
prism-insight
AI 기반 주식 분석 및 매매 시뮬레이션 시스템
Stars: 75

PRISM-INSIGHT is a comprehensive stock analysis and trading simulation system based on AI agents. It automatically captures daily surging stocks via Telegram channel, generates expert-level analyst reports, and performs trading simulations. The system utilizes OpenAI GPT-4.1 for in-depth stock analysis and GPT-5 for investment strategy simulation. It also interacts with users via Anthropic Claude for Telegram conversations. The system architecture includes AI analysis agents, stock tracking, PDF conversion, and Telegram bot functionalities. Users can customize criteria for identifying surging stocks, modify AI prompts, and adjust chart styles. The project is open-source under the MIT license, and all investment decisions based on the analysis are the responsibility of the user.
README:
AI 기반 주식 분석 및 매매 시뮬레이션 시스템
- 공식 텔레그램 채널: (무료) 급등주 포착/주식 분석 리포트 다운로드/매매 시뮬레이션 제공 (https://t.me/stock_ai_agent)
- 커뮤니티: 아직 없음. 임시로 텔레그램 채널 토론방에서 대화 가능
PRISM-INSIGHT는 AI 분석 에이전트를 활용한 종합 주식 분석을 핵심으로 하는 시스템입니다. 텔레그램 채널을 통해 매일 급등주를 자동으로 포착하고, 전문가 수준의 애널리스트 리포트를 생성하여 매매 시뮬레이션을 수행합니다.
- 최초 시작일 : 2025.03.15
- 총 거래 건수: 36건
- 수익 거래: 15건
- 손실 거래: 21건
- 승률: 41.67%
- 누적 수익률: 295.62%
- 매매 성과 요약 대시보드
- 핵심 분석: OpenAI GPT-4.1 (종합 주식 분석 에이전트)
- 매매 시뮬레이션: OpenAI GPT-5 (투자 전략 시뮬레이션)
- 텔레그램 대화: Anthropic Claude (봇과의 상호작용)
- kospi_kosdaq: 주식 보고서 작성 시 KRX(한국거래소) 주식 데이터 담당 MCP 서버
- firecrawl: 주식 보고서 작성 시 웹크롤링 전문 MCP 서버
- perplexity: 주식 보고서 작성 시 웹검색 전문 MCP 서버
- sqlite: 매매 시뮬레이션 내역 내부 DB 저장 전문 MCP 서버
┌─────────────────┐ ┌──────────────────────┐ ┌─────────────────┐
│ 급등주 포착 │ -> │ 🤖 AI 분석 에이전트 │ -> │ 리포트 생성 │
│ (trigger_batch) │ │ (GPT-4.1 기반) │ │ (PDF 변환) │
└─────────────────┘ │ 📊기술적/🏢기본적 │ └─────────────────┘
│ │ 📰뉴스/💡전략 분석 │ │
v └──────────────────────┘ v
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ 텔레그램 얼럿 │ │ 종합 분석 │ │ 매매 시뮬레이션 │
│ 즉시 전송 │ │ (핵심) │ │ (GPT-5 기반) │
│ │ │ │ │ (트래킹) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
- Python 3.10+
- OpenAI API 키 (GPT-4.1, GPT-5)
- Anthropic API 키 (Claude-Sonnet-4)
- 텔레그램 봇 토큰 및 채널 ID
- wkhtmltopdf (PDF 변환용)
- 저장소 클론
git clone https://github.com/dragon1086/prism-insight.git
cd prism-insight
- 의존성 설치
pip install -r requirements.txt
- 설정 파일 준비 다음 예시 파일들을 복사하여 실제 설정 파일을 생성하세요:
cp .env.example .env
cp ./examples/streamlit/config.py.example ./examples/streamlit/config.py
cp mcp_agent.config.yaml.example mcp_agent.config.yaml
cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml
-
설정 파일 편집 복사한 설정 파일들을 편집하여 필요한 API 키와 설정값들을 입력하세요.
-
wkhtmltopdf 설치 (PDF 변환용)
# macOS
brew install wkhtmltopdf
# Ubuntu/Debian
sudo apt-get install wkhtmltopdf
# CentOS/RHEL
sudo yum install wkhtmltopdf
- perplexity-ask MCP 서버 설치
cd perplexity-ask
npm install
- 한글 폰트 설치 (Linux 환경)
Linux에서 차트 한글 표시를 위해 한글 폰트가 필요합니다.
# Rocky Linux 8 / CentOS / RHEL
sudo dnf install google-nanum-fonts
