Search Results for "rag"

Trieve is an all-in-one infrastructure for building hybrid vector search, recommendations, and RAG.

Korvus is an open-source retrieval-augmented generation (RAG) pipeline designed to run entirely inside PostgreSQL, allowing developers to build AI search and knowledge systems directly within a database environment. The project consolidates the typical steps of a RAG pipeline—including embedding generation, document retrieval, reranking, and text generation—into a single query executed within the Postgres ecosystem.

...The interface is intentionally familiar, offering a ChatGPT-like experience with customizable branding, fast Rust-based performance, and conversation history management. Beyond chat, Bionic focuses heavily on enterprise RAG by letting users create AI assistants that work with their own documents, share those assistants across teams, and configure embeddings, chunking, and system prompts through the UI. The platform supports a wide variety of document types, includes data isolation features for teams, and layers in security measures such as RBAC, row-level security in Postgres, strong content security policy settings, and minimal container builds.

Arch is an intelligent Layer 7 gateway designed to protect, observe, and personalize LLM applications (agents, assistants, co-pilots) with your APIs. Engineered with purpose-built LLMs, Arch handles the critical but undifferentiated tasks related to the handling and processing of prompts, including detecting and rejecting jailbreak attempts, intelligently calling "backend" APIs to fulfill the user's request represented in a prompt, routing to and offering disaster recovery between upstream...

CocoIndex is an open-source framework designed for building powerful, local-first semantic search systems. It lets users index and retrieve content based on meaning rather than keywords, making it ideal for modern AI-based search applications. CocoIndex leverages vector embeddings and integrates with various models and frameworks, including OpenAI and Hugging Face, to provide high-quality semantic understanding. It’s built for transparency, ease of use, and local control over your search...

Shinkai is a free, open-source AI platform that lets anyone create powerful AI agents without coding. These agents can collaborate with each other, handle complex tasks, and operate in decentralized crypto environments. Key Features: - No-Code Agent Creation - Build specialized agents (trading bots, sentiment trackers, etc.) with simple descriptions - Multi-Agent Collaboration - Agents work together to solve complex problems - Crypto Integration - Built-in support for decentralized...