Embedding Explorer is changing how you test embeddings in real time in your browser. It ingests data, generates embeddings with multiple providers like OpenAI, Google Gemini, and Ollama, and runs fast similarity tests—all locally, no backend [1].
The stack runs on Dart + Jaspr, with persistence via libSQL WASM and vectors plus metadata stored in the browser's OPFS. You can upload CSV or point at a SQLite DB, then compare models with k‑NN / cosine queries powered by libSQL in WASM. All results stay local to your device [1].
Over in the SQLite ecosystem, the sqlite-vector extension promises ultra-efficient vector search, but the post notes it's not fully open source and licensing can complicate adoption [2]. Some threads also mention you can point DuckDB at a SQLite file to read it, illustrating OSS trade‑offs in the space [2].
Qdrant positions itself as a high‑performance vector database and vector search engine in Rust. It’s the production‑oriented link from browser experiments to Rust‑backed storage for vector data [3].
Beyond the hobbyist tool, the move to tensor‑based retrieval could unify these layers, potentially tying in-browser experimentation, SQLite extensions, and dedicated vector DBs into a single retrieval stack [4].
From Embedding Explorer to Qdrant, the vector stack is climbing from browser tinkering to robust, scalable storage.
References
Show HN: Embedding Explorer – compare text embedding models in your browser
Tool to compare embedding models locally, stores vectors in WASM libSQL, enables rapid A/B testing of models and retrieval
View sourceUltra efficient vector extension for SQLite
Discussion of sqlite-vector extension, licensing concerns, comparisons to sqlite-vec, DuckDB, and HNSW, with brute-force search performance.
View sourceQdrant: High-Performance Vector Database and Vector Search Engine in Rust
Overview of Qdrant, a high-performance vector database and vector search engine implemented in Rust, designed for efficient similarity search scalability.
View sourceBeyond Vector Search: The Move to Tensor-Based Retrieval
Discusses moving from vector search to tensor-based retrieval in data systems and implications for databases and search performance.
View source