The platform for developers building applications powered by LLMs

8 Lessons, Get Started Building with Generative AI and Gemini API

Code for ICLR 2024 Paper: CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning

Local image search engine powered by AI

Dynamic Few-Shot Prompting is a Python package that dynamically selects N samples that are contextually close to the user's task or query from a knowledge base (similar to RAG) to include in the prompt.

This repo implements many methods to retrieve molecules that are similar to a target molecule from a large molecule corpus.

Docker Compose stack for scalable TEI embeddings (multi-GPU) fronted by a FastAPI proxy with a Qdrant cache. 🐳⛓️💾

This Streamlit application demonstrates the integration of ChatGroq (Llama3 model), OpenAIEmbeddings, and FAISS for document embedding and retrieval.

A lightweight implementation of Retrieval-Augmented Generation (RAG) for enhancing language models with external knowledge.

🤵🏻‍♂️🍷 An AI-powered wine recommendation system that helps customers find the perfect bottle based on taste preferences, grape varietals, food and cheese pairings, or mood. 🍇 🍝 🧀

Using hugging face for Q&A retrieval

LLM-powered semantic search Q&A system using RAG (Retrieval-Augmented Generation). Built with LangChain, FAISS vector search, and HuggingFace Transformers. Deployed on HuggingFace Spaces.

Legal-RAG — A law-grounded, graph-aware retrieval-augmented generation system, featuring statute-centric hybrid retrieval, task-aware routing, and LLM provider-agnostic generation.

This repository implements a Retrieval-Augmented Generation (RAG) system for the Supreme Court of Pakistan, utilizing different LLMs, embedding models, and retrieval and generation enhancement strategies. It processes SCP judgments, applies chunking, and generates legal summaries and answers based on relevant case data.

This repository hosts the canonical version of the THINKD-IDX13026 model, originally published as a Gist. Original Gist: https://gist.github.com/ottor28-cyber/851d072fe489d95094fbfe1942a04525 For full system instructions, see THINKD-IDX13026.md in this repository.