← Latest products

EmbedFlow –> Upgrade embedding models without re-embedding your corpus

Zero downtime embedding upgrades. I was playing around with embedding models and I realized the moving between embedding models on a large corpus can cause a huge backfill, as all of the previous documents would have to be re embedded.

Open source

55 stars · GitHubexternal site

Visit github.comexternal site

Reactions (2)

Similar products

by description similarity

  1. Drift

    github.com

    an embedding-model upgrade should be a rotation, not a reindex

    Hacker News6 pts

  2. Superlinked

    github.com

    Vector Embeddings for Structured and Unstructured Data

    Hacker News7 pts

  3. Model2vec

    github.com

    Lightning-fast Static Embeddings for RAG/Semantic Search

    Hacker News28 pts

  4. Open-Source AI Embedding Pre-Processing Editor

    embedditor.ai

    ⚡ GUI for editing LLM vector embeddings. No more blind chunking. Upload content in any file extension, join and split chunks, edit metadata and embedding tokens + remove stop-words and punctuation with one click, add images, and download in .veml to share it with your team.

    Hacker News16 pts

  5. Connecting MLflow Hosted Models and Label Studio for Auto Labelling

    news.ycombinator.com

    I’m a PhD student working on DL interpretability & Optimization Theory.

    Hacker News5 pts