similarity search
A query operation over embeddings that returns the documents whose vectors are mathematically closest (most semantically similar) to a query.
As defined in This combo makes smart note systems magical.
Where it comes up · 2
- When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer9 claims
- This combo makes smart note systems magical.2 claims
Most important claims · 10 of 11Search all claims for “similarity search” →
- Vector retrieval fails with concentrated/homogeneous enterprise data because when multiple documents use the same specialized vocabulary (e.g., phone specs like megapixels, battery life, cameras), similarity search cannot disambiguate between different entities and context.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- A semantic search system can be built for Obsidian by vibe-coding a TypeScript plugin that calls Claude Code, which uses an MCP server to query a Chroma vector database storing embeddings of every note, enabling similarity search on meaning rather than keywords.This combo makes smart note systems magical.
- Embedding models work by converting a document into a vector of numbers that represents the document's meaning, a mechanism similar to the internal embeddings used inside large language models, which then enables similarity search across stored documents.This combo makes smart note systems magical.
- Graph-based RAG retrieves relevant documents using keys and relationships within a graph database, which preserves relational context and provides more information to the language model compared to vector similarity alone.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Graph-based RAG, which queries a graph database to retrieve relevant documents using keys and generate answers, preserves semantic relationships and provides more context to the model, significantly improving accuracy compared to vector-only retrieval.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Writer identified and discussed the benefits of knowledge graphs and shortcomings of vector databases for enterprise RAG at scale as early as November 2023, positioning the company ahead of industry recognition of this problem.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Writer's next approach used vector embeddings with chunking and stored results in a database for similarity search, then passed results to the LLM, but this caused two major problems: inaccurate answers from chunking artifacts and failure on concentrated data.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Writer's initial approach used algorithmic keyword search to query knowledge bases and pass results to the LLM, but this quickly failed because it was only effective for basic keyword searches and insufficient for advanced similarity search.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Writer initially started with basic keyword search (regular search/querying of knowledge bases) before moving to vector embeddings.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Vector embeddings with chunking and nearest-neighbor search was Writer's second major retrieval approach before moving to graph-based systems.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer