine designed for executing large language models, vision models, and speech-to-text systems on mobile and wearable hardware. It provides a programmable tensor computation graph for defining sequences of matrix operations and activation functions, alongside a local retrieval augmented generation framework that grounds model responses using local text files. The project features a multiplatform SDK with language bindings for integrating AI capabilities into mobile applications and a model conversion system that transforms external model formats for optimiz

LEANN is a framework for local retrieval augmented generation and vector indexing. It functions as a system for building local knowledge bases and source code search engines that combine large language models with retrieved private data to generate context-aware responses. The project distinguishes itself through a vision-model based document layout extractor for parsing complex PDF figures and diagrams, and a source code search engine that employs structure-aware chunking to preserve function and class boundaries. It also implements the Model Context Protocol to integrate real-time data sour

This project is a technical curriculum and development guide focused on large language model prompt engineering, fine-tuning, and the creation of retrieval augmented generation applications. It serves as a comprehensive resource for developers to master crafting precise instructions and textual patterns to improve the quality and predictability of model outputs. The material covers the end-to-end workflow of adapting open-source models to specific datasets and integrating language models with vector databases to generate responses based on private information. It also provides a systematic ap

This project is a transformer-based framework for generating dense and sparse vector embeddings of text and multimodal data. It serves as a library for fine-tuning models to perform semantic similarity tasks, retrieval, and reranking. The system is distinguished by its support for diverse architectural patterns, including bi-encoders for fast similarity search and cross-encoders for high-precision reranking. It provides dedicated pipelines for multimodal embeddings, mapping text and images into a shared vector space, and implements knowledge distillation to compress large models into smaller,

This project is an educational implementation guide and framework for building Retrieval Augmented Generation systems. It provides a workflow for constructing a knowledge base pipeline that partitions documents, indexes them as vectors, and provides external context for language model prompts. The system features a document chunking framework that uses recursive character splitting to fit text into model context windows. It includes an in-memory vector store and a similarity search system that retrieves relevant text segments by calculating the mathematical distance between dense embedding ve

This project is a high-performance BERT embedding service and inference server designed to map text sequences into fixed-length numerical vectors. It functions as a machine learning microservice and distributed model server that decouples request handling from heavy computation. The system utilizes a ZeroMQ messaging infrastructure to provide low-latency communication between distributed clients and the inference server. It incorporates server-side batch processing and GPU workload scaling to maximize hardware utilization and manage high request volumes. The platform supports semantic search

text2vec is a text vectorization toolkit and semantic similarity framework used to convert words and sentences into numerical vectors. It provides integrated toolsets for generating embeddings, calculating semantic closeness, and implementing lexical and semantic search. The project includes a model fine-tuning pipeline for optimizing embedding and matching models using supervised or unsupervised datasets. It further distinguishes itself by providing a text embedding API that allows vectorization models to be deployed as network services via gRPC or HTTP protocols. The framework covers a bro

Rags is an orchestration tool for building retrieval-augmented generation pipelines and managing conversational data interfaces. It serves as a system for creating these pipelines from local files and web pages using natural language instructions to query, retrieve, and summarize information from connected datasets. The project features a multimodal retrieval system that identifies and extracts information across different data types and modalities. It includes a vector search orchestrator to manage chunking strategies and search parameters, alongside a pipeline builder that translates conver

MineContext is a context management system designed to collect, store, and retrieve multimodal data to build targeted context windows for large language models. It functions as an orchestration tool and retrieval augmented generation framework that utilizes a local vector data store to index documents and enable similarity searches. The system differentiates itself through a multimodal context collector that gathers information from screen captures, files, and version control systems. It provides mechanisms for proactive information retrieval, extracting summaries and activity records from ca

document.ai is a local document question-answering system and vector database search engine. It functions as a retrieval-augmented generation knowledge base that combines a vector database with language models to generate answers grounded in private local datasets. The project features a domain-specific embedding pipeline and a fine-tuned language model framework. These tools allow for the use of specialized embedding models and mathematical theme extraction to improve retrieval accuracy for professional terminology and technical subject areas. The system covers vector-based semantic retriev

llm-zoomcamp is a comprehensive educational program and course for building real-life AI systems using large language models. It serves as a structured curriculum and implementation guide for developing AI applications and retrieval techniques. The project provides instructional material on building retrieval augmented generation pipelines to ground model responses in custom knowledge bases. It includes training on vector database implementation, semantic search, and the use of function calling to create autonomous agentic workflows. The curriculum covers a broad range of system development

localGPT is a private AI knowledge base and retrieval-augmented generation application. It provides a local document indexer, a hybrid search engine, and an inference interface to enable chatting with private documents and managing a self-hosted information repository without sending data to external servers. The system distinguishes itself through a dual-pass verification pipeline that ensures generated answers are grounded in retrieved sources, accompanied by explicit source attribution. It employs a hybrid retrieval approach combining semantic vector search with keyword matching and rerank

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Vercel is a cloud platform for building, deploying, and scaling web applications. It provides a unified infrastructure that automates the build process by detecting project frameworks and distributing static and dynamic content through a global content delivery network. The platform executes application logic using serverless functions that scale automatically based on real-time traffic demand. The platform distinguishes itself through a centralized AI gateway that proxies requests to multiple model providers, enabling standardized authentication, observability, and cost tracking. It supports