🗃️ Confluent
2 items
📄️ Anthropic
MongoDB - Anthropic Quickstart is an integrated end-to-end technology stack that combines MongoDB Atlas capabilities with Anthropic's Claude AI models to create an intelligent Agentic conversational interface. It allows users to interact with MongoDB data sources through natural language queries, leveraging vector search, full-text search, hybrid search and other advanced querying techniques.
📄️ Arcee
The MongoDB - Arcee Quickstart is a project aimed at facilitating the rapid and straightforward deployment of AI-driven applications utilizing MongoDB Atlas and the Arcee models. It offers scripts and configurations to streamline and automate the setup process, integrating MongoDB Atlas for data storage and Arcee models for AI functionalities.
📄️ Cohere
The MongoDB - Cohere Quickstart is a comprehensive, integrated end-to-end technology stack meticulously designed to facilitate the rapid development and seamless deployment of gen AI-powered applications. This innovative framework combines the robust capabilities of MongoDB Atlas for scalable data storage and advanced vector search functionalities with Cohere's state-of-the-art command-r-plus language model and Cohere's re-ranker for powerful natural language processing and retrieval.
📄️ Fireworks
BFSI Credit Recommendation & Scoring Application
📄️ IBM
Welcome to the MongoDB - IBM Quickstart, we will be using a financial dataset containing customer details, transactions, spending insights, and metadata, which we are storing in MongoDB Atlas, a fully managed cloud database platform. These records represent real-world scenarios such as payments, savings, and expenses, making the dataset highly relevant for building an intelligent finance assistant. To generate the vector embeddings for storing and retrieving this data, we will use the Granite Embedding Models (ibm-granite/granite-embedding-125m-english) from IBM Watsonx.ai. These embeddings capture the semantic meaning of financial data, enabling efficient similarity searches and contextual data retrieval. In addition to embedding models, Watsonx.ai also provides large language models (LLMs) for conversational chat query and retrieval capabilities, in our use case we are using Granite 3.0 (ibm/granite-3-8b-instruct) model, which are integral to this tutorial. By the end of this tutorial, you’ll have a functional system ready to support real-time financial assistance and personalized recommendations.
📄️ Langchain
Introduction to MongoDB Atlas with LangChain
📄️ Meta
The MongoDB - Meta Quickstart is a comprehensive, integrated end-to-end technology stack meticulously designed to facilitate the rapid development and seamless deployment of AI-powered Agentic applications. This innovative framework combines the robust capabilities of MongoDB Atlas for scalable data storage and advanced vector search functionalities with Meta's Llama AI state-of-the-art language models for powerful natural language processing and generation.
📄️ Temporal
The MongoDB - Temporal Quickstart is an integrated end-to-end AI application framework that combines MongoDB Atlas, Amazon Bedrock, and Temporal Workflow technology. The system provides a conversational AI interface with advanced memory capabilities, semantic caching, and robust document processing abilities.
📄️ TogtherAI
License: MIT