AI4Bharat / setuLinks
Setu is a comprehensive pipeline designed to clean, filter, and deduplicate diverse data sources including Web, PDF, and Speech data. Built on Apache Spark, Setu encompasses four key stages: document preparation, document cleaning and analysis, flagging and filtering, and deduplication.
☆15Updated last year
Alternatives and similar repositories for setu
Users that are interested in setu are comparing it to the libraries listed below
Sorting:
- Data extraction with LLM on CPU☆68Updated last year
- Solving data for LLMs - Create quality synthetic datasets!☆150Updated 9 months ago
- Writing Blog Posts with Generative Feedback Loops!☆50Updated last year
- Repository for fine-tuning gemma models using unsloth for indic languages☆96Updated last year
- Create a music review RAG application with Neo4j☆21Updated last year
- A lightweight evaluation suite tailored specifically for assessing Indic LLMs across a diverse range of tasks☆38Updated last year
- Recipes and resources for building, deploying, and fine-tuning generative AI with Fireworks.☆127Updated last week
- ☆30Updated last year
- Lightweight Non-Parametric Embedding Fine-Tuning☆36Updated last month
- Median is an open-source flashcard application that leverages the power of spaced repetition and artificial intelligence to transform the…☆23Updated last year
- ☆55Updated 2 months ago
- Your local personalised AI agent☆42Updated 11 months ago
- This repo is the central repo for all the RAG Evaluation reference material and partner workshop☆76Updated 6 months ago
- Mistral + Haystack: build RAG pipelines that rock 🤘☆106Updated last year
- ☆50Updated 9 months ago
- Simple Graph Memory for AI applications☆89Updated 5 months ago
- Supervised instruction finetuning for LLM with HF trainer and Deepspeed☆36Updated 2 years ago
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆67Updated last year
- Verbosity control for AI agents☆64Updated last year
- Text to Python Objects via a LLM Function Call☆58Updated last year
- ☆210Updated 4 months ago
- A simple, consistent and extendable toolkit for IndicTrans2. (Pypi: https://pypi.org/project/indictranstoolkit)☆37Updated 3 months ago
- ☆20Updated last year
- Code for evaluating with Flow-Judge-v0.1 - an open-source, lightweight (3.8B) language model optimized for LLM system evaluations. Crafte…☆78Updated last year
- Build Agentic workflows with function calling using open LLMs☆28Updated this week
- Experimental Code for StructuredRAG: JSON Response Formatting with Large Language Models☆111Updated 7 months ago
- ☆124Updated 8 months ago
- Medical Mixture of Experts LLM using Mergekit.☆20Updated last year
- LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. I…☆116Updated 3 months ago
- Simple examples using Argilla tools to build AI☆56Updated 11 months ago