Best AI tools for< Train Documents >

DocsAI is an AI-powered document companion that helps you organize, search, and chat with your documents. It integrates with various sources, including websites, text files, PDFs, Docx, Notion, and Confluence. You can customize the companion's appearance to match your brand and suggest better answers to improve its accuracy. DocsAI also offers a chat widget that can be embedded on any website, allowing you to chat with your documents and get summaries, insights, and leads. It is mobile and tablet-friendly, and you can export chats and analyze data to identify trends and improve customer satisfaction. DocsAI is open source and offers custom prompts and multi-language support.

Bothatch is a platform that allows users to create custom chatbots powered by OpenAI's GPT technology. With Bothatch, users can upload their own data and documents to train their chatbots, which can then be used to engage in meaningful and productive conversations. Bothatch is designed to be easy to use, with no coding or technical skills required. It is also affordable, with pricing plans starting at $0 per month.

UnravelX is an AI-powered platform that transforms documents into 3D interactive virtual scenarios for training purposes. It automates training processes by using generative AI to create immersive learning experiences. The platform caters to various industries such as F&B, Retail, Sales, and Hospitality, offering a cost-effective and efficient solution for upskilling employees. With over 60 years of combined AI and training expertise, UnravelX leads the innovation in scenario-based learning, providing a seamless onboarding experience for organizations.

DocsChat is an AI-powered document conversation tool that revolutionizes the way users interact with various types of documents. It leverages OCR-powered AI technology to streamline document interactions, making it easier to comprehend, exchange knowledge, troubleshoot, and navigate through different document types. With a focus on enhancing user experiences across reading, research, business, legal, and training domains, DocsChat offers a versatile platform for effortless and personalized document engagement.

Whismer is an AI application that allows users to build custom AI chatbots using their own data. The platform enables users to train their own ChatGPT by uploading documents, adding links, and writing notes. With Whismer, users can customize resources to help the AI system better adapt to specific fields or tasks, improving accuracy and efficiency. The AI proactively learns from user resources to solve various problems. Users can create a professional AI knowledge base in minutes, allowing the AI to learn and provide accurate answers. Whismer also enables users to share their customized AI projects with others, making AI accessible to more people.

Artiko.ai is a multi-model AI chat platform that integrates advanced AI models such as ChatGPT, Claude 3, Gemini 1.5, and Mistral AI. It offers a convenient and cost-effective solution for work, business, or study by providing a single chat interface to harness the power of multi-model AI. Users can save time and money while achieving better results through features like text rewriting, data conversation, AI assistants, website chatbot, PDF and document chat, translation, brainstorming, and integration with various tools like Woocommerce, Amazon, Salesforce, and more.

Scribe is a tool that allows users to create step-by-step guides for any process. It uses AI to automatically generate instructions and screenshots, and it can be used to document processes, train employees, and answer questions. Scribe is available as a Chrome extension and a desktop app.

Cody is an intelligent AI assistant designed to boost team productivity by providing instant answers, support, troubleshooting, and idea generation. It can be trained on your business knowledge base to cater to your specific needs, making it a valuable asset for various departments such as marketing, HR, IT support, business consultancy, creative tasks, sales, training, hiring, customer support, and translation. Cody offers features like prompt manager, focus mode, conversation logs, scratchpad, and source checking, ensuring efficient and tailored assistance. With multilingual capabilities and customizable access controls, Cody prioritizes data security and user experience.

Lamini is an enterprise-level LLM platform that offers precise recall with Memory Tuning, enabling teams to achieve over 95% accuracy even with large amounts of specific data. It guarantees JSON output and delivers massive throughput for inference. Lamini is designed to be deployed anywhere, including air-gapped environments, and supports training and inference on Nvidia or AMD GPUs. The platform is known for its factual LLMs and reengineered decoder that ensures 100% schema accuracy in the JSON output.

Kudra is an AI-powered data extraction tool that offers dedicated solutions for finance, human resources, logistics, legal, and more. It effortlessly extracts critical data fields, tables, relationships, and summaries from various documents, transforming unstructured data into actionable insights. Kudra provides customizable AI models, seamless integrations, and secure document processing while supporting over 20 languages. With features like custom workflows, model training, API integration, and workflow builder, Kudra aims to streamline document processing for businesses of all sizes.

