Trending repositories for topic question-answering
AdalFlow: The library to build & auto-optimize LLM applications.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
A list of software that allows searching the web with the assistance of AI.
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Sear...
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。
[NeurIPS'22] EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
Powerful web application that combines Streamlit, LangChain, and Pinecone to simplify document analysis. Powered by OpenAI's GPT-3, RAG enables dynamic, interactive document conversations, making it i...
[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
An AI-powered arXiv paper summarization website with a virtual assistant for answering questions.
A list of software that allows searching the web with the assistance of AI.
AdalFlow: The library to build & auto-optimize LLM applications.
[NeurIPS'22] EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
Powerful web application that combines Streamlit, LangChain, and Pinecone to simplify document analysis. Powered by OpenAI's GPT-3, RAG enables dynamic, interactive document conversations, making it i...
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
An AI-powered arXiv paper summarization website with a virtual assistant for answering questions.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links
A list of software that allows searching the web with the assistance of AI.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
AdalFlow: The library to build & auto-optimize LLM applications.
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Sear...
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
An AI-powered arXiv paper summarization website with a virtual assistant for answering questions.
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financia...
An open source library for deep learning end-to-end dialog systems and chatbots.
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
Retrieval augmented generation for middle-school math question answering and hint generation.
A list of software that allows searching the web with the assistance of AI.
Retrieval augmented generation for middle-school math question answering and hint generation.
AdalFlow: The library to build & auto-optimize LLM applications.
Labs for the "Build an agentic LLM assistant on AWS" workshop. A step by step agentic llm assistant development workshop using serverless three-tier architecture.
An AI-powered arXiv paper summarization website with a virtual assistant for answering questions.
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
[NeurIPS'22] EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records
A large-scale (194k), Multiple-Choice Question Answering (MCQA) dataset designed to address realworld medical entrance exam questions.
🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
Powerful web application that combines Streamlit, LangChain, and Pinecone to simplify document analysis. Powered by OpenAI's GPT-3, RAG enables dynamic, interactive document conversations, making it i...
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financia...
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
[SIGIR 2022] Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
A list of software that allows searching the web with the assistance of AI.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
AdalFlow: The library to build & auto-optimize LLM applications.
A list of software that allows searching the web with the assistance of AI.
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Sear...
Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype, scalable, under developpement
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
农业知识图谱(AgriKG)：农业领域的信息检索，命名实体识别，关系抽取，智能问答，辅助决策
An open source library for deep learning end-to-end dialog systems and chatbots.
北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。
Tevatron - A flexible toolkit for neural retrieval research and development.
A list of software that allows searching the web with the assistance of AI.
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype, scalable, under developpement
AdalFlow: The library to build & auto-optimize LLM applications.
RAG-QA-Generator 是一个用于检索增强生成（RAG）系统的自动化知识库构建与管理工具。该工具通过读取文档数据，利用大规模语言模型生成高质量的问答对（QA对），并将这些数据插入数据库中，实现RAG系统知识库的自动化构建和管理。
Labs for the "Build an agentic LLM assistant on AWS" workshop. A step by step agentic llm assistant development workshop using serverless three-tier architecture.
This project focuses on fine-tuning a BERT model for question answering using a limited dataset for illustration purposes.
Retrieval augmented generation for middle-school math question answering and hint generation.
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
This repository is an AI Bootcamp material that consist of a workflow for LLM
LIQUID: A Framework for List Question Anwering Dataset Generation (AAAI 2023)
A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android
Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities
Ứng dụng hỗ trợ tra cứu, hỏi đáp tri thức pháp luật dựa trên Bộ pháp điển và CSDL văn bản QPPL Việt Nam.
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23
Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
A list of software that allows searching the web with the assistance of AI.
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models
Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities
Query language for blending SQL logic and LLM reasoning across structured + unstructured data. [Findings of ACL 2024]
A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android
Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"
Labs for the "Build an agentic LLM assistant on AWS" workshop. A step by step agentic llm assistant development workshop using serverless three-tier architecture.
RAG-QA-Generator 是一个用于检索增强生成（RAG）系统的自动化知识库构建与管理工具。该工具通过读取文档数据，利用大规模语言模型生成高质量的问答对（QA对），并将这些数据插入数据库中，实现RAG系统知识库的自动化构建和管理。
(Let's start with a) Scalable question-answering system utilizing FastAPI, LangChain (LCEL), and PGVector, featuring an ingestion pipeline. Deployed on GCP Cloud Run via Terraform.
This project focuses on fine-tuning a BERT model for question answering using a limited dataset for illustration purposes.
Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
AdalFlow: The library to build & auto-optimize LLM applications.
👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Sear...
Framework for enhancing LLMs for RAG tasks using fine-tuning.
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
A list of software that allows searching the web with the assistance of AI.
农业知识图谱(AgriKG)：农业领域的信息检索，命名实体识别，关系抽取，智能问答，辅助决策
An open source library for deep learning end-to-end dialog systems and chatbots.
Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financia...
This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses WebLLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space
Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"
This repository is an AI Bootcamp material that consist of a workflow for LLM
🌲 Code for our EMNLP 2023 paper - 🎄 "Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models"
A list of software that allows searching the web with the assistance of AI.
Powerful web application that combines Streamlit, LangChain, and Pinecone to simplify document analysis. Powered by OpenAI's GPT-3, RAG enables dynamic, interactive document conversations, making it i...
Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"
[NeurIPS 2022] Official Code for REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.
Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23
[Paper][ACL 2024 Findings] Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"
[Preprint] Learning to Filter Context for Retrieval-Augmented Generaton
Efficient Retrieval Augmentation and Generation Framework
🤖 Long-form question answering in the legal domain. (AAAI 2024)
WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)
🦙 Free and Open Source Large Language Model (LLM) chatbot web UI and API. Self-hosted, offline capable and easy to setup. Powered by LangChain.