Trending repositories for topic question-answering

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...

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.

A list of software that allows searching the web with the assistance of AI.

AdalFlow: The library to build & auto-optimize LLM applications.

knowledge graph知识图谱,从零开始构建知识图谱

👑 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...

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

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

Efficient Retrieval Augmentation and Generation Framework

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

An open source library for deep learning end-to-end dialog systems and chatbots.

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。

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

The codebase for the book "AI-Powered Search" (Manning Publications, 2024)

Medical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

Chat with multiple PDFs locally

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Tevatron - A flexible toolkit for neural retrieval research and development.

A list of software that allows searching the web with the assistance of AI.

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。

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

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.

AdalFlow: The library to build & auto-optimize LLM applications.

knowledge graph知识图谱,从零开始构建知识图谱

The codebase for the book "AI-Powered Search" (Manning Publications, 2024)

Efficient Retrieval Augmentation and Generation Framework

Medical Question Answering Dataset of 47,457 QA pairs created from 12 NIH websites

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

Chat with multiple PDFs locally

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...

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Tevatron - A flexible toolkit for neural retrieval research and development.

[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖

An LLM-powered advanced RAG pipeline built from scratch

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...

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.

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.

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...

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

knowledge graph知识图谱,从零开始构建知识图谱

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.

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

Chat with multiple PDFs locally

Efficient Retrieval Augmentation and Generation Framework

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

State of the Art Natural Language Processing

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...

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。

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

A list of software that allows searching the web with the assistance of AI.

A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.

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。

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) 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

Synthetic question-answering dataset to formally analyze the chain-of-thought output of large language models on a reasoning task.

Chat with multiple PDFs locally

AdalFlow: The library to build & auto-optimize LLM applications.

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

Query language for blending SQL logic and LLM reasoning across structured + unstructured data. [Findings of ACL 2024]

Mixing Language Models with Self-Verification and Meta-Verification

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

knowledge graph知识图谱,从零开始构建知识图谱

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

Code and Checkpoints for "Generate rather than Retrieve: Large Language Models are Strong Context Generators" in ICLR 2023.

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

Explore LangChain and build powerful chatbots that interact with your own data. Gain insights into document loading, splitting, retrieval, question answering, and more.

Framework for enhancing LLMs for RAG tasks using fine-tuning.

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...

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.

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.

👑 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...

knowledge graph知识图谱,从零开始构建知识图谱

Efficient Retrieval Augmentation and Generation Framework

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

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

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。

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

Chat with multiple PDFs locally

An open source library for deep learning end-to-end dialog systems and chatbots.

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

A collection of research on knowledge graphs

State of the Art Natural Language Processing

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...

A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.

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。

A list of software that allows searching the web with the assistance of AI.

Q/A using gemini-pro and next.js

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

AdalFlow: The library to build & auto-optimize LLM applications.

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) 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

Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"

Langchain Models for RAGs and Agents

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

(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.

Chat with multiple PDFs locally

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.

Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset

Leverages extensive power of multiple Machine Learning algorithms & LLM to provide in-depth answers to medical queries and predicts condition/diseases based on patient symptoms

knowledge graph知识图谱,从零开始构建知识图谱

Query language for blending SQL logic and LLM reasoning across structured + unstructured data. [Findings of ACL 2024]

A Multi-subject High School Examinations Dataset for Cross-lingual and Multilingual Question Answering

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) with a RESTful API.

AdalFlow: The library to build & auto-optimize LLM applications.

A list of software that allows searching the web with the assistance of AI.

Framework for enhancing LLMs for RAG tasks using fine-tuning.

Chat with multiple PDFs locally

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

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.

Kubernetes operator for Qdrant

Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"

OLAPH: Improving Factuality in Biomedical Long-form Question Answering

(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.

A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.

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...

The most advanced AI retrieval system. Containerized, Retrieval-Augmented Generation (RAG) 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...

Efficient Retrieval Augmentation and Generation Framework

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

knowledge graph知识图谱,从零开始构建知识图谱

A list of software that allows searching the web with the assistance of AI.

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.

Chat with multiple PDFs locally

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

State of the Art Natural Language Processing

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

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...

【C++ 面试 + C++ 学习指南】 一份涵盖大部分 C++ 程序员所需要掌握的核心知识。

ChatGPT 中文语料库 对话语料 小说语料 客服语料 用于训练大模型

Official Code for "Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction (CVPR 2024)"

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 repository is an AI Bootcamp material that consist of a workflow for LLM

A list of software that allows searching the web with the assistance of AI.

🌲 Code for our EMNLP 2023 paper - 🎄 "Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models"

Ứng dụng hỗ trợ tra cứu, hỏi đáp tri thức pháp luật dựa trên Bộ pháp điển và CSDL văn bản QPPL Việt Nam.

Retrieval augmented generation for middle-school math question answering and hint generation.

Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"

LangChain, Llama2-Chat, and zero- and few-shot prompting are used to generate synthetic datasets for IR and RAG system evaluation

[NeurIPS 2022] Official Code for REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering

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...

Langchain Models for RAGs and Agents

Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23

Q/A using gemini-pro and next.js

Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.

Efficient Retrieval Augmentation and Generation Framework

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

🤖 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/)