A toolkit for detecting file formats and extracting text and metadata.
Search & Retrieval
Finding relevant information through search, crawling, embeddings, and retrieval for AI applications.
Saved Links in Search & Retrieval
A Python framework for fetching websites and extracting structured data.
Documentation for a self-hosted document management system.
Hugging Face documentation for a model that retrieves document pages using visual representations.
Cohere's announcement of the Command R7B language model.
Google Cloud's announcement of Agentspace for enterprise search and agent workflows.
A LangChain example that combines language models with iterative web research and summarization.
A search and discovery service for academic literature.
Vercel examines traffic from crawlers used by AI services.
A self-hostable interface for interacting with language models.
A conversational knowledge base that combines retrieval and graph-based information with TiDB storage.
A web crawling and extraction toolkit for preparing website content for AI applications.