Perplexideez - An open-source local AI search assistant that intelligently searches for and traces the source of information.
Perplexideez is a native AI assistant that enables users to quickly search for information on the web and in self-hosted applications. The Perplexideez project is based on the Postgres database, supports Ollam or OpenAI-compatible endpoints, and uses SearchXNG...
What is Perplexideez?
Perplexideez is a native AI assistant that enables users to quickly search for information on the web and in self-hosted applications. Based on the Postgres database, the Perplexideez project supports Ollam or OpenAI-compatible endpoints and uses SearchXNG instances for web searches. Perplexideez features multi-user support, single sign-on (SSO) functionality, and aesthetically pleasing embedded display of search results. Perplexideez aims to provide better integration with self-hosted services and a superior user experience.
Perplexideez's main functions
- Web searchUsing AI technology to help users filter online search results and improve search efficiency.
- Source tracing of conclusionsUsers can view the source annotations used by LLM (Large Language Model) and directly access the source code.
- In-depth studyLLM generates follow-up questions for users, making it easier for them to further explore content of interest.
- Search TrackingUsers can save search results that interest them for easy access later.
- Experience customizationIt supports users in selecting appropriate models based on different tasks and provides environment variables and UI configurations to optimize resource usage.
- Search sharingUsers can easily share search result links with others and have access controls implemented.
The technical principles of Perplexideez
- Natural Language Query: Use large language models (LLM) to process and understand natural language queries, filter search results, and generate relevant follow-up questions.
- Supports integration with Ollam or OpenAI-compatible endpoints, which provide interfaces for AI models to perform complex language processing tasks.
- Database supportThe project backend uses a Postgres database to store user data, search history, and preference settings, ensuring data persistence and multi-user support.
- Self-hosted search instanceBased on a SearchXNG instance, search the web. SearchXNG is an open-source, privacy-preserving meta-search engine.
- Multi-user and Single Sign-On (SSO)Supports multi-user access, with each user having an independent data view. Integrates with OIDC (OpenID Connect) SSO, allowing users to access multiple services with a single identity authentication.
- Containerized deploymentPerplexideez leverages container technologies such as Docker and Kubernetes to enable flexible deployment in various environments, including bare metal, virtual machines, and cloud platforms. Containerization also improves application portability and scalability.
Perplexideez project address
- GitHub repository:https://github.com/brunostjohn/perplexideez
Application scenarios of Perplexideez
- Personal knowledge managementIndividual users can search and organize their personal collections of information to quickly find the information they need.
- Internal Enterprise SearchAs an internal search engine, it helps employees quickly access the company's knowledge base, documents, and data.
- Research and AcademicResearchers and scholars can search for academic resources, track research citations, and generate research questions.
- educateEducational institutions assist in teaching, helping students and teachers quickly access educational resources and academic materials.
- Development and ProgrammingDevelopers can search for programming-related documents, code snippets, and development resources to improve development efficiency.