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
astronomer/ask-astro
Ask Astro is an open-source reference implementation illustrating an LLM application architecture, specifically designed to offer a Q&A interface for Apache Airflow® and Astronomer. It demonstrates an end-to-end LLM application incorporating several key components: Airflow DAGs for data ingestion from various sources into a vector database, an API for managing business logic related to user prompts and response generation, and user interfaces such as a Slack bot and a web UI. The project emphasizes data retrieval and embedding, prompt orchestration, and continuous feedback loops. For data retrieval, it leverages Retrieval Augmented Generation (RAG) by populating a Weaviate vector database with up-to-date information from sources like Airflow and Astronomer documentation, blogs, and GitHub repositories. Airflow DAGs handle the ingestion process, including data preprocessing, chunking, and embedding using OpenAI's embedding models. Prompt orchestration is managed via LangChain's ConversationalRetrievalChain, which rephrases prompts, retrieves relevant documents from the vector database, reranks them with Cohere, and generates answers using models like GPT-3.5-turbo and GPT-4o. Feedback loops are integrated to improve model performance over time, collecting user and LLM-generated feedback to refine answers and update the vector store, ensuring continuous learning and improvement. The project also outlines future exploration areas such as data privacy, fine-tuning, semantic caching, and enhanced observability for LLM operations.
https://github.com/astronomer/ask-astro
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.