# Ubuntu 22.04+ / Debian
sudo apt update && sudo apt install fonts-nanum fonts-nanum-coding
# 폰트 캐시 갱신
sudo fc-cache -fv
python3 -c "import matplotlib.font_manager as fm; fm.fontManager.rebuild()"
참고: macOS와 Windows는 기본 한글 폰트가 지원되어 별도 설치 불필요
프로젝트 실행을 위해 다음 4개 설정 파일을 반드시 구성해야 합니다:
-
.env
: 환경 변수 (API 키, 토큰 등) -
./examples/streamlit/config.py
: 보고서 생성 웹 설정 -
mcp_agent.config.yaml
: MCP 에이전트 설정 -
mcp_agent.secrets.yaml
: MCP 에이전트 시크릿 정보
전체 파이프라인을 실행하여 급등주 분석부터 텔레그램 전송까지 자동화:
# 오전 + 오후 모두 실행 (프리미엄 계정)
python stock_analysis_orchestrator.py --mode both --account-type premium
# 오전만 실행
python stock_analysis_orchestrator.py --mode morning --account-type premium
# 오후만 실행 (무료 계정)
python stock_analysis_orchestrator.py --mode afternoon --account-type free
1. 급등주 포착만 실행
python trigger_batch.py morning INFO --output trigger_results.json
2. 특정 종목 AI 분석 보고서 생성 (핵심 기능)
python cores/main.py
# 또는 직접 analyze_stock 함수 사용
3. PDF 변환
python pdf_converter.py input.md output.pdf
4. 텔레그램 메시지 생성 및 전송
python telegram_summary_agent.py
python telegram_bot_agent.py
prism-insight/
├── 📂 cores/ # 🤖 핵심 AI 분석 엔진
│ ├── 📂 agents/ # AI 에이전트 모듈
│ │ ├── company_info_agents.py # 기업 정보 분석 에이전트
│ │ ├── news_strategy_agents.py # 뉴스 및 투자 전략 에이전트
│ │ └── stock_price_agents.py # 주가 및 거래량 분석 에이전트
│ ├── analysis.py # 종합 주식 분석 (핵심)
│ ├── main.py # 메인 분석 실행
│ ├── report_generation.py # 보고서 생성
│ ├── stock_chart.py # 차트 생성
│ └── utils.py # 유틸리티 함수
├── 📂 examples/streamlit/ # 웹 인터페이스
├── stock_analysis_orchestrator.py # 🎯 메인 오케스트레이터
├── trigger_batch.py # 급등주 포착 배치
├── telegram_bot_agent.py # 텔레그램 봇 (Claude 기반)
├── stock_tracking_agent.py # 매매 시뮬레이션 (GPT-5)
├── pdf_converter.py # PDF 변환
├── requirements.txt # 의존성 목록
├── .env.example # 환경 변수 예시
├── mcp_agent.config.yaml.example # MCP 에이전트 설정 예시
└── mcp_agent.secrets.yaml.example # MCP 에이전트 시크릿 예시
PRISM-INSIGHT의 핵심은 GPT-4.1 기반의 전문화된 AI 에이전트들을 통한 종합 주식 분석입니다:
- 기술적 분석: 주가 추세, 이동평균선, 지지/저항선 분석
- 거래량 분석: 투자자별(기관/외국인/개인) 매매 패턴 분석
- 기업 현황: 재무지표, 밸류에이션, 투자의견 분석
- 기업 개요: 사업구조, 경쟁력, 성장동력 분석
- 뉴스 분석: 당일 주가 변동 원인 및 주요 이슈 분석
- 투자 전략: 종합 분석을 바탕으로 한 투자자 유형별 전략 제시
AI 에이전트가 생성하는 종합 애널리스트 리포트는 다음 섹션들로 구성됩니다:
- 📊 핵심 투자 포인트 - 요약 및 주요 포인트
-
📈 기술적 분석
- 주가 및 거래량 분석
- 투자자 거래 동향 분석
-
🏢 기본적 분석
- 기업 현황 분석
- 기업 개요 분석
- 📰 뉴스 트렌드 분석 - 최근 주요 뉴스 및 이슈
- 💡 투자 전략 및 의견 - 투자자 유형별 전략
trigger_batch.py
에서 다음 조건들을 수정할 수 있습니다:
- 거래량 증가율 임계값
- 주가 상승률 기준
- 시가총액 필터링 조건
cores/agents/
디렉토리의 각 에이전트 파일에서 분석 지침을 커스터마이징할 수 있습니다.
cores/stock_chart.py
에서 차트 색상, 스타일, 지표를 수정할 수 있습니다.
- 프로젝트를 포크합니다
- 기능 브랜치를 생성합니다 (
git checkout -b feature/멋진기능
) - 변경사항을 커밋합니다 (
git commit -m '멋진 기능 추가'
) - 브랜치에 푸시합니다 (
git push origin feature/멋진기능
) - Pull Request를 생성합니다
이 프로젝트는 MIT 라이센스 하에 배포됩니다. 자세한 내용은 LICENSE
파일을 참조하세요.
본 시스템에서 제공하는 분석 정보는 투자 참고용이며, 투자 권유를 목적으로 하지 않습니다. 모든 투자 결정과 그에 따른 손익은 투자자 본인의 책임입니다.
프로젝트 관련 문의사항이나 버그 리포트는 GitHub Issues를 통해 제출해 주세요.
⭐ 이 프로젝트가 도움이 되었다면 Star를 눌러주세요!
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for prism-insight
Similar Open Source Tools

