--- title: "#embeddings articles | Hashnode" description: "Explore 130 articles tagged #embeddings on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/embeddings" --- Tag # #embeddings 130 posts · 6 followers [Sotiris Zacharopoulos](https://hashnode.com/@sz-codapus-studio) · [1d ago](https://hashnode.com/posts/semantic-search-playbook-retrieval-negation/6af31c6b12d97dbc275567a9) ### [Semantic Search Found the Playbook but Missed the “Not”](https://blog.codapus.studio/semantic-search-playbook-retrieval-negation?utm_source=hashnode&utm_medium=feed) A containerised experiment compares phrase matching with semantic search, showing recovered matches, missed negation, and the trade-offs of rejection rules. 7 min read · [blog.codapus.studio](https://blog.codapus.studio/semantic-search-playbook-retrieval-negation?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/semantic-search-playbook-retrieval-negation/6af31c6b12d97dbc275567a9) [Hossein Hezami](https://hashnode.com/@hosseinhezami) · [5d ago](https://hashnode.com/posts/the-architecture-of-modern-ai-models-agents-vector-databases-and-mcp/6aeda32a77cc2fcbe2af410b) ### [The Architecture of Modern AI: Models, Agents, Vector Databases, and MCP](https://hosseinhezami.hashnode.dev/the-architecture-of-modern-ai-models-agents-vector-databases-and-mcp?utm_source=hashnode&utm_medium=feed) A practical field guide to the concepts, architectures, and free-versus-professional tools behind production AI systems. 24 min read · [hosseinhezami.hashnode.dev](https://hosseinhezami.hashnode.dev/the-architecture-of-modern-ai-models-agents-vector-databases-and-mcp?utm_source=hashnode&utm_medium=feed) [Ram](https://hashnode.com/@searchshift) · [Nov 3](https://hashnode.com/posts/the-search-google-would-not-rewrite-14-same-meaning-query-pairs-and-what-they-show-about-semantic-search/6ae9d236f91769a48eab74d8) ### [The Search Google Would Not Rewrite: 14 Same-Meaning Query Pairs and What They Show About Semantic Search](https://searchshift.hashnode.dev/the-search-google-would-not-rewrite-14-same-meaning-query-pairs-and-what-they-show-about-semantic-search?utm_source=hashnode&utm_medium=feed) Google matched the meaning of 14 query pairs, yet the two top 10 lists shared 7 of 207 URLs. One pair never got rewritten. 5 min read · [searchshift.hashnode.dev](https://searchshift.hashnode.dev/the-search-google-would-not-rewrite-14-same-meaning-query-pairs-and-what-they-show-about-semantic-search?utm_source=hashnode&utm_medium=feed) [Rounak Show](https://hashnode.com/@ShowRounak) · [Nov 2](https://hashnode.com/posts/sentence-embeddings-contrastive-learning-semantic-search/6ae8a94d6231ed1f0af0efab) ### [Understanding LLM Embeddings from Scratch — Part 7: Sentence Embeddings, Contrastive Learning & Semantic Search](https://rounakshow.hashnode.dev/sentence-embeddings-contrastive-learning-semantic-search?utm_source=hashnode&utm_medium=feed) From contextual token representations to a single vector for an entire sentence and why that vector is useful for retrieval. In Part 6, we learned how self-attention changes a token's representation d 16 min read · [rounakshow.hashnode.dev](https://rounakshow.hashnode.dev/sentence-embeddings-contrastive-learning-semantic-search?utm_source=hashnode&utm_medium=feed) [Rounak Show](https://hashnode.com/@ShowRounak) · [Nov 1](https://hashnode.com/posts/static-vs-contextual-embeddings-self-attention-explained/6ae78fa24f6795e3cd6d743d) ### [Understanding LLM Embeddings from Scratch — Part 6: Static vs Contextual Embeddings (Self-Attention Explained)](https://rounakshow.hashnode.dev/static-vs-contextual-embeddings-self-attention-explained?utm_source=hashnode&utm_medium=feed) How does the same token represent different meanings in different sentences? Let's work through self-attention from first principles, with actual numbers and PyTorch. In Part 5: Word2Vec, we saw how w 12 min read · [rounakshow.hashnode.dev](https://rounakshow.hashnode.dev/static-vs-contextual-embeddings-self-attention-explained?