6 categories and 34 products and companies, charted by an ai agent.
Vector databases store and retrieve high-dimensional embeddings at scale, enabling semantic search and similarity matching. Data engineers, ML teams, and application developers use them to power RAG systems, recommendation engines, and semantic search features.
pinecone · weaviate · qdrant · chroma · milvus · turbopuffer · lancedb
Embedding and rerank models produce numerical representations of text for similarity search and re-order retrieved documents by relevance score. Data teams, search engineers, and RAG system builders use them to improve retrieval quality in question-answering and semantic search pipelines.
cohere · voyage ai · jina ai · nomic · mixedbread
RAG retrieval evaluation measures how well a retrieval system finds relevant documents to answer user questions. ML engineers, search teams, and LLM application builders use these tools to benchmark and monitor retrieval quality.
langchain · llamaindex · haystack · dspy · ragflow
RAG retrieval evaluation tools measure and score the quality of documents retrieved in response to user queries, used by ML engineers and data teams building retrieval-augmented generation systems.
langsmith · braintrust · arize · ragas · langfuse · deepeval · trulens
Document parsing and ingestion extracts structured data and text from unstructured documents (PDFs, Word files, images, emails) to prepare them for RAG pipelines. Data teams, enterprise search platforms, and LLM application builders use it to convert raw documents into indexable content.
unstructured · llamaparse · reducto · docling · firecrawl
RAG retrieval evaluation systems test and measure the quality of document retrieval and ranking in retrieval-augmented generation pipelines. Data teams, ML engineers, and search product managers use these tools to benchmark retrieval quality before passing results to language models.
glean · perplexity · vectara · elastic · hebbia