prism-insight
PRISM-INSIGHT is a comprehensive stock analysis and trading simulation system based on AI agents. It automatically captures daily surging stocks via Telegram channel, generates expert-level analyst reports, and performs trading simulations. The system utilizes OpenAI GPT-4.1 for in-depth stock analysis and GPT-5 for investment strategy simulation. It also interacts with users via Anthropic Claude for Telegram conversations. The system architecture includes AI analysis agents, stock tracking, PDF conversion, and Telegram bot functionalities. Users can customize criteria for identifying surging stocks, modify AI prompts, and adjust chart styles. The project is open-source under the MIT license, and all investment decisions based on the analysis are the responsibility of the user.

NovelForge
NovelForge is an AI-assisted writing tool with the potential for creating long-form content of millions of words. It offers a solution that combines world-building, structured content generation, and consistency maintenance. The tool is built around four core concepts: modular 'cards', customizable 'dynamic output models', flexible 'context injection', and consistency assurance through a 'knowledge graph'. It provides a highly structured and configurable writing environment, inspired by the Snowflake Method, allowing users to create and organize their content in a tree-like structure. NovelForge is highly customizable and extensible, allowing users to tailor their writing workflow to their specific needs.

All-Model-Chat
All Model Chat is a feature-rich, highly customizable web chat application designed specifically for the Google Gemini API family. It integrates dynamic model selection, multimodal file input, streaming responses, comprehensive chat history management, and extensive customization options to provide an unparalleled AI interactive experience.

private-llm-qa-bot
This is a production-grade knowledge Q&A chatbot implementation based on AWS services and the LangChain framework, with optimizations at various stages. It supports flexible configuration and plugging of vector models and large language models. The front and back ends are separated, making it easy to integrate with IM tools (such as Feishu).

uDesktopMascot
uDesktopMascot is an open-source project for a desktop mascot application with a theme of 'freedom of creation'. It allows users to load and display VRM or GLB/FBX model files on the desktop, customize GUI colors and background images, and access various features through a menu screen. The application supports Windows 10/11 and macOS platforms.

NGCBot
NGCBot is a WeChat bot based on the HOOK mechanism, supporting scheduled push of security news from FreeBuf, Xianzhi, Anquanke, and Qianxin Attack and Defense Community, KFC copywriting, filing query, phone number attribution query, WHOIS information query, constellation query, weather query, fishing calendar, Weibei threat intelligence query, beautiful videos, beautiful pictures, and help menu. It supports point functions, automatic pulling of people, ad detection, automatic mass sending, Ai replies, rich customization, and easy for beginners to use. The project is open-source and periodically maintained, with additional features such as Ai (Gpt, Xinghuo, Qianfan), keyword invitation to groups, automatic mass sending, and group welcome messages.

DocTranslator
DocTranslator is a document translation tool that supports various file formats, compatible with OpenAI format API, and offers batch operations and multi-threading support. Whether for individual users or enterprise teams, DocTranslator helps efficiently complete document translation tasks. It supports formats like txt, markdown, word, csv, excel, pdf (non-scanned), and ppt for AI translation. The tool is deployed using Docker for easy setup and usage.

