Open-Source Alternatives to Perplexity

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

Fireplexity is an AI-powered search engine designed to retrieve real-time web data and synthesize it into comprehensive, conversational answers. It functions as a search application that integrates automated web crawling to aggregate information from multiple online sources, grounding its responses in current internet content. The platform distinguishes itself through a focus on transparency and responsiveness. It provides verifiable citations and direct links to original source material for every generated answer, allowing users to confirm the accuracy and context of the information provided

This project is a web-based interface designed to automate multi-step research tasks by synthesizing web data through large language models. It functions as an research assistant that combines automated search queries, web scraping, and model-based synthesis to generate comprehensive reports. The platform distinguishes itself through an iterative agentic orchestration loop that manages complex investigations, coupled with a provider-agnostic abstraction layer that allows for seamless switching between different language models and search services. Users can monitor the research process in rea

This project provides a programmatic client for interacting with AI-powered search services. It is designed to automate research tasks by facilitating batch query processing, real-time response streaming, and document content analysis through both synchronous and asynchronous interfaces. To ensure continuous service access and high throughput, the system includes an automated account provisioning and lifecycle management framework. This allows for the rotation of authenticated sessions and the automatic renewal of credentials, which helps maintain access during high-volume operations. The pr

Gemini-Search is a conversational search interface that synthesizes real-time web data to provide answers to user queries. It functions as a generative AI grounding tool, connecting language models to live internet information to ensure responses are based on verifiable facts rather than training data alone. The platform distinguishes itself by anchoring model outputs to specific web sources, mapping segments of generated text directly to their original URLs. This approach enables source-verified content generation, allowing users to confirm the accuracy of information through provided citati

Open-deep-research is an automated research platform that utilizes autonomous agents to perform recursive web queries and synthesize information into structured reports. The system functions as an AI-powered research agent, capable of navigating complex topics by iteratively generating follow-up search queries and mapping interconnected findings. The platform distinguishes itself through a recursive orchestration model that allows for deep exploration of subjects beyond initial search results. It provides a unified interface for both cloud-based and local inference engines, enabling users to

This project provides a search service designed to retrieve and rerank web content for use in large language model applications. It functions as a retrieval augmented search engine that processes natural language queries to fetch contextually relevant information from external web sources. The system distinguishes itself through a combination of semantic retrieval and precision-focused reranking. It converts user queries into high-dimensional embeddings to perform similarity searches across indexed collections, then refines these results by passing candidate pairs through a secondary model to

OpenChatKit is a training and inference toolkit for large language models. It provides a comprehensive set of tools for managing the model lifecycle, including a fine-tuning pipeline, a model weight converter, and a command-line interface for interacting with conversational agents. The toolkit features a framework for retrieval augmented generation, allowing models to incorporate relevant context from external vector indices. It also includes utilities for converting trained model checkpoints into formats compatible with standard inference libraries. The project covers conversational AI trai

Quivr is a framework for building retrieval-augmented generation pipelines that connect large language models to custom knowledge bases. It serves as a generative AI integration layer that abstracts the process of transforming diverse document sources into searchable context for AI responses. The project orchestrates the end-to-end flow between document ingestion, vector storage management, and model provider interfaces. It features a vector-store-agnostic retrieval system and a modular API layer that allows for flexible switching between different generative model providers. The system cove

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

Dynamiq is an agent development platform designed for building, orchestrating, and monitoring autonomous agents. It provides a framework for constructing complex, multi-step workflows using a graph-based engine that supports conditional branching, feedback loops, and iterative task execution. The platform distinguishes itself through its focus on secure, private infrastructure, allowing for the deployment of language models and orchestration services within virtual private clouds to maintain data sovereignty. It integrates retrieval-augmented generation pipelines to ground model responses in

TaskingAI is an AI agent orchestrator and application platform used to build, deploy, and scale AI-native applications. It functions as a multi-tenant backend as a service, providing the infrastructure to host and manage independent AI agent instances across multiple users or organizations on a shared architecture. The platform features a visual workflow builder and project management console, allowing users to configure agent logic and test conversation workflows through a graphical interface before moving them to a production environment. The system orchestrates large language models by st