Tfidf Python Packages

cereja

Cereja is a bundle of useful functions we don't want to rewrite and .. just pure fun!

jobfunnel

Scrape job websites into a single spreadsheet with no duplicates.

weighted-class-tfidf

Weighted Class TFIDF technique to deal with imbalanced datasets

mnemosyne-engine

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

wikirec

Recommendation engine framework based on Wikipedia data

memboot

Zero-infrastructure persistent memory for any LLM

fast-code-embed

Algorithmic code embeddings. No GPU. No API keys. No nonsense.

findlike

Command-line tool that finds lexically similar documents in relation to a reference text file or ad-hoc query

kwx

BERT, LDA, and TFIDF based keyword extraction in Python

mnemosyne-ollama

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

youglance

Package for analyzing Youtube Videos from searching by relevant entities to analyzing sentiments and clustering different parts of the video according to your liking

llm-distiller

Model distiller automator — recursively drives an LLM with seed prompts and stores compressed outputs in SQLite

mnemosyne-mcp

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

sassyshell

A sassy, AI-powered CLI sidekick that remembers the commands you forget and mocks you into getting better.

preprocess-nlp

A fast framework for pre-processing (Cleaning text, Reduction of vocabulary, Feature extraction and Vectorization). Implemented with parallel processing using custom number of processes.

summarizeit

Package for analyzing Youtube Videos from searching by relevant entities to analyzing sentiments and clustering different parts of the video according to your liking

semshift

Local-first semantic review assistant that flags likely risky meaning changes in edited text.