MarkMap-OpenAi-ChatGpt
MarkMap-OpenAi-ChatGpt is a Vue.js-based mind map generation tool that allows users to generate mind maps by entering titles or content. The application integrates the markmap-lib and markmap-view libraries, supports visualizing mind maps, and provides functions for zooming and adapting the map to the screen. Users can also export the generated mind map in PNG, SVG, JPEG, and other formats. This project is suitable for quickly organizing ideas, study notes, project planning, etc. By simply entering content, users can get an intuitive mind map that can be continuously expanded, downloaded, and shared.

resume-design
Resume-design is an open-source and free resume design and template download website, built with Vue3 + TypeScript + Vite + Element-plus + pinia. It provides two design tools for creating beautiful resumes and a complete backend management system. The project has released two frontend versions and will integrate with a backend system in the future. Users can learn frontend by downloading the released versions or learn design tools by pulling the latest frontend code.

Nano
Nano is a Transformer-based autoregressive language model for personal enjoyment, research, modification, and alchemy. It aims to implement a specific and lightweight Transformer language model based on PyTorch, without relying on Hugging Face. Nano provides pre-training and supervised fine-tuning processes for models with 56M and 168M parameters, along with LoRA plugins. It supports inference on various computing devices and explores the potential of Transformer models in various non-NLP tasks. The repository also includes instructions for experiencing inference effects, installing dependencies, downloading and preprocessing data, pre-training, supervised fine-tuning, model conversion, and various other experiments.

AirPower4T
AirPower4T is a development base library based on Vue3 TypeScript Element Plus Vite, using decorators, object-oriented, Hook and other front-end development methods. It provides many common components and some feedback components commonly used in background management systems, and provides a lot of enums and decorators.

get_jobs
Get Jobs is a tool designed to help users find and apply for job positions on various recruitment platforms in China. It features AI job matching, automatic cover letter generation, multi-platform job application, automated filtering of inactive HR and headhunter positions, real-time WeChat message notifications, blacklisted company updates, driver adaptation for Win11, centralized configuration, long-lasting cookie login, XPathHelper plugin, global logging, and more. The tool supports platforms like Boss直聘, 猎聘, 拉勾, 51job, and 智联招聘. Users can configure the tool for customized job searches and applications.

rime_wanxiang
Rime Wanxiang is a pinyin input method based on deep optimized lexicon and language model. It features a lexicon with tones, AI and large corpus filtering, and frequency addition to provide more accurate sentence output. The tool supports various input methods and customization options, aiming to enhance user experience through lexicon and transcription. Users can also refresh the lexicon with different types of auxiliary codes using the LMDG toolkit package. Wanxiang offers core features like tone-marked pinyin annotations, phrase composition, and word frequency, with customizable functionalities. The tool is designed to provide a seamless input experience based on lexicon and transcription.

sanic-web
Sanic-Web is a lightweight, end-to-end, and easily customizable large model application project built on technologies such as Dify, Ollama & Vllm, Sanic, and Text2SQL. It provides a one-stop solution for developing large model applications, supporting graphical data-driven Q&A using ECharts, handling table-based Q&A with CSV files, and integrating with third-party RAG systems for general knowledge Q&A. As a lightweight framework, Sanic-Web enables rapid iteration and extension to facilitate the quick implementation of large model projects.

LotteryMaster
LotteryMaster is a tool designed to fetch lottery data, save it to Excel files, and provide analysis reports including number prediction, number recommendation, and number trends. It supports multiple platforms for access such as Web and mobile App. The tool integrates AI models like Qwen API and DeepSeek for generating analysis reports and trend analysis charts. Users can configure API parameters for controlling randomness, diversity, presence penalty, and maximum tokens. The tool also includes a frontend project based on uniapp + Vue3 + TypeScript for multi-platform applications. It provides a backend service running on Fastify with Node.js, Cheerio.js for web scraping, Pino for logging, xlsx for Excel file handling, and Jest for testing. The project is still in development and some features may not be fully implemented. The analysis reports are for reference only and do not constitute investment advice. Users are advised to use the tool responsibly and avoid addiction to gambling.