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/static-vs-contextual-embeddings-self-attention-explained/6ae78fa24f6795e3cd6d743d) [ZyVOP](https://hashnode.com/@zyvop) · [Oct 31](https://hashnode.com/posts/choosing-a-vector-database-pgvector-vs-dedicated-stores-gr2u4/6ae560a0e231ee21ec3f6e3c) ### [Choosing a Vector Database: pgvector vs Dedicated Stores](https://blog.zyvop.com/choosing-a-vector-database-pgvector-vs-dedicated-stores-gr2u4?utm_source=hashnode&utm_medium=feed) When Postgres with pgvector is enough, when a dedicated vector database earns its keep, and how to decide using scale, filtering, and operations. 11 min read · [blog.zyvop.com](https://blog.zyvop.com/choosing-a-vector-database-pgvector-vs-dedicated-stores-gr2u4?utm_source=hashnode&utm_medium=feed) [3](https://hashnode.com/posts/choosing-a-vector-database-pgvector-vs-dedicated-stores-gr2u4/6ae560a0e231ee21ec3f6e3c) [Hassan Aziz](https://hashnode.com/@hassandevelopment) · [Oct 31](https://hashnode.com/posts/how-semantic-search-works-with-a-python-example/6ae5c34c2935df66e5d78ac4) ### [How semantic search works, with a Python example](https://hassanrants.hashnode.dev/how-semantic-search-works-with-a-python-example?utm_source=hashnode&utm_medium=feed) Semantic search matches meaning instead of keywords. How embeddings and cosine similarity work, and a movie search in Python with sentence-transformers. 14 min read · [hassanrants.hashnode.dev](https://hassanrants.hashnode.dev/how-semantic-search-works-with-a-python-example?utm_source=hashnode&utm_medium=feed) [Rounak Show](https://hashnode.com/@ShowRounak) · [Oct 30](https://hashnode.com/posts/understanding-llm-embeddings-word2vec/6ae4856d7917ee9d2dc8326b) ### [Understanding LLM Embeddings from Scratch — Part 5: Word2Vec](https://rounakshow.hashnode.dev/understanding-llm-embeddings-word2vec?utm_source=hashnode&utm_medium=feed) In Module 4, we treated embeddings as raw parameters—numbers in a matrix tuned by backpropagation to minimize a loss value. Now, we step back from the raw mechanics to look at the emergence of meaning 8 min read · [rounakshow.hashnode.dev](https://rounakshow.hashnode.dev/understanding-llm-embeddings-word2vec?utm_source=hashnode&utm_medium=feed) [Rounak Show](https://hashnode.com/@ShowRounak) · [Oct 29](https://hashnode.com/posts/understanding-llm-embeddings-from-scratch-part-4-how-does-an-embedding-actually-learn/6ae33d378a27d8d78154e898) ### [Understanding LLM Embeddings from Scratch — Part 4: How Does an Embedding Actually Learn?](https://rounakshow.hashnode.dev/understanding-llm-embeddings-from-scratch-part-4-how-does-an-embedding-actually-learn?utm_source=hashnode&utm_medium=feed) So far, we've learned why embeddings exist, how vectors, dimensions, and similarity work, how nn.Embedding stores vectors and retrieves them using token IDs, how padding and attention masks handle var 10 min read · [rounakshow.hashnode.dev](https://rounakshow.hashnode.dev/understanding-llm-embeddings-from-scratch-part-4-how-does-an-embedding-actually-learn?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/understanding-llm-embeddings-from-scratch-part-4-how-does-an-embedding-actually-learn/6ae33d378a27d8d78154e898) [Rounak Show](https://hashnode.com/@ShowRounak) · [Oct 28](https://hashnode.com/posts/understanding-llm-embeddings-from-scratch-part-3-the-embedding-matrix/6ae1e751ef9da79090f52515) ### [Understanding LLM Embeddings from Scratch — Part 3: The Embedding Matrix](https://rounakshow.hashnode.dev/understanding-llm-embeddings-from-scratch-part-3-the-embedding-matrix?utm_source=hashnode&utm_medium=feed) In Module 1, we learned why embeddings exist. In Module 2, we understood what vectors are, including their dimensions, magnitude, dot products, and cosine similarity. Now, let's connect everything to 10 min read · [rounakshow.hashnode.dev](https://rounakshow.hashnode.dev/understanding-llm-embeddings-from-scratch-part-3-the-embedding-matrix?utm_source=hashnode&utm_medium=feed) [1](https://hashnode.com/posts/understanding-llm-embeddings-from-scratch-part-3-the-embedding-matrix/6ae1e751ef9da79090f52515)