Docsumo is an advanced Document AI platform designed for scalability and efficiency. It offers a wide range of capabilities such as pre-processing documents, extracting data, reviewing and analyzing documents. The platform provides features like document classification, touchless processing, ready-to-use AI models, auto-split functionality, and smart table extraction. Docsumo is a leader in intelligent document processing and is trusted by various industries for its accurate data extraction capabilities. The platform enables enterprises to digitize their document processing workflows, reduce manual efforts, and maximize data accuracy through its AI-powered solutions.

Kopyst is an AI-powered documentation tool that revolutionizes the process of creating engaging video and documents. It helps users streamline workflows, create user manuals, SOPs, and training documents with unmatched accuracy and efficiency. Kopyst offers features like instant documentation, versatile application for various document types, AI-powered intelligence, easy sharing and collaboration, and seamless integration with existing tools. The application empowers users to save time, reduce errors, optimize resources, and enhance productivity in documentation tasks.

Quivr is an open-source chat-powered second brain application that transforms private and enterprise knowledge into a personal AI assistant. It continuously learns and improves at every interaction, offering AI-powered workplace search synced with user data. Quivr allows users to connect with their favorite tools, databases, and applications, and configure their 'second brain' to train on their company's unique context for improved search relevance and knowledge discovery.

Petal is a document analysis platform powered by generative AI technology. It allows users to chat with their documents, providing fully sourced and reliable answers by linking to their own knowledge bases. Users can train AI on their documents to support their work, ensuring centralized knowledge management and document synchronization. Petal offers features such as automatic metadata extraction, file deduplication, and collaboration tools to enhance productivity and streamline workflows for researchers, faculty, and industry experts.

ResolveAI is a platform that allows users to create and train AI agents for customer service. These agents can be used to automate tasks such as answering FAQs, scheduling meetings, and collecting leads. ResolveAI's agents are trained using a variety of sources, including documents, website pages, and live data sources. Once trained, agents can be customized to fit the user's brand and integrated with a variety of platforms, including websites, social media, and messaging apps.

Instant Answers is an AI-powered chatbot builder that enables users to create customized chatbots for their websites in minutes. The platform allows users to train their chatbots to provide instant answers to a wide range of questions by uploading documents or inputting website URLs. With features like easy customization, effortless integration, conversation analytics, and dynamic learning, Instant Answers offers a user-friendly interface for enhancing customer service and engagement.

Visus is a tool that allows you to create your own ChatGPT AI. With Visus, you can train your AI on your own data, ask it questions, and get instant answers. Visus is designed to understand your language and provide quick and accurate responses to any question you may have about your documents. It can help you uncover valuable insights from your data quickly and effortlessly.

Laika is an AI-powered writing assistant that helps you write better, faster, and more efficiently. With Laika, you can generate text, translate languages, summarize documents, and more. Laika is designed to be easy to use, so you can get started right away. Just type in your text and Laika will do the rest.

Compliance Quarter is a leading provider of compliance solutions for the energy industry. We offer a range of services to help businesses manage their compliance obligations, including expert advice, document review, and technology solutions. Our team of experienced professionals has deep expertise in the energy industry and is committed to providing our clients with the highest level of service. We are proud to be the trusted partner of some of the world's largest energy companies.

Delibr is a document-writing solution with generative AI baked in. Through interviewing and coaching over 500 product leaders, we've learned what's important and used it to train our AI. Delibr offers a range of AI-enhanced product templates, including PRDs, user personas, and strategy documents. Each template is designed to help you create high-quality documents that stand out. Delibr also includes an AI Copilot assistant that can review your documents, suggest impactful changes, and offer insights on comments. With Delibr, you can save time writing requirements, organize your ideas, and track your progress. Delibr is trusted by product teams around the world, including Storytel, Nectarine Health, RunaHR, and DecisionLink.

Docs AI is a platform that allows users to train their documents, chat with their documents, and create chatbots to solve queries. It is built using NextJS, Tailwind, tRPC, ShadcnUI, Prisma, Postgres, NextAuth, Pinecone, and Cloudflare R2. The platform requires Node.js (Version: >=18.x), PostgreSQL, and Redis for setup. Users can utilize Docker for development by using the provided `docker-compose.yml` file in the `/app` directory.

Train-llm-from-scratch is a repository that guides users through training a Large Language Model (LLM) from scratch. The model size can be adjusted based on available computing power. The repository utilizes deepspeed for distributed training and includes detailed explanations of the code and key steps at each stage to facilitate learning. Users can train their own tokenizer or use pre-trained tokenizers like ChatGLM2-6B. The repository provides information on preparing pre-training data, processing training data, and recommended SFT data for fine-tuning. It also references other projects and books related to LLM training.