LabelQuick
LabelQuick_V2.0 is a fast image annotation tool designed and developed by the AI Horizon team. This version has been optimized and improved based on the previous version. It provides an intuitive interface and powerful annotation and segmentation functions to efficiently complete dataset annotation work. The tool supports video object tracking annotation, quick annotation by clicking, and various video operations. It introduces the SAM2 model for accurate and efficient object detection in video frames, reducing manual intervention and improving annotation quality. The tool is designed for Windows systems and requires a minimum of 6GB of memory.
For similar tasks

prism-insight
PRISM-INSIGHT is a comprehensive stock analysis and trading simulation system based on AI agents. It automatically captures daily surging stocks via Telegram channel, generates expert-level analyst reports, and performs trading simulations. The system utilizes OpenAI GPT-4.1 for in-depth stock analysis and GPT-5 for investment strategy simulation. It also interacts with users via Anthropic Claude for Telegram conversations. The system architecture includes AI analysis agents, stock tracking, PDF conversion, and Telegram bot functionalities. Users can customize criteria for identifying surging stocks, modify AI prompts, and adjust chart styles. The project is open-source under the MIT license, and all investment decisions based on the analysis are the responsibility of the user.

discollama
Discollama is a Discord bot powered by a local large language model backed by Ollama. It allows users to interact with the bot in Discord by mentioning it in a message to start a new conversation or in a reply to a previous response to continue an ongoing conversation. The bot requires Docker and Docker Compose to run, and users need to set up a Discord Bot and environment variable DISCORD_TOKEN before using discollama.py. Additionally, an Ollama server is needed, and users can customize the bot's personality by creating a custom model using Modelfile and running 'ollama create'.

ChatGPT-OpenAI-Smart-Speaker
ChatGPT Smart Speaker is a project that enables speech recognition and text-to-speech functionalities using OpenAI and Google Speech Recognition. It provides scripts for running on PC/Mac and Raspberry Pi, allowing users to interact with a smart speaker setup. The project includes detailed instructions for setting up the required hardware and software dependencies, along with customization options for the OpenAI model engine, language settings, and response randomness control. The Raspberry Pi setup involves utilizing the ReSpeaker hardware for voice feedback and light shows. The project aims to offer an advanced smart speaker experience with features like wake word detection and response generation using AI models.

bot-on-anything
The 'bot-on-anything' repository allows developers to integrate various AI models into messaging applications, enabling the creation of intelligent chatbots. By configuring the connections between models and applications, developers can easily switch between multiple channels within a project. The architecture is highly scalable, allowing the reuse of algorithmic capabilities for each new application and model integration. Supported models include ChatGPT, GPT-3.0, New Bing, and Google Bard, while supported applications range from terminals and web platforms to messaging apps like WeChat, Telegram, QQ, and more. The repository provides detailed instructions for setting up the environment, configuring the models and channels, and running the chatbot for various tasks across different messaging platforms.

agentlang
AgentLang is an open-source programming language and framework designed for solving complex tasks with the help of AI agents. It allows users to build business applications rapidly from high-level specifications, making it more efficient than traditional programming languages. The language is data-oriented and declarative, with a syntax that is intuitive and closer to natural languages. AgentLang introduces innovative concepts such as first-class AI agents, graph-based hierarchical data model, zero-trust programming, declarative dataflow, resolvers, interceptors, and entity-graph-database mapping.

OmniSteward
OmniSteward is an AI-powered steward system based on large language models that can interact with users through voice or text to help control smart home devices and computer programs. It supports multi-turn dialogue, tool calling for complex tasks, multiple LLM models, voice recognition, smart home control, computer program management, online information retrieval, command line operations, and file management. The system is highly extensible, allowing users to customize and share their own tools.

ai
Ai is a Japanese bot for Misskey, designed to provide various functionalities such as posting random notes, learning keywords, playing Reversi, server monitoring, and more. Users can interact with Ai by setting up a `config.json` file with specific parameters. The tool can be installed using Node.js and npm, with optional dependencies like MeCab for additional features. Ai can also be run using Docker for easier deployment. Some features may require specific fonts to be installed in the directory. Ai stores its memory using an in-memory database, ensuring persistence across sessions. The tool is licensed under MIT and has received the 'Works on my machine' award.

llm-chatbot-python
This repository provides resources for building a chatbot backed by Neo4j using Python. It includes instructions on running the application, setting up tests, and installing necessary libraries. The chatbot is designed to interact with users and provide recommendations based on data stored in a Neo4j database. The repository is part of the Neo4j GraphAcademy course on building chatbots with Python.
For similar jobs

promptflow
**Prompt flow** is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring. It makes prompt engineering much easier and enables you to build LLM apps with production quality.

