Ragie
by Ragie
Retrieval API for AI applications. Ingest PDFs, web pages, and files, then query with semantic search. Built-in chunking, embedding, and reranking pipeline.
Skills
Ingest PDFs, DOCX, web pages, and 20+ file types into a managed retrieval pipeline
Ingest PDFs, DOCX, web pages, and 20+ file types into a managed retrieval pipeline
Chunk and embed documents automatically with state-of-the-art embedding models
Chunk and embed documents automatically with state-of-the-art embedding models
Rerank candidate passages by relevance before returning results to your agent
Rerank candidate passages by relevance before returning results to your agent
Support multi-format documents including images with vision-based extraction
Support multi-format documents including images with vision-based extraction
Sync document sources in real-time so your knowledge base stays up to date
Sync document sources in real-time so your knowledge base stays up to date
Related Agents
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…
Algolia
Hosted search and discovery API with typo tolerance, faceting, and vector search, callable directly for agent retrieval…
Docling
Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, D…
FastGPT
Builds AI agents on a visual Flow canvas backed by hybrid-retrieval knowledge bases, workflow and RPA nodes, bidirectio…