SuperAPI AI Directory
Partner with us中文AI newsFavorites

All AI tools

35,738 results · Page 734 of 993

llama-agents

AI agents

llama-agents (LlamaAgents) is an open-source Python framework released by run-llama for building and publishing document-centric agents. It is based on the Agent Workflows event-driven orchestration library; steps are async Python functions that can branch, loop, run in parallel, persist state, and recover from failures, with no DSL required. It can be embedded as a library in scripts, notebooks, or services, wrapped as a REST API via llama-agents-server, or built and deployed with one command using llamactl to LlamaParse, AWS Bedrock AgentCore, or your own infrastructure, and it works together with LlamaParse's document capabilities such as OCR and structured extraction.

Read more

LLaMA-O1

AI developer platforms

LLaMA-O1 is an open-source large reasoning model framework built on PyTorch and HuggingFace, designed to support training, inference, and evaluation. The project is developed by SimpleBerry and has released multiple pretrained and fine-tuned models and datasets, including LLaMA-O1-Supervised-1129 and others. The framework is dedicated to advancing the development of open-source large reasoning models, supporting features such as Long Chain-of-Thought (Long CoT) tokens, pretraining, supervised fine-tuning, Process Reward Model (PRM) token correction, and reinforcement learning with self-play. Some features, such as reinforcement learning, are still in training, and the inference-time reasoning enhancement framework is temporarily postponed. Users can obtain models, datasets, and an online demo (CPU only) through HuggingFace.

Read more

LLM Evaluation

AI developer platforms

Publisher-source summary: LLM Evaluation is the Clarifai large-language-model evaluation reference linked by the original catalog. A retained public list explicitly identifies the exact address as a Clarifai Guide. The publisher's Release 10.2 index describes an evaluation module for examining LLM performance against standardized benchmarks and custom criteria. This summary covers that documented purpose without inventing procedures from the unrecovered legacy guide. Current availability of the original documentation route and evaluation service was not verified.

Read more

LLM+RAG，支持Showdoc批量导入

AI marketing

This platform is an enterprise knowledge management and conversational robot system based on LLM (Large Language Model), GPT (Generative Pre-trained Transformer), and RAG (Retrieval-Augmented Generation) technologies. It integrates a vector database and advanced large language models, supporting enterprises in quickly building dedicated Q&A robots to achieve automated customer service, accelerated data retrieval, and internal knowledge sharing. The platform provides highly customized services and can create dedicated robots based on different knowledge bases, adapting to diverse business scenarios. The knowledge base management function is flexible, supporting division by business module and setting access permissions to ensure the security of digital assets. The independence of the knowledge base is strictly protected and is not shared with external large language models, strengthening data privacy and security. Installation is convenient, and it can be integrated into one's own system through a script-style single piece of code, quickly realizing intelligent business processes. The complete history of human-machine conversations is preserved, facilitating issue tracing and continuous improvement. In addition, this solution is also suitable for the medical field, providing preliminary diagnosis based on symptoms, health advice, and answers to medical knowledge by retrieving literature, manuals, and medical guides, improving the efficiency of obtaining health information.

Read more