2 repository-uri
Awesome GitHub RepositoriesLLM-Based Classifiers
Assigns labels to text using a configured large language model, without requiring a full extraction result.
Distinct from Text Classifiers: Distinct from Text Classifiers: uses LLMs for classification rather than traditional ML models or rule-based approaches.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · LLM-Based Classifiers. Refine with filters or upvote what's useful.
Awesome LLM-Based Classifiers GitHub Repositories
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- kreuzberg-dev/kreuzberg
kreuzberg-dev/kreuzberg
8,527Vezi pe GitHubKreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo
Assigns labels to a single piece of plain text using a configured LLM, without requiring an extraction result.
Rustdocument-intelligenceelixirffi - datajuicer/data-juicer
datajuicer/data-juicer
6,574Vezi pe GitHubData-Juicer is an open-source framework for cleaning, filtering, deduplicating, and transforming multimodal datasets to prepare them for training large language and vision models. It functions as a distributed data pipeline engine that runs processing jobs across Ray clusters, handling billions of samples with automatic operator fusion and adaptive parallelism. The framework provides a library of operators that leverage large language models for semantic extraction, filtering, and data synthesis within processing pipelines. The project distinguishes itself through a YAML-based data recipe sys
Runs a quality classifier on web-crawled text to filter low-quality samples.
Pythondatadata-analysisdata-pipeline
