PassoOrg / dedupe_itLinks
Simple fuzzy deduplication
☆26Updated 9 months ago
Alternatives and similar repositories for dedupe_it
Users that are interested in dedupe_it are comparing it to the libraries listed below
Sorting:
- A TypeScript library to create platform-agnostic applications☆68Updated this week
- Fast similarity search using DuckDB☆138Updated 9 months ago
- Chat strategies for LLMs☆98Updated 11 months ago
- Client Side Vector Database☆269Updated last year
- GUI for selecting text files for concatenation and submission to LLMs☆177Updated last month
- What if an HNSW index was just a file, and you could serve it from a CDN, and search it directly in the browser?☆106Updated 4 months ago
- Extremely memory-efficient vector database☆71Updated 10 months ago
- Visual inference exploration & experimentation playground☆95Updated 8 months ago
- OmiAI is an opinionated AI SDK for Typescript that auto-picks the best model from a suite of curated models depending on the prompt. It i…☆106Updated last month
- Experimental jsxdom☆94Updated 10 months ago
- Library for performant, modular, low-memory file processing at scale, in the Cloud☆74Updated 2 months ago
- ☆59Updated 4 months ago
- SyncLite : Build Anything Sync Anywhere☆152Updated 9 months ago
- 🦉⚡️Serverless, distributed vector database as an API☆270Updated last year
- AI web parser library + CLI☆49Updated 3 months ago
- RΞASON is a minimalistic Typescript framework for building great LLM apps☆49Updated 7 months ago
- AI Powered Analytics☆148Updated last month
- A Datasource provider based on DuckDB for analytics/pivot tables☆16Updated 5 months ago
- High-Performance Implementation of OpenAI's TikToken.☆444Updated last month
- Documentation for the Krixik Python client.☆38Updated 9 months ago
- Attempt to create an Open Source Privacy Focused Rewind.ai Alternative for data capture☆221Updated 6 months ago
- A Chrome extension to extract any data from any website☆48Updated 10 months ago
- Multi-model transactional embedded database☆68Updated 8 months ago
- Peer to peer video chat, file sharing etc☆68Updated 4 months ago
- Web-optimized vector database (written in Rust).☆252Updated 5 months ago
- Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.☆279Updated 2 weeks ago
- Better Bookmarks Search w/ Transformers☆195Updated last year
- Postgres extension that speeds up analytics queries by upto 90%☆50Updated last year
- A bring-your-own-key browser extension for summarizing Hacker News articles with LLMs☆54Updated 6 months ago
- Finetune your embeddings in-browser☆34Updated last year