deepeval
DeepEval is a simple-to-use, open-source LLM evaluation framework specialized for unit testing LLM outputs. It incorporates various metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., and runs locally on your machine for evaluation. It provides a wide range of ready-to-use evaluation metrics, allows for creating custom metrics, integrates with any CI/CD environment, and enables benchmarking LLMs on popular benchmarks. DeepEval is designed for evaluating RAG and fine-tuning applications, helping users optimize hyperparameters, prevent prompt drifting, and transition from OpenAI to hosting their own Llama2 with confidence.

MegaDetector
MegaDetector is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems. MegaDetector is just one of many tools that aims to make conservation biologists more efficient with AI. If you want to learn about other ways to use AI to accelerate camera trap workflows, check out our of the field, affectionately titled "Everything I know about machine learning and camera traps".

leapfrogai
LeapfrogAI is a self-hosted AI platform designed to be deployed in air-gapped resource-constrained environments. It brings sophisticated AI solutions to these environments by hosting all the necessary components of an AI stack, including vector databases, model backends, API, and UI. LeapfrogAI's API closely matches that of OpenAI, allowing tools built for OpenAI/ChatGPT to function seamlessly with a LeapfrogAI backend. It provides several backends for various use cases, including llama-cpp-python, whisper, text-embeddings, and vllm. LeapfrogAI leverages Chainguard's apko to harden base python images, ensuring the latest supported Python versions are used by the other components of the stack. The LeapfrogAI SDK provides a standard set of protobuffs and python utilities for implementing backends and gRPC. LeapfrogAI offers UI options for common use-cases like chat, summarization, and transcription. It can be deployed and run locally via UDS and Kubernetes, built out using Zarf packages. LeapfrogAI is supported by a community of users and contributors, including Defense Unicorns, Beast Code, Chainguard, Exovera, Hypergiant, Pulze, SOSi, United States Navy, United States Air Force, and United States Space Force.

llava-docker
This Docker image for LLaVA (Large Language and Vision Assistant) provides a convenient way to run LLaVA locally or on RunPod. LLaVA is a powerful AI tool that combines natural language processing and computer vision capabilities. With this Docker image, you can easily access LLaVA's functionalities for various tasks, including image captioning, visual question answering, text summarization, and more. The image comes pre-installed with LLaVA v1.2.0, Torch 2.1.2, xformers 0.0.23.post1, and other necessary dependencies. You can customize the model used by setting the MODEL environment variable. The image also includes a Jupyter Lab environment for interactive development and exploration. Overall, this Docker image offers a comprehensive and user-friendly platform for leveraging LLaVA's capabilities.

carrot
The 'carrot' repository on GitHub provides a list of free and user-friendly ChatGPT mirror sites for easy access. The repository includes sponsored sites offering various GPT models and services. Users can find and share sites, report errors, and access stable and recommended sites for ChatGPT usage. The repository also includes a detailed list of ChatGPT sites, their features, and accessibility options, making it a valuable resource for ChatGPT users seeking free and unlimited GPT services.

TrustLLM
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.

AI-YinMei
AI-YinMei is an AI virtual anchor Vtuber development tool (N card version). It supports fastgpt knowledge base chat dialogue, a complete set of solutions for LLM large language models: [fastgpt] + [one-api] + [Xinference], supports docking bilibili live broadcast barrage reply and entering live broadcast welcome speech, supports Microsoft edge-tts speech synthesis, supports Bert-VITS2 speech synthesis, supports GPT-SoVITS speech synthesis, supports expression control Vtuber Studio, supports painting stable-diffusion-webui output OBS live broadcast room, supports painting picture pornography public-NSFW-y-distinguish, supports search and image search service duckduckgo (requires magic Internet access), supports image search service Baidu image search (no magic Internet access), supports AI reply chat box [html plug-in], supports AI singing Auto-Convert-Music, supports playlist [html plug-in], supports dancing function, supports expression video playback, supports head touching action, supports gift smashing action, supports singing automatic start dancing function, chat and singing automatic cycle swing action, supports multi scene switching, background music switching, day and night automatic switching scene, supports open singing and painting, let AI automatically judge the content.