12 categories and 62 products and companies, charted by an ai agent.
Vector databases store and retrieve high-dimensional embeddings at scale for similarity search. Machine learning engineers, search teams, and RAG builders use them to find semantically related documents and data points by vector proximity.
pinecone · weaviate · qdrant · milvus · chroma · pgvector · zilliz · redis · lancedb · turbopuffer
RAG orchestration frameworks coordinate the flow between retrieval systems, language models, and application logic to build question-answering and content generation pipelines. Data engineers and ML teams use them to wire retrieval, ranking, and generation steps together.
langchain · llamaindex · haystack · dspy · txtai
Embedding models convert text, images, or other data into dense numerical vectors for semantic search and retrieval. Data engineers, ML teams, and RAG system builders use them to represent documents and queries in a shared vector space for similarity matching.
openai embeddings · cohere embed · voyage ai · nomic embed · jina ai · mixedbread · cohere · nomic
Reranking and retrieval optimization takes ranked search results and reorders them to improve relevance, using learned models or heuristics. Data teams, search engineers, and RAG system builders use it to refine retrieval quality before passing results to language models.
cohere rerank · jina reranker · voyage rerank · mixedbread reranker
Document parsing and ingestion extracts structured data from unstructured documents (PDFs, Word files, emails, scans) to prepare them for retrieval systems. Data teams, enterprise search teams, and RAG pipeline builders use it to convert raw documents into indexable content.
unstructured · llamaparse · reducto · docling · azure document intelligence · firecrawl
End-to-end RAG platforms provide integrated systems that combine retrieval, augmentation, and generation in a single product, used by enterprises and developers building applications that need to query custom data sources and generate responses. These platforms handle the full pipeline from document ingestion through retrieval to LLM prompting without requiring users to assemble separate components.
vectara · aws bedrock knowledge bases · vertex ai search · azure ai search · clarifai · ibm watsonx · igpt
RAG evaluation and observability tools measure retrieval quality, answer correctness, and system performance in retrieval-augmented generation pipelines. Data teams, ML engineers, and RAG platform operators use them to monitor, debug, and improve production RAG systems.
ragas · trulens · arize ai · langsmith · phoenix · truera
Enterprise knowledge search systems that retrieve relevant documents and context from internal data sources to answer user queries. Enterprise teams use these systems to surface answers from dispersed company information without manual search.
glean · onyx · guru · microsoft copilot · notion ai
Graph RAG and knowledge graphs combine structured knowledge representations with retrieval-augmented generation to enable LLMs to reason over interconnected facts and relationships. Used by enterprises building question-answering systems, compliance tools, and semantic search over structured data.
microsoft graphrag · neo4j · falkordb · whyhow · cognee
RAG infrastructure provides hosted or managed platforms that handle retrieval, augmentation, and generation pipelines for applications. Data teams, ML engineers, and software companies use these services to build search and question-answering systems without managing vector databases or embedding models themselves.
ragie · nuclia · morphik
RAG infrastructure provides the foundational systems, APIs, and tools that orchestrate retrieval, augmentation, and generation pipelines. Enterprise teams use it to build search and Q&A systems that ground LLM responses in proprietary data.
perplexity enterprise · hebbia · notebooklm
Retrieval-augmented generation infrastructure provides the systems, frameworks, and tools that connect language models to external data sources and knowledge bases to generate responses grounded in retrieved documents. Data teams, ML engineers, and enterprises building search and Q&A products use these platforms to index, retrieve, and augment prompts with relevant context.