RAG

Builds a context limited to the PDFs, docs and links you upload, and refuses to answer outside them. in AI · Models & Assistants →

Turns your query into a web search, feeds the retrieved pages to a model, then footnotes each sentence. in AI · Models & Assistants →

The most widely used family of open embedding models. in AI · RAG, Embeddings & Vectors →

Combines BM25 keyword search with vector search in a single query and fuses the results with RRF. in AI · RAG, Embeddings & Vectors →

Walks a codebase via AST analysis and folds in docs, SQL schemas and PDFs to build a queryable graph. in AI · RAG, Embeddings & Vectors →

Extracts entities and relations into a knowledge graph, then builds community summaries. in AI · RAG, Embeddings & Vectors →

You wire components together explicitly, so what happens at each stage stays readable. in AI · RAG, Embeddings & Vectors →

Multimodal embedding and search infrastructure that makes documents and images searchable by vector. in AI · RAG, Embeddings & Vectors →

Makes each stage — loading, chunking, indexing, querying — independently swappable. in AI · RAG, Embeddings & Vectors →

An end-to-end vector search engine that handles everything from embedding generation to search. in AI · RAG, Embeddings & Vectors →

Relationships are first-class data, not foreign keys. in AI · RAG, Embeddings & Vectors →

A fully managed vector database whose serverless tier removes capacity planning. in AI · RAG, Embeddings & Vectors →

A metrics library for RAG pipelines, including metrics that work without reference answers. in AI · RAG, Embeddings & Vectors →

Built on deep document parsing: it recognises complex PDF layouts, tables and figures before chunking. in AI · RAG, Embeddings & Vectors →

Measures the RAG triad — context relevance, groundedness, answer relevance. in AI · RAG, Embeddings & Vectors →

Reduces PDF, DOCX, HTML, email and slides to a shared document-element model. in AI · RAG, Embeddings & Vectors →

Open-source AI answering engine (formerly Perplexica) that pairs web search with local or cloud LLMs to produce cited… in AI · RAG, Embeddings & Vectors →

Maintains a temporal knowledge graph for agents, recording when a fact held and when it was invalidated. in AI · RAG, Embeddings & Vectors →

Collects many documents into one library you can query together, with page-cited answers. in AI · Applied Tools →

Merges snippet search with chat. Unlike general chatbots, it searches repositories and docs and uses the hits as context. in AI · Applied Tools →

Searches open datasets scattered across the web via schema.org markup. in Data Science & ML →