Ray is a unified framework for scaling AI and Python applications. It consists of a core distributed runtime and a set of AI libraries for simplifying ML compute, including Data, Train, Tune, RLlib, and Serve. Ray runs on any machine, cluster, cloud provider, and Kubernetes, and features a growing ecosystem of community integrations. With Ray, you can seamlessly scale the same code from a laptop to a cluster, making it easy to meet the compute-intensive demands of modern ML workloads.

LLoCO is a technique that learns documents offline through context compression and in-domain parameter-efficient finetuning using LoRA, which enables LLMs to handle long context efficiently.

The 'gritlm' repository provides all materials for the paper Generative Representational Instruction Tuning. It includes code for inference, training, evaluation, and known issues related to the GritLM model. The repository also offers models for embedding and generation tasks, along with instructions on how to train and evaluate the models. Additionally, it contains visualizations, acknowledgements, and a citation for referencing the work.

The Oracle Cloud Infrastructure Data Science and AI services Examples repository provides demos, tutorials, and code examples showcasing various features of the OCI Data Science service and AI services. It offers tools for data scientists to develop and deploy machine learning models efficiently, with features like Accelerated Data Science SDK, distributed training, batch processing, and machine learning pipelines. Whether you're a beginner or an experienced practitioner, OCI Data Science Services provide the resources needed to build, train, and deploy models easily.

**deep** doctection is a Python library that orchestrates document extraction and document layout analysis tasks using deep learning models. It does not implement models but enables you to build pipelines using highly acknowledged libraries for object detection, OCR and selected NLP tasks and provides an integrated framework for fine-tuning, evaluating and running models. For more specific text processing tasks use one of the many other great NLP libraries. **deep** doctection focuses on applications and is made for those who want to solve real world problems related to document extraction from PDFs or scans in various image formats. **deep** doctection provides model wrappers of supported libraries for various tasks to be integrated into pipelines. Its core function does not depend on any specific deep learning library. Selected models for the following tasks are currently supported: * Document layout analysis including table recognition in Tensorflow with **Tensorpack**, or PyTorch with **Detectron2**, * OCR with support of **Tesseract**, **DocTr** (Tensorflow and PyTorch implementations available) and a wrapper to an API for a commercial solution, * Text mining for native PDFs with **pdfplumber**, * Language detection with **fastText**, * Deskewing and rotating images with **jdeskew**. * Document and token classification with all LayoutLM models provided by the **Transformer library**. (Yes, you can use any LayoutLM-model with any of the provided OCR-or pdfplumber tools straight away!). * Table detection and table structure recognition with **table-transformer**. * There is a small dataset for token classification available and a lot of new tutorials to show, how to train and evaluate this dataset using LayoutLMv1, LayoutLMv2, LayoutXLM and LayoutLMv3. * Comprehensive configuration of **analyzer** like choosing different models, output parsing, OCR selection. Check this notebook or the docs for more infos. * Document layout analysis and table recognition now runs with **Torchscript** (CPU) as well and **Detectron2** is not required anymore for basic inference. * [**new**] More angle predictors for determining the rotation of a document based on **Tesseract** and **DocTr** (not contained in the built-in Analyzer). * [**new**] Token classification with **LiLT** via **transformers**. We have added a model wrapper for token classification with LiLT and added a some LiLT models to the model catalog that seem to look promising, especially if you want to train a model on non-english data. The training script for LayoutLM can be used for LiLT as well and we will be providing a notebook on how to train a model on a custom dataset soon. **deep** doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words into contiguous text. You will get an output in JSON format that you can customize even further by yourself. Have a look at the **introduction notebook** in the notebook repo for an easy start. Check the **release notes** for recent updates. **deep** doctection or its support libraries provide pre-trained models that are in most of the cases available at the **Hugging Face Model Hub** or that will be automatically downloaded once requested. For instance, you can find pre-trained object detection models from the Tensorpack or Detectron2 framework for coarse layout analysis, table cell detection and table recognition. Training is a substantial part to get pipelines ready on some specific domain, let it be document layout analysis, document classification or NER. **deep** doctection provides training scripts for models that are based on trainers developed from the library that hosts the model code. Moreover, **deep** doctection hosts code to some well established datasets like **Publaynet** that makes it easy to experiment. It also contains mappings from widely used data formats like COCO and it has a dataset framework (akin to **datasets** so that setting up training on a custom dataset becomes very easy. **This notebook** shows you how to do this. **deep** doctection comes equipped with a framework that allows you to evaluate predictions of a single or multiple models in a pipeline against some ground truth. Check again **here** how it is done. Having set up a pipeline it takes you a few lines of code to instantiate the pipeline and after a for loop all pages will be processed through the pipeline.

