Alternatives
Products that do what SemHash – Fast Semantic Text Deduplication for Cleaner Datasets does
We’ve just open-sourced SemHash, a lightweight package for semantic text deduplication. It lets you effortlessly clean up your datasets and avoid pitfalls caused by duplicate samples in semantic search, RAG, and machine learning. Main Features: - Fast and hardware friendly: Deduplicate datasets with millions of records in minutes, on a CPU. - Flexible: Works on single or multiple datasets (e.g., train/test deduplication), and multi-column data (e.g., Question-Answering datasets). - Lightweight: Minimal dependencies (largest is NumPy). - Explainable: Easily inspect duplicates and what…
- 1SF
We’ve just open-sourced SemHash, a lightweight package for semantic text deduplication. It lets you effortlessly clean up your datasets and avoid pitfalls caused by duplicate samples in semantic search, RAG, and machine learning. Main Features: - Fast and hardware friendly: Deduplicate datasets with millions of records in minutes, on a CPU. - Flexible: Works on single or multiple datasets (e.g., train/test deduplication), and multi-column data (e.g., Question-Answering datasets). - Lightweight: Minimal dependencies (largest is NumPy). - Explainable: Easily inspect duplicates and what…
2025 · github.com
- 2SS
We’ve just released SemHash v0.3.0, a major rework of our open-source text pre-processing library. We’ve added two new functionalities: outlier filtering & representative sampling. The core API has been reworked to make sure all of these features can be used together in an intuitive way. Our new features use the existing approximate nearest neighbors index that we already used for semantic deduplication, so they can be ran very quickly after building the index on your dataset. The core package can now be used for: - Semantic Deduplication: Remove semantic duplicates from your dataset. This…
2025 · github.com
- 3WT
After working with LLMs for long enough, I found myself wanting a lightweight utility for doing various small tasks to prepare inputs, locate information and create evaluators. This library is two things: a very simple model and utilities that inference it (eg. fuzzy deduplication). The target platform is CPU, and it’s intended to be light, fast and pip installable — a library that lowers the barrier to working with strings semantically. You don’t need to install pytorch to use it, or any deep learning runtimes. How can this be accomplished? The model is simply token embeddings that are…
2024 · github.com
- 4SG
Much improved new version. Search for words similar to the query. For example, "death" will find "death", "dying", "dead", "killing"... Incredibly useful for exploring large text datasets where exact matches are too restrictive.
2024 · github.com
- 5SC
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality. Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused…
May 2026 · github.com
- 6CA
TLDR: I’ve made a transformer model and a wrapper library that segments text into meaningful semantic chunks. The current text splitting approaches rely on heuristics (although one can use neural embedder to group semantically related sentences). I propose a fully neural approach to semantic chunking. I took the base distilbert model and trained it on a bookcorpus to split concatenated text paragraphs into original paragraphs. Basically it’s a token classification task. Model fine-tuning took day and a half on a 2x1080ti. The library could be used as a text splitter module in a RAG system or…
2025 · github.com
- 7IM
As a grad student (and an ADHDer), I had trouble doing literature review systematically. To combat this, I made a website that finds similar papers using the meaning of the thing I am looking for. I used MixedBread's [^1] embedding model to generate vectors from the abstracts. I store and search similar vectors using Milvus [^2] and finally use Gradio [^3] to serve the frontend. I update the vector database weekly by pulling the metadata dataset from Kaggle [^4]. To speed up the search process on my free oracle instance, I binarise the embeddings and use Hamming distance as a metric. I would…
2024 · papermatch.mitanshu.tech
- 8CA
I built Chonkie because I was tired of rewriting chunking code for RAG applications. Existing libraries were either too bloated (80MB+) or too basic, with no middle ground. Core features: - 21MB default install vs 80-171MB alternatives - 33x faster token chunking than popular alternatives - Supports multiple chunking strategies: token, word, sentence, and semantic - Works with all major tokenizers (transformers, tokenizers, tiktoken) - Zero external dependencies for basic functionality Technical optimizations: - Uses tiktoken with multi-threading for faster tokenization - Implements…
2024 · github.com
- 9SG
Sep 2025 · github.com
- 10FV
I recently found myself computing the similarity between lots of very high dimensional vectors (i.e., sentence embedding vectors from LLMs), and I wanted to try some more powerful measures of similarity/dependency than just Cosine similarity, which seems to be the default for everything nowadays because of its computational efficiency. There are many other more involved measures that can detect more subtle relationships, but the problem is that some of them are quite slow to compute, especially if you're trying to do it in Python. For my favorite measure of statistical dependency,…
2023 · github.com
- 11CT
Jul 2026 · github.com
- 12
- 13BS
Introducing Biblos, a simple tool for semantic search and summarization of Bible passages. Leveraging Chroma for vector search with BAAI BGE embeddings, semantically find related verses across the Bible. The tool employs Anthropic's Claude LLM model for generating high-quality summaries of retrieved passages, contextualizing your search topic. Built on a Retrieval Augmented Generation (RAG) architecture, the app implements a simple Streamlit Web UI using Python. Deployed using render.com, the app is available at https://biblos.app Note: Search by just topic/keywords, e.g.…
