Embedditor [::] - Improved vector search with open-source AI embeddings editor

Hey Everybody, We are thrilled to open source Embedditor today. Embedditor is the open-source MS Word equivalent for embeddings that helps you get the most out of your vector search, while saving up to 30% on vectorisation and storage. Github : https://github.com/embedditor It's an innovative solution inspired by the experiences of over 30,000 IngestAI users. Our insights revealed a common bottleneck in AI and LLM-related applications, one that goes beyond LLM hallucinations or token limits, which are far easier to resolve. The prevailing issue lies in the GIGO (garbage in, garbage out) principle. With no one-size-fits-all approach to chunking and embedding, certain models excel with individual sentences, while others thrive on chunks of 250 to 500 tokens. Blindly splitting chunks by the quantity of characters or tokens, and embedding content without normalization and with up to 40% of redundant noise (such as punctuations, stop-words, and low-relevance frequent terms) often leads to suboptimal vector search results and low-performing LLM-related applications using semantic or generative search. The issue was consisting in trying to enhance vector search using existing technologies, which proved to be as challenging for our users, as creating an outstanding document using a basic .txt format. We decided to address the root problem, so we developed Embedditor - the Microsoft Word equivalent for embedding pre-processing, enabling with no background in data science or technical skills to improve performance of their vector search capabilities while saving up to 40% on embedding and storage. We've made Embedditor open-source and accessible to all because we genuinely believe that by improving vector search performance and boosting cost-efficiency simultaneously, Embedditor may have significant impact on current NLP and LLM industry. Hope you loved it. ❤️ and we would love to hear your usecases & feedbacks. 🙌

Congratulations guys!!! Great job 👏🏻

Cool!!!! Congratulations!!!!

That's super cool. Just yesterday we were discussing about embeddings editing issues at our company (Lastro)...

Warmest congratulations on your achievement! Wishing you even more success in the future 🎉🥳👏🏻

Really cool and innovative self-hosted web application with a simple and minimalistic interface to search through your documents and communication with Openai based on different models!

Cheers for open-sourcing a visual editor for vector embeddings, enabling an inexpensive, intuitive search that yields striking results and savings!

Firstly congratulations on your launch guys!!!!!i just couldnt resist myself to leave a comment over here! This is such an wonderful project you guys have created!!! This is going to help many of us a lot!

ah . this is so very useful for us

Releasing a new product is a huge accomplishment. Wishing you congrats, kudos and high fives! May the rewards of your hard work be plentiful.

you are the best!

ment. Wishing you well done, praise and high fives! May the compensations of your diligent effort be copious.

Congrats for the amazing launch of this good project , i think this is gonna be brilliant especially this is an open source AI

I am so ready to utilize this and start saving that 30% on embedding and vector storage, during inflation such discounts are such a life saver.

I'm stunned at how fast this community is coming together and how our mentors have offered feedback and support - every day is a proud moment to work here!

This service to help improve vector search seems fantastic to me, the efficiency for improving embedding metadata and tokens, this tool is extremely useful and I would like to try it right now.

It sounds like the web application you described is really cool and innovative, with a simple and minimalistic interface for searching through documents and communicating using different OpenAI models. This application could be useful for individuals and businesses alike who are looking to improve their information management and communication in a more efficient and intelligent way.

Embedditor is a game-changer! It effortlessly transforms the way we embed content, making it a breeze to enhance our websites and apps. Love it! #ProductHunt

This open-source AI embeddings editor allows for faster and more accurate searches. The improved search capabilities of Embedditor are a dream come true for researchers and data analysts. The software is easy to use and the interface is intuitive, making it easy to get started.

I'm truly impressed by Embedditor and its capabilities. It offers an intuitive interface that makes working with vector LLM embeddings a breeze. The ability to generate impressive search results is a huge advantage, and the fact that it enhances the performance of vector search is remarkable.