Catalyst is a C# Natural Language Processing library designed for speed, inspired by spaCy's design. It provides pre-trained models, support for training word and document embeddings, and flexible entity recognition models. The library is fast, modern, and pure-C#, supporting .NET standard 2.0. It is cross-platform, running on Windows, Linux, macOS, and ARM. Catalyst offers non-destructive tokenization, named entity recognition, part-of-speech tagging, language detection, and efficient binary serialization. It includes pre-built models for language packages and lemmatization. Users can store and load models using streams. Getting started with Catalyst involves installing its NuGet Package and setting the storage to use the online repository. The library supports lazy loading of models from disk or online. Users can take advantage of C# lazy evaluation and native multi-threading support to process documents in parallel. Training a new FastText word2vec embedding model is straightforward, and Catalyst also provides algorithms for fast embedding search and dimensionality reduction.

The `sec-parser` project simplifies extracting meaningful information from SEC EDGAR HTML documents by organizing them into semantic elements and a tree structure. It helps in parsing SEC filings for financial and regulatory analysis, analytics and data science, AI and machine learning, causal AI, and large language models. The tool is especially beneficial for AI, ML, and LLM applications by streamlining data pre-processing and feature extraction.

BABILong is a generative benchmark designed to evaluate the performance of NLP models in processing long documents with distributed facts. It consists of 20 tasks that simulate interactions between characters and objects in various locations, requiring models to distinguish important information from irrelevant details. The tasks vary in complexity and reasoning aspects, with test samples potentially containing millions of tokens. The benchmark aims to challenge and assess the capabilities of Large Language Models (LLMs) in handling complex, long-context information.

ScrapeGraphAI is a Python library that uses Large Language Models (LLMs) and direct graph logic to create web scraping pipelines for websites, documents, and XML files. It allows users to extract specific information from web pages by providing a prompt describing the desired data. ScrapeGraphAI supports various LLMs, including Ollama, OpenAI, Gemini, and Docker, enabling users to choose the most suitable model for their needs. The library provides a user-friendly interface through its `SmartScraper` class, which simplifies the process of building and executing scraping pipelines. ScrapeGraphAI is open-source and available on GitHub, with extensive documentation and examples to guide users. It is particularly useful for researchers and data scientists who need to extract structured data from web pages for analysis and exploration.

This repository contains data and code for the experiments in the SummHay paper. It includes publicly released Haystacks in conversational and news domains, along with scripts for running the pipeline, visualizing results, and benchmarking automatic evaluation. The data structure includes topics, subtopics, insights, queries, retrievers, summaries, evaluation summaries, and documents. The pipeline involves scripts for retriever scores, summaries, and evaluation scores using GPT-4o. Visualization scripts are provided for compiling and visualizing results. The repository also includes annotated samples for benchmarking and citation information for the SummHay paper.

PaperQA is a minimal package for question and answering from PDFs or text files, providing very good answers with in-text citations. It uses OpenAI Embeddings to embed and search documents, and includes a process of embedding docs, queries, searching for top passages, creating summaries, using an LLM to re-score and select relevant summaries, putting summaries into prompt, and generating answers. The tool can be used to answer specific questions related to scientific research by leveraging citations and relevant passages from documents.

This repository contains a curated list of resources on generative information retrieval, including research papers, datasets, tools, and applications. Generative information retrieval is a subfield of information retrieval that uses generative models to generate new documents or passages of text that are relevant to a given query. This can be useful for a variety of tasks, such as question answering, summarization, and document generation. The resources in this repository are intended to help researchers and practitioners stay up-to-date on the latest advances in generative information retrieval.

Ax is a Typescript library that allows users to build intelligent agents inspired by agentic workflows and the Stanford DSP paper. It seamlessly integrates with multiple Large Language Models (LLMs) and VectorDBs to create RAG pipelines or collaborative agents capable of solving complex problems. The library offers advanced features such as streaming validation, multi-modal DSP, and automatic prompt tuning using optimizers. Users can easily convert documents of any format to text, perform smart chunking, embedding, and querying, and ensure output validation while streaming. Ax is production-ready, written in Typescript, and has zero dependencies.

qlora-pipe is a pipeline parallel training script designed for efficiently training large language models that cannot fit on one GPU. It supports QLoRA, LoRA, and full fine-tuning, with efficient model loading and the ability to load any dataset that Axolotl can handle. The script allows for raw text training, resuming training from a checkpoint, logging metrics to Tensorboard, specifying a separate evaluation dataset, training on multiple datasets simultaneously, and supports various models like Llama, Mistral, Mixtral, Qwen-1.5, and Cohere (Command R). It handles pipeline- and data-parallelism using Deepspeed, enabling users to set the number of GPUs, pipeline stages, and gradient accumulation steps for optimal utilization.

LangDrive is an open-source AI library that simplifies training, deploying, and querying open-source large language models (LLMs) using private data. It supports data ingestion, fine-tuning, and deployment via a command-line interface, YAML file, or API, with a quick, easy setup. Users can build AI applications such as question/answering systems, chatbots, AI agents, and content generators. The library provides features like data connectors for ingestion, fine-tuning of LLMs, deployment to Hugging Face hub, inference querying, data utilities for CRUD operations, and APIs for model access. LangDrive is designed to streamline the process of working with LLMs and making AI development more accessible.

Txtai is an all-in-one embeddings database for semantic search, LLM orchestration, and language model workflows. It combines vector indexes, graph networks, and relational databases to enable vector search with SQL, topic modeling, retrieval augmented generation, and more. Txtai can stand alone or serve as a knowledge source for large language models (LLMs). Key features include vector search with SQL, object storage, topic modeling, graph analysis, multimodal indexing, embedding creation for various data types, pipelines powered by language models, workflows to connect pipelines, and support for Python, JavaScript, Java, Rust, and Go. Txtai is open-source under the Apache 2.0 license.

Vespa is an open-source search and AI engine that provides a unified platform for building and deploying search and AI applications. Vespa sample applications showcase various use cases and features of Vespa, including basic search, recommendation, semantic search, image search, text ranking, e-commerce search, question answering, search-as-you-type, and ML inference serving.

The LLM course is divided into three parts: 1. 🧩 **LLM Fundamentals** covers essential knowledge about mathematics, Python, and neural networks. 2. 🧑‍🔬 **The LLM Scientist** focuses on building the best possible LLMs using the latest techniques. 3. 👷 **The LLM Engineer** focuses on creating LLM-based applications and deploying them. For an interactive version of this course, I created two **LLM assistants** that will answer questions and test your knowledge in a personalized way: * 🤗 **HuggingChat Assistant**: Free version using Mixtral-8x7B. * 🤖 **ChatGPT Assistant**: Requires a premium account. ## 📝 Notebooks A list of notebooks and articles related to large language models. ### Tools | Notebook | Description | Notebook | |----------|-------------|----------| | 🧐 LLM AutoEval | Automatically evaluate your LLMs using RunPod |  | | 🥱 LazyMergekit | Easily merge models using MergeKit in one click. |  | | 🦎 LazyAxolotl | Fine-tune models in the cloud using Axolotl in one click. |  | | ⚡ AutoQuant | Quantize LLMs in GGUF, GPTQ, EXL2, AWQ, and HQQ formats in one click. |  | | 🌳 Model Family Tree | Visualize the family tree of merged models. |  | | 🚀 ZeroSpace | Automatically create a Gradio chat interface using a free ZeroGPU. |  |

Expert in Medical Communications

Formal-tone expert on Google Gemini, using document-based info.

Especialista em Análise de Direitos Humanos em Contextos Multilíngues

An expert chatbot on AR 600-20, Army Command Policy

Expert on OpenAI's documentation, providing detailed and clear explanations.

Asistente experto en Botpress, centrado en brindar respuestas basadas en su documentación oficial.

Technical expert blending Kahneman's cognitive insights with Carmack's clarity.

Enter a product name in ExplodeView to get a three-stage visual transition from intact to fully exploded views.

Explains security concepts simply to juniors

Chew on this steak with me

Comprehensive training and wellness guide for Chesapeake Bay Retrievers.

Friendly train travel guide focusing on the best routes, essential travel information, and personalized travel insights, for both experienced and novice travelers.

Expert in pet training advice, friendly and engaging.

Your personal advisor for eco-friendly train travel. Let's plan your next journey together!

Train monsters, travel the world, earn Arena Tokens and become the ultimate monster battling champion of earth!

Train to pass the Reverse Turing Test!

Train to become a superhero or a supervillain. Master your powers, make pivotal choices. Each decision you make in this action-packed game not only shapes your abilities but also your moral alignment in the battle between good and evil. Another GPT Simulator by Dave Lalande

Your purpose is to create the pytorch code to train language models using pytorch

Learn Python and train for interviews with me

I'm a voice coach here to train your voice.