A cloud-native vector database, storage for next generation AI applications
-
Updated
Jul 26, 2024 - Go
A cloud-native vector database, storage for next generation AI applications
cuVS - a library for vector search and clustering on the GPU
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
A website that summarizes PDFs into simple paragraphs based on user's queries_using Streamlit, LangChain, OpenAI, and ChromaDB Docker Image technologies.
An AI-based application leveraging Gemini/OpenAI and JinaAI embeddings with a FastAPI backend and Svelte frontend. The app can read PDFs, maintain webpage memory, and facilitate interactive chat with websites, webpages, and PDFs.
An LLM powered chatbot that can answer questions based on your specific data
Vector Index / Vector Store implemented in go, nginx load balancing and an angular management frontend
just testing langchain with llama cpp documents embeddings
Kubernetes-native package for Weaviate, an AI-native vector database that helps developers create intuitive and reliable AI-powered applications.
Incorporar distintos tipos de documentos simultáneamente a la base de datos de embeddings Chroma con LangChain.
🗲 A high-performance on-disk dictionary.
Final Project for Information Retrival, this is an implementation that uses numpy of a vector store and a RAG PoC with ollama
The AI Assistant uses OpenAI's GPT models and Langchain for agent management and memory handling. With a Streamlit interface, it offers interactive responses and supports efficient document search with FAISS. Users can upload and search pdf, docx, and txt files, making it a versatile tool for answering questions and retrieving content.
Chat and Ask on your own data. Accelerator to quickly upload your own enterprise data and use OpenAI services to chat to that uploaded data and ask questions
React Hook for indexed-vector-store package
A Question Generation Application leveraging RAG and Weaviate vector store to be able to retrieve relative contexts and generate a more useful answer-aware questions
Semantic product search on Databricks
Add a description, image, and links to the vector-store topic page so that developers can more easily learn about it.
To associate your repository with the vector-store topic, visit your repo's landing page and select "manage topics."