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
pixeltable/pixeltable
Pixeltable provides a comprehensive Python API for building AI data applications, aiming to simplify the process by combining functionalities typically handled by multiple disparate systems. It allows users to store various media types (images, video, audio, documents, JSON) alongside structured data in a single system, supporting cloud storage destinations. The platform facilitates data import and export from diverse sources, including files, URLs, and Hugging Face datasets, and can export to formats like Parquet, PyTorch, and COCO. Pixeltable offers iterative processing capabilities, enabling the splitting of documents into chunks, video into frames, and audio into segments through declarative views and built-in or custom iterators. Its core orchestration mechanism uses declarative computed columns that run incrementally, supporting over 30 AI integrations for LLM providers and local models, including multimodal vision tasks. Developers can extend Pixeltable's capabilities with user-defined functions (UDFs) and queries, which benefit from built-in caching and retry mechanisms. Furthermore, it integrates vector search with `add_embedding_index()`, ensuring indexes stay synchronized with table data and allowing combined similarity and metadata filtering within a single query, thus replacing the need for separate vector databases.
https://github.com/pixeltable/pixeltable
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.