IBM / data-prep-kit
Open source project for data preparation of LLM application builders
☆300Updated this week
Related projects ⓘ
Alternatives and complementary repositories for data-prep-kit
- Granite Snack Cookbook -- easily consumable recipes (python notebooks) that showcase the capabilities of the Granite models☆64Updated last week
- 🦄 Unitxt: a python library for getting data fired up and set for training and evaluation☆160Updated this week
- ☆214Updated last week
- Prompt Declaration Language (PDL) is a declarative prompt programming language.☆74Updated this week
- awesome synthetic (text) datasets☆242Updated 3 weeks ago
- GenAIOps on Kubernetes: A collection of reference architectures for running GenAI at scale on Kubernetes using OSS tooling☆128Updated 3 weeks ago
- Build Enterprise RAG (Retriver Augmented Generation) Pipelines to tackle various Generative AI use cases with LLM's by simply plugging co…☆110Updated 3 months ago
- Repository to demonstrate Chain of Table reasoning with multiple tables powered by LangGraph☆146Updated 7 months ago
- ARAGOG- Advanced RAG Output Grading. Exploring and comparing various Retrieval-Augmented Generation (RAG) techniques on AI research paper…☆96Updated 7 months ago
- This package, developed as part of our research detailed in the Chroma Technical Report, provides tools for text chunking and evaluation.…☆160Updated last month
- Let's build better datasets, together!☆206Updated this week
- Tutorial for building LLM router☆163Updated 4 months ago
- ☆131Updated 4 months ago
- In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.☆386Updated 9 months ago
- FastAPI wrapper around DSPy☆214Updated 8 months ago
- Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs☆165Updated 2 weeks ago
- RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker☆106Updated 3 weeks ago
- Generate large synthetic data using a local LLM☆212Updated last week
- Code for explaining and evaluating late chunking (chunked pooling)☆248Updated last month
- 🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.☆27Updated this week
- Framework for enhancing LLMs for RAG tasks using fine-tuning.☆505Updated this week
- LLM-driven automated knowledge graph construction from text using DSPy and Neo4j.☆154Updated 7 months ago
- Building a chatbot powered with a RAG pipeline to read,summarize and quote the most relevant papers related to the user query.☆162Updated 6 months ago
- Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on task…☆133Updated last month
- OpenTelemetry Instrumentation for AI Observability☆220Updated this week
- IBM development fork of https://github.com/huggingface/text-generation-inference☆57Updated last month
- ☆182Updated this week
- Automated knowledge graph creation SDK☆113Updated 4 months ago
- Taxonomy tree that will allow you to create models tuned with your data☆200Updated this week
- 🕹️ Performance Comparison of MLOps Engines, Frameworks, and Languages on Mainstream AI Models.☆134Updated 3 months ago