2023 · github.com
- 14DA
I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features: -- An implementation of a sub-question query engine from scratch to answer complex user questions. -- Illustrative explanations that unveil the inner workings of the system. -- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation. -- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective. Key Takeaway:…
2023 · github.com
- 15AL
Hi HN! I am Maria, solo founder of DataQA (https://dataqa.ai/), a tool to search and label documents for various NLP tasks (e.g. entity extraction, entity linking, etc). I have worked as a data scientist and ML engineer for the better part of a decade, and over that time have specialised mainly in applications involving natural language processing (NLP). One of the key questions I have always had at the back of my mind is whether my time was well spent. Whenever I spent more time on feature engineering or trying different models, I always wondered whether I would get better…
2021
- 16KG
Hi HN! My latest side project is knowledge graph that maps the French culinary network using data extracted from restaurant reviews from LeFooding.com. The project uses LLMs to extract structured information from unstructured text. Some technical aspects you may be interested in: - Used structured generation to reliably parse unstructured text into a consistent schema - Tested multiple models (Mistral-7B-v0.3, Llama3.2-3B, gpt4o-mini) for information extraction - Created an interactive visualization using gephi-lite and Retina (WebGL) - Built (with Claude) a simple Flask web app to clean and…
2025 · theophilecantelob.re
- 17SC
I've been playing with embeddings and wanted to try out what results the embedding layer will produce based on just word-by-word input and addition / subtraction, beyond what many videos / papers mention (like the obvious king-man+woman=queen). So I built something that doesn't just give the first answer, but ranks the matches based on distance / cosine symmetry. I polished it a bit so that others can try it out, too. For now, I only have nouns (and some proper nouns) in the dataset, and pick the most common interpretation among the homographs. Also, it's case sensitive.
2025 · calc.datova.ai
- 18SS
Sep 2025 · github.com
- 19ML
We’ve recently open-sourced Model2vec, a method to distill sentence transformers into static embeddings that outperform all previous approaches by a large margin on MTEB. Our new models set a new state-of-the-art for static embeddings. Main features: - Our best model (potion-base-8M) has only 8M parameters, which is ~30mb on disk - Inference is ~500x faster than the distilled base model (bge-base), on a CPU - New models can be distilled in 30 seconds on a CPU without requiring a dataset - just a vocabulary - Numpy-only inference: The packaged can be install the package with minimal…
2024 · github.com
- 20AA
Hi HN! I'm excited to share Autolabel, an open-source Python library to label and enrich text datasets with any Large Language Model (LLM) of your choice. We built Autolabel because access to clean, labeled data is a huge bottleneck for most ML/data science teams. The most capable LLMs are able to label data with high accuracy, and at a fraction of the cost and time compared to manual labeling. With Autolabel, you can leverage LLMs to label any text dataset with <5 lines of code. We’re eager for your feedback!
2023 · github.com
- 21CA
TLDR: I’m expanding the family of text-splitting Chonky models with new multilingual model. You can learn more about this neural approach in a previous post: https://news.ycombinator.com/item?id=43652968 Since the release of the first distilbert-based model I’ve released two more models based on a ModernBERT. All these models were pre-trained and fine-tuned primary on English texts. But recently mmBERT(https://huggingface.co/blog/mmbert) has been released. This model pre-trained on massive dataset that contains 1833 languages. So I had an idea of…
Oct 2025 · huggingface.co
- 22DB
I've been doing some data cleaning for my fine tuning projects using LLMs, and decided to just build a package for it as a side project. Check it out here: https://github.com/databonsai/databonsai Some features: - categorization (labelling), transformation and decomposition (text into structured format) - validates llm outputs - batch mode batches up the inputs/outputs so you don't send the prompt (schema, fewshot examples) for every row of data, saving a significant amount of tokens There are some similarities to the Instructor repo, but this is simpler and made for…
2024 · github.com
- 23CL
I have a proposal that addresses long-term memory problems for LLMs when new data arrives continuously (cheaply!). The program involves no code, but two Markdown files. For retrieval, there is a semantic filesystem that makes it easy for LLMs to search using shell commands. It is currently a scrappy v1, but it works better than anything I have tried. Curious for any feedback!
Apr 2026 · github.com
- 24UD
I've been working a fair bit with DSPy lately, and I did some work in combining the benefits of vector search and LLMs (via a DSPy pipeline) to disambiguate records with a high degree of accuracy to help enrich a dataset. The blog post shows how this approach scales well, is very cost-effective and super concise - all it takes is < 100 lines of DSPy code and it all runs async. The code to reproduce is in this repo if anyone's interested (all tools are 100% free and open source, and the methodology will work with open weight LLMs too).…
2025 · blog.kuzudb.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →