Best AI tools for< Develop Llms >

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.

LangChain is a framework for developing applications powered by large language models (LLMs). It simplifies every stage of the LLM application lifecycle, including development, productionization, and deployment. LangChain consists of open-source libraries such as langchain-core, langchain-community, and partner packages. It also includes LangGraph for building stateful agents and LangSmith for debugging and monitoring LLM applications.

YourGPT is a suite of next-generation AI products designed to empower businesses with the potential of Large Language Models (LLMs). Its products include a no-code AI Chatbot solution for customer support and LLM Spark, a developer platform for building and deploying production-ready LLM applications. YourGPT prioritizes data security and is GDPR compliant, ensuring the privacy and protection of customer data. With over 2,000 satisfied customers, YourGPT has earned trust through its commitment to quality and customer satisfaction.

Denvr DataWorks AI Cloud is a cloud-based AI platform that provides end-to-end AI solutions for businesses. It offers a range of features including high-performance GPUs, scalable infrastructure, ultra-efficient workflows, and cost efficiency. Denvr DataWorks is an NVIDIA Elite Partner for Compute, and its platform is used by leading AI companies to develop and deploy innovative AI solutions.

Dify.AI is a generative AI application development platform that allows users to create AI agents, chatbots, and other AI-powered applications. It provides a variety of tools and services to help developers build, deploy, and manage their AI applications. Dify.AI is designed to be easy to use, even for those with no prior experience in AI development.

OdiaGenAI is a collaborative initiative focused on conducting research on Generative AI and Large Language Models (LLM) for the Odia Language. The project aims to leverage AI technology to develop Generative AI and LLM-based solutions for the overall development of Odisha and the Odia language through collaboration among Odia technologists. The initiative offers pre-trained models, codes, and datasets for non-commercial and research purposes, with a focus on building language models for Indic languages like Odia and Bengali.

The website is a simple and straightforward platform that seems to lack content or functionality. It appears to be a placeholder or under construction. There is no specific information available on the site, and it seems to be in a basic state of development.

Anyscale is a company that provides a scalable compute platform for AI and Python applications. Their platform includes a serverless API for serving and fine-tuning open LLMs, a private cloud solution for data privacy and governance, and an open source framework for training, batch, and real-time workloads. Anyscale's platform is used by companies such as OpenAI, Uber, and Spotify to power their AI workloads.

Focus Group Simulator is an AI tool designed to generate market insights instantly by simulating focus groups. By combining the power of LLMs to personate target segments with marketing quants analysis and best marketing frameworks, the tool provides valuable insights for businesses, especially startups. It helps identify low-hanging-fruit segments and offers guidance on product development, pricing, and promotion strategies to create more value and avoid waste. Users can customize simulations and engage with the team for further enhancements.

LLMChess is a web-based chess game that utilizes large language models (LLMs) to power the gameplay. Players can select the LLM model they wish to play against, and the game will commence once the "Start" button is clicked. The game logs are displayed in a black-bordered pane on the right-hand side of the screen. LLMChess is compatible with the Google Chrome browser. For more information on the game's functionality and participation guidelines, please refer to the provided link.

Weam is an AI adoption platform designed for digital agencies to supercharge their operations with collaborative AI. It offers a comprehensive suite of tools for simplifying AI implementation, including project management, resource allocation, training modules, and ongoing support to ensure successful AI integration. Weam enables teams to interact and collaborate over their preferred LLMs, facilitating scalability, time-saving, and widespread AI adoption across the organization.

Prompt Engineering is a discipline focused on developing and optimizing prompts to efficiently utilize language models (LMs) for various applications and research topics. It involves skills to understand the capabilities and limitations of large language models, improving their performance on tasks like question answering and arithmetic reasoning. Prompt engineering is essential for designing robust prompting techniques that interact with LLMs and other tools, enhancing safety and building new capabilities by augmenting LLMs with domain knowledge and external tools.

Retell AI provides a Conversational Voice API that enables developers to integrate human-like voice interactions into their applications. With Retell AI's API, developers can easily connect their own Large Language Models (LLMs) to create AI-powered voice agents that can engage in natural and engaging conversations. Retell AI's API offers a range of features, including ultra-low latency, realistic voices with emotions, interruption handling, and end-of-turn detection, ensuring seamless and lifelike conversations. Developers can also customize various aspects of the conversation experience, such as voice stability, backchanneling, and custom voice cloning, to tailor the AI agent to their specific needs. Retell AI's API is designed to be easy to integrate with existing LLMs and frontend applications, making it accessible to developers of all levels.

WeGPT.ai is an AI tool that focuses on enhancing Generative AI capabilities through Retrieval Augmented Generation (RAG). It provides versatile tools for web browsing, REST APIs, image generation, and coding playgrounds. The platform offers consumer and enterprise solutions, multi-vendor support, and access to major frontier LLMs. With a comprehensive approach, WeGPT.ai aims to deliver better results, user experience, and cost efficiency by keeping AI models up-to-date with the latest data.

UnfoldAI is a website offering articles, strategies, and tutorials for building production-grade ML systems. Authored by Simeon Emanuilov, the site covers topics such as deep learning, computer vision, LLMs, programming, MLOps, performance, scalability, and AI consulting. It aims to provide insights and best practices for professionals in the field of machine learning to create robust, efficient, and scalable systems.

FutureSmart AI is a platform that provides custom Natural Language Processing (NLP) solutions. The platform focuses on integrating Mem0 with LangChain to enhance AI Assistants with Intelligent Memory. It offers tutorials, guides, and practical tips for building applications with large language models (LLMs) to create sophisticated and interactive systems. FutureSmart AI also features internship journeys and practical guides for mastering RAG with LangChain, catering to developers and enthusiasts in the realm of NLP and AI.

Devika AI is an open-source AI software engineer that can understand high-level human instructions, break them down into steps, research relevant information, and generate code for particular tasks. It uses Claude 3, GPT-4, GPT-3.5, and Local LLMs via Ollama.

UBOS is an engineering platform for Software 3.0 and AI Agents, offering a comprehensive suite of tools for building enterprise-ready internal development platforms, web applications, and intelligent workflows. It enables users to connect to over 1000 APIs, automate workflows with AI, and access a marketplace with templates and AI models. UBOS empowers startups, small and medium businesses, and large enterprises to drive growth, efficiency, and innovation through advanced ML orchestration and Generative AI custom integration. The platform provides a user-friendly interface for creating AI-native applications, leveraging Generative AI, Node-Red SCADA, Edge AI, and IoT technologies. With a focus on open-source development, UBOS offers full code ownership, flexible exports, and seamless integration with leading LLMs like ChatGPT and Llama 2 from Meta.

The website page text discusses the latest advancements in AI technology, specifically focusing on the introduction of AI assistants and capabilities by various companies. It highlights the use of Large Language Models (LLMs) and generative AI to enhance customer service experiences, improve operational efficiency, and drive innovation across industries. The text showcases how AI avatars powered by NVIDIA technology are revolutionizing customer interactions and employee service experiences. It also mentions the collaboration between ServiceNow and NVIDIA to develop AI avatars for Now Assist, demonstrating the potential for more engaging and personalized communication through digital characters. Additionally, the text features the launch of Orchestrator LLM by Yellow.ai, an agent model that enables contextually aware and human-like customer conversations without the need for training, leading to increased customer satisfaction and operational efficiency.

StandardNodeAI is an AI application that offers end-to-end sales systems utilizing AI to help businesses scale without huge costs. It provides bespoke AI solutions, AI chat agents, and tools to optimize operations, streamline workflows, and automate tasks. The application also offers AI models to gain actionable insights, custom solutions to save time and increase revenue, and LLM's to improve work productivity. StandardNodeAI replaces manual staff timings with 24/7 customer support and lead qualification, making it easier for clients to manage leads effectively. The application aims to revolutionize businesses by harnessing the efficiency of AI and providing tailored solutions for startups and businesses.

This repository contains code for research conducted by the LLM-Random research group at IDEAS NCBR in Warsaw, Poland. The group focuses on developing and using this repository to conduct research. For more information about the group and its research, refer to their blog, llm-random.github.io.

TrustLLM is a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. The document explains how to use the trustllm python package to help you assess the performance of your LLM in trustworthiness more quickly. For more details about TrustLLM, please refer to project website.

Cherry Data Selection project introduces a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, minimizing manual curation and cost for instruction tuning. The project focuses on selecting impactful training samples ('cherry data') to enhance LLM instruction tuning by estimating instruction-following difficulty. The method involves phases like 'Learning from Brief Experience', 'Evaluating Based on Experience', and 'Retraining from Self-Guided Experience' to improve LLM performance.

LLM-Merging is a repository containing starter code for the LLM-Merging competition. It provides a platform for efficiently building LLMs through merging methods. Users can develop new merging methods by creating new files in the specified directory and extending existing classes. The repository includes instructions for setting up the environment, developing new merging methods, testing the methods on specific datasets, and submitting solutions for evaluation. It aims to facilitate the development and evaluation of merging methods for LLMs.

This repository provides a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from **model-centric** , **data-centric** , and **framework-centric** perspective, respectively. We hope our survey and this GitHub repository can serve as valuable resources to help researchers and practitioners gain a systematic understanding of the research developments in efficient LLMs and inspire them to contribute to this important and exciting field.

This repository contains tutorials for using Large Language Models (LLMs) in the U.S. Department of Defense. The tutorials utilize open-source frameworks and LLMs, allowing users to run them in their own cloud environments. The repository is maintained by the Defense Digital Service and welcomes contributions from users.

This is the official repository for the ACM CCS 2024 paper 'Do Anything Now': Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models. The project employs a new framework called JailbreakHub to conduct the first measurement study on jailbreak prompts in the wild, collecting 15,140 prompts from December 2022 to December 2023, including 1,405 jailbreak prompts. The dataset serves as the largest collection of in-the-wild jailbreak prompts. The repository contains examples of harmful language and is intended for research purposes only.

The 'llms' repository is a comprehensive guide on Large Language Models (LLMs), covering topics such as language modeling, applications of LLMs, statistical language modeling, neural language models, conditional language models, evaluation methods, transformer-based language models, practical LLMs like GPT and BERT, prompt engineering, fine-tuning LLMs, retrieval augmented generation, AI agents, and LLMs for computer vision. The repository provides detailed explanations, examples, and tools for working with LLMs.

Labelbox is a data-centric AI platform for enterprises to develop, optimize, and use AI to solve problems and power new products and services. Enterprises use Labelbox to curate data, generate high-quality human feedback data for computer vision and LLMs, evaluate model performance, and automate tasks by combining AI and human-centric workflows. The academic & research community uses Labelbox for cutting-edge AI research.

Floneum is a graph editor that makes it easy to develop your own AI workflows. It uses large language models (LLMs) to run AI models locally, without any external dependencies or even a GPU. This makes it easy to use LLMs with your own data, without worrying about privacy. Floneum also has a plugin system that allows you to improve the performance of LLMs and make them work better for your specific use case. Plugins can be used in any language that supports web assembly, and they can control the output of LLMs with a process similar to JSONformer or guidance.

Uni-MoE is a MoE-based unified multimodal model that can handle diverse modalities including audio, speech, image, text, and video. The project focuses on scaling Unified Multimodal LLMs with a Mixture of Experts framework. It offers enhanced functionality for training across multiple nodes and GPUs, as well as parallel processing at both the expert and modality levels. The model architecture involves three training stages: building connectors for multimodal understanding, developing modality-specific experts, and incorporating multiple trained experts into LLMs using the LoRA technique on mixed multimodal data. The tool provides instructions for installation, weights organization, inference, training, and evaluation on various datasets.

Raspberry is an open source project aimed at creating a toy dataset for finetuning Large Language Models (LLMs) with reasoning abilities. The project involves synthesizing complex user queries across various domains, generating CoT and Self-Critique data, cleaning and rectifying samples, finetuning an LLM with the dataset, and seeking funding for scalability. The ultimate goal is to develop a dataset that challenges models with tasks requiring math, coding, logic, reasoning, and planning skills, spanning different sectors like medicine, science, and software development.

OpenRedTeaming is a repository focused on red teaming for generative models, specifically large language models (LLMs). The repository provides a comprehensive survey on potential attacks on GenAI and robust safeguards. It covers attack strategies, evaluation metrics, benchmarks, and defensive approaches. The repository also implements over 30 auto red teaming methods. It includes surveys, taxonomies, attack strategies, and risks related to LLMs. The goal is to understand vulnerabilities and develop defenses against adversarial attacks on large language models.

LLMOps Duke AIPI is a course focused on operationalizing Large Language Models, teaching methodologies for developing applications using software development best practices with large language models. The course covers various topics such as generative AI concepts, setting up development environments, interacting with large language models, using local large language models, applied solutions with LLMs, extensibility using plugins and functions, retrieval augmented generation, introduction to Python web frameworks for APIs, DevOps principles, deploying machine learning APIs, LLM platforms, and final presentations. Students will learn to build, share, and present portfolios using Github, YouTube, and Linkedin, as well as develop non-linear life-long learning skills. Prerequisites include basic Linux and programming skills, with coursework available in Python or Rust. Additional resources and references are provided for further learning and exploration.

This project is a tutorial on developing large model applications for novice developers. It aims to provide a comprehensive introduction to large model development, focusing on Alibaba Cloud servers and integrating personal knowledge assistant projects. The tutorial covers the following topics: 1. **Introduction to Large Models**: A simplified introduction for novice developers on what large models are, their characteristics, what LangChain is, and how to develop an LLM application. 2. **How to Call Large Model APIs**: This section introduces various methods for calling APIs of well-known domestic and foreign large model products, including calling native APIs, encapsulating them as LangChain LLMs, and encapsulating them as Fastapi calls. It also provides a unified encapsulation for various large model APIs, such as Baidu Wenxin, Xunfei Xinghuo, and Zh譜AI. 3. **Knowledge Base Construction**: Loading, processing, and vector database construction of different types of knowledge base documents. 4. **Building RAG Applications**: Integrating LLM into LangChain to build a retrieval question and answer chain, and deploying applications using Streamlit. 5. **Verification and Iteration**: How to implement verification and iteration in large model development, and common evaluation methods. The project consists of three main parts: 1. **Introduction to LLM Development**: A simplified version of V1 aims to help beginners get started with LLM development quickly and conveniently, understand the general process of LLM development, and build a simple demo. 2. **LLM Development Techniques**: More advanced LLM development techniques, including but not limited to: Prompt Engineering, processing of multiple types of source data, optimizing retrieval, recall ranking, Agent framework, etc. 3. **LLM Application Examples**: Introduce some successful open source cases, analyze the ideas, core concepts, and implementation frameworks of these application examples from the perspective of this course, and help beginners understand what kind of applications they can develop through LLM. Currently, the first part has been completed, and everyone is welcome to read and learn; the second and third parts are under creation. **Directory Structure Description**: requirements.txt: Installation dependencies in the official environment notebook: Notebook source code file docs: Markdown documentation file figures: Pictures data_base: Knowledge base source file used

This simple package can be used to fix an invalid json string. To know all cases in which this package will work, check out the unit test. Inspired by https://github.com/josdejong/jsonrepair Motivation Some LLMs are a bit iffy when it comes to returning well formed JSON data, sometimes they skip a parentheses and sometimes they add some words in it, because that's what an LLM does. Luckily, the mistakes LLMs make are simple enough to be fixed without destroying the content. I searched for a lightweight python package that was able to reliably fix this problem but couldn't find any. So I wrote one How to use from json_repair import repair_json good_json_string = repair_json(bad_json_string) # If the string was super broken this will return an empty string You can use this library to completely replace `json.loads()`: import json_repair decoded_object = json_repair.loads(json_string) or just import json_repair decoded_object = json_repair.repair_json(json_string, return_objects=True) Read json from a file or file descriptor JSON repair provides also a drop-in replacement for `json.load()`: import json_repair try: file_descriptor = open(fname, 'rb') except OSError: ... with file_descriptor: decoded_object = json_repair.load(file_descriptor) and another method to read from a file: import json_repair try: decoded_object = json_repair.from_file(json_file) except OSError: ... except IOError: ... Keep in mind that the library will not catch any IO-related exception and those will need to be managed by you Performance considerations If you find this library too slow because is using `json.loads()` you can skip that by passing `skip_json_loads=True` to `repair_json`. Like: from json_repair import repair_json good_json_string = repair_json(bad_json_string, skip_json_loads=True) I made a choice of not using any fast json library to avoid having any external dependency, so that anybody can use it regardless of their stack. Some rules of thumb to use: - Setting `return_objects=True` will always be faster because the parser returns an object already and it doesn't have serialize that object to JSON - `skip_json_loads` is faster only if you 100% know that the string is not a valid JSON - If you are having issues with escaping pass the string as **raw** string like: `r"string with escaping\"" Adding to requirements Please pin this library only on the major version! We use TDD and strict semantic versioning, there will be frequent updates and no breaking changes in minor and patch versions. To ensure that you only pin the major version of this library in your `requirements.txt`, specify the package name followed by the major version and a wildcard for minor and patch versions. For example: json_repair==0.* In this example, any version that starts with `0.` will be acceptable, allowing for updates on minor and patch versions. How it works This module will parse the JSON file following the BNF definition: ::= | ::= | | ; Where: ; is a valid real number expressed in one of a number of given formats ; is a string of valid characters enclosed in quotes ; is one of the literal strings 'true', 'false', or 'null' (unquoted) ::=