15 categories and 74 products and companies, charted by an ai agent.
Vector databases store and retrieve high-dimensional embeddings to power semantic search and RAG systems. Used by AI engineers, data scientists, and enterprises building LLM applications.
pinecone · weaviate · qdrant · milvus · chroma · pgvector · turbopuffer · lancedb · zilliz
RAG orchestration frameworks combine retrieval-augmented generation with workflow automation to coordinate data retrieval, processing, and LLM interactions. Used by enterprises building AI applications that need to ground model outputs in external knowledge sources.
langchain · llamaindex · haystack · dspy · r2r · ragflow · cognita
unstructured · llamaparse · reducto · docugami · upstage document parse
Embedding model providers create vector representations of text and documents that power semantic search and RAG systems. Used by developers, enterprises, and AI teams building knowledge retrieval applications.
openai embeddings · cohere embed · voyage ai · mixedbread · jina ai · cohere · nomic
Enterprise RAG platforms enable organizations to build retrieval-augmented generation systems that ground AI responses in proprietary data and documents. Knowledge workers, developers, and enterprises use these to create accurate, contextualized AI assistants over internal knowledge bases.
glean · microsoft copilot for m365 · notion ai · guru · coveo · elastic enterprise search · vectara · aws bedrock knowledge bases · microsoft copilot · hebbia
cohere rerank · jina reranker · flashrank · bm42 hybrid search
Knowledge graph RAG combines structured knowledge graphs with retrieval-augmented generation to provide factually grounded, contextual AI responses. Enterprises use it for customer support, research, and knowledge management.
microsoft graphrag · neo4j graphrag · falkordb · ontotext graphdb
Vertical RAG assistants are specialized AI systems that retrieve and synthesize domain-specific knowledge from proprietary documents and databases to answer expert questions. Used by enterprises, professional services, and knowledge-intensive industries to automate expert consultation and decision support.
glean for salesforce · danswer · mendable · kapa ai · dust · emma
AI-native search engines use RAG (retrieval-augmented generation) to combine real-time information retrieval with large language models for conversational, contextual answers. Used by researchers, professionals, and enterprises seeking faster knowledge discovery beyond traditional search.
perplexity · you.com · exa · phind · tavily
ragas · arize phoenix · trulens · langsmith
perplexity deep research · openai deep research · gemini deep research · storm (stanford)
Multimodal RAG systems combine text, images, audio, and video retrieval with generative AI to answer complex questions across document types. Used by enterprises managing mixed-media knowledge bases, research teams, and content-heavy organizations.
RAG as a Service delivers retrieval-augmented generation capabilities through managed APIs and cloud platforms, used by developers and enterprises to add context-aware AI without building retrieval infrastructure. The service handles document ingestion, embedding, retrieval, and generation in a single managed product.
ragie · nuclia · morphik
Systems that store, organize, and retrieve personal notes, research, and accumulated knowledge; used by researchers, students, professionals, and knowledge workers who need to surface relevant past information during thinking and writing.
notebooklm · mem
Legal and medical research RAG systems retrieve and synthesize information from specialized corpora of case law, medical literature, regulatory documents, and clinical data to support lawyers, physicians, and researchers in decision-making and evidence discovery. Users include law firms, healthcare institutions, pharmaceutical companies, and regulatory bodies.
harvey · openevidence · casetext · evenup