pathwaycom/llm-app
Ready-to-run cloud templates for building real-time RAG, AI pipelines, and enterprise search applications that synchronize with various live data sources.
Awesome Infra for AI › Vector Databases & Retrieval Infrastructure
lightonai/next-plaid
NextPlaid is a robust, local-first multi-vector database and indexing engine designed for efficient retrieval workloads. It differentiates itself from traditional single-vector databases by storing multiple embeddings per document, allowing for richer semantic representations, particularly beneficial for complex data like code. NextPlaid features built-in encoding for ColBERT models using ONNX Runtime, offering a complete search solution without external inference servers. Its architecture emphasizes resource efficiency with memory-mapped indices, low RAM footprint, and product quantization (2-bit or 4-bit compression), enabling millions of documents to fit in memory. The engine supports incremental updates, allowing documents to be added and deleted without full index rebuilds, and integrates metadata pre-filtering via SQL WHERE clauses on an embedded SQLite store to refine search results before scoring. It is primarily CPU-optimized but also supports CUDA for enhanced performance when needed. NextPlaid is the underlying technology for ColGREP, a semantic code search tool that combines regex filtering with semantic ranking for developer terminals and AI coding agents. ColGREP allows users to build and search indexes locally, integrating with tools like Claude Code, OpenCode, and Codex. It processes code units into structured text before embedding, providing richer context for the model.
https://github.com/lightonai/next-plaid
Also in Vector Databases & Retrieval Infrastructure
run-llama/llama_index
LlamaIndex is an open-source data framework for building LLM applications by connecting custom data sources to large language models, focusing on data ingestion, indexing, and retrieval augmented g...
milvus-io/milvus
Milvus is a high-performance, cloud-native vector database designed for scalable vector Approximate Nearest Neighbor (ANN) search, efficiently organizing and searching vast amounts of unstructured ...
VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes from documents and uses LLMs to reason over them for context-aware retrieval.
qdrant/qdrant
Qdrant is an open-source, high-performance vector similarity search engine and vector database designed specifically for AI applications, enabling fast storage, search, and management of vectors wi...
Tencent/WeKnora
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and autonomous reasoning, featuring RAG, ReAct agents, and an auto-maintaining ...
topoteretes/cognee
Cognee is an open-source AI memory platform that provides AI agents with persistent long-term memory through a self-hosted knowledge graph, combining vector embeddings and graph reasoning.
RyanCodrai/turbovec
TurboVec is a Rust-based approximate nearest neighbor (ANN) vector index with Python bindings, built on Google Research's TurboQuant algorithm for efficient, memory-optimized vector similarity search.