Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (3.1%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: zinojeng
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 8.21 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme License Citation

README.md

Vision Agent

這是一個基於 LandingAI API 的智能文件分析工具,結合了 Anthropic Claude-3.5 和 OpenAI API 來提供最佳性能。目前支持以下功能:

功能特點

  • PDF 文件解析與分析
  • 智能文本提取
  • 文件結構識別
  • 多 LLM 支持(Anthropic Claude-3.5 和 OpenAI)

安裝要求

  • Python 3.8+
  • 相關依賴套件(見 requirements.txt)

快速開始

  1. 安裝依賴: bash pip install -r requirements.txt

  2. 設置環境變數: bash export LANDING_AI_API_KEY=your_landing_ai_key export ANTHROPIC_API_KEY=your_anthropic_key export OPENAI_API_KEY=your_openai_key

  3. 使用範例: ```python from visionagent.tools.pdfparser import PDFParser from vision_agent.utils.config import Config

config = Config() parser = PDFParser(config) result = parser.process_pdf("path/to/your/document.pdf") ```

專案結構

vision_agent/ ├── tools/ │ └── pdf_parser.py # PDF 解析工具 ├── utils/ │ ├── config.py # 配置管理 │ └── logger.py # 日誌工具 └── examples/ # 使用範例

LLM 提供者配置

本專案默認使用 Anthropic Claude-3.5 和 OpenAI API 的組合來提供最佳性能。你需要:

  1. Anthropic 註冊並獲取 API 金鑰
  2. OpenAI 註冊並獲取 API 金鑰
  3. LandingAI 註冊並獲取 API 金鑰

所有 API 金鑰都應該通過環境變數設置。

授權

MIT License

貢獻指南

歡迎提交 Pull Requests 來改善這個專案。

Owner

  • Login: zinojeng
  • Kind: user

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Laird"
  given-names: "Dillon"
- family-names: "Jagadeesan"
  given-name: "Shankar"
- family-names: "Cao"
  given-name: "Yazhou"
- family-names: "Ng"
  given-name: "Andrew"
title: "Vision Agent"
version: 0.2
date-released: 2024-02-12
url: "https://github.com/landing-ai/vision-agent"

GitHub Events

Total
  • Push event: 4
  • Create event: 2
Last Year
  • Push event: 4
  • Create event: 2

Dependencies

.github/workflows/ci_cd.yml actions
  • abatilo/actions-poetry v2.1.0 composite
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
.github/workflows/docs.yml actions
  • Gr1N/setup-poetry v8 composite
  • actions/checkout v3 composite
  • actions/deploy-pages v4 composite
  • actions/setup-python v4 composite
  • actions/upload-pages-artifact v3 composite
examples/chat/chat-app/package-lock.json npm
  • 495 dependencies
examples/chat/chat-app/package.json npm
  • @types/node ^20 development
  • @types/react ^18 development
  • @types/react-dom ^18 development
  • eslint ^8 development
  • eslint-config-next 15.0.2 development
  • postcss ^8 development
  • tailwindcss ^3.4.1 development
  • typescript ^5 development
  • @radix-ui/react-collapsible ^1.1.1
  • @radix-ui/react-scroll-area ^1.2.1
  • @radix-ui/react-slot ^1.1.0
  • @radix-ui/react-tabs ^1.1.1
  • class-variance-authority ^0.7.0
  • clsx ^2.1.1
  • lucide-react ^0.454.0
  • next 15.0.2
  • react 19.0.0-rc-02c0e824-20241028
  • react-dom 19.0.0-rc-02c0e824-20241028
  • react-syntax-highlighter ^15.6.1
  • tailwind-merge ^2.5.4
  • tailwindcss-animate ^1.0.7
  • zeromq ^6.1.1
examples/custom_tools/requirements.txt pypi
  • torch *
  • torchvision *
examples/mask_app/requirements.txt pypi
  • streamlit *
  • streamlit-drawable-canvas *
poetry.lock pypi
  • 157 dependencies
pyproject.toml pypi
  • autoflake 1.* develop
  • black >=23,<25 develop
  • data-science-types ^0.2.23 develop
  • griffe ^0.45.3 develop
  • isort 5.* develop
  • mkdocs ^1.5.3 develop
  • mkdocs-material ^9.4.2 develop
  • mkdocstrings ^0.23.0 develop
  • mypy <1.8.0 develop
  • pre-commit ^3.8.0 develop
  • pytest 7.* develop
  • responses ^0.23.1 develop
  • scikit-image <0.23.1 develop
  • setuptools ^68.0.0 develop
  • types-pillow ^9.5.0.4 develop
  • types-requests ^2.31.0.0 develop
  • types-tabulate ^0.9.0.20240106 develop
  • types-tqdm ^4.65.0.1 develop
  • PyMuPDF ^1.23.0
  • anthropic ^0.31.0
  • av ^11.0.0
  • e2b ^0.17.2a50
  • e2b-code-interpreter 0.0.11a37
  • flake8 ^7.0.0
  • ipykernel ^6.29.4
  • libcst ^1.5.0
  • matplotlib ^3.9.2
  • nbclient ^0.10.0
  • nbformat ^5.10.4
  • numpy >=1.21.0,<2.0.0
  • openai 1.*
  • opencv-python 4.*
  • opentelemetry-api ^1.29.0
  • pandas 2.*
  • pillow 10.*
  • pillow-heif ^0.16.0
  • pydantic 2.7.4
  • pydantic-settings ^2.2.1
  • pypdf2 ^3.0.1
  • python >=3.9,<4.0
  • python-dotenv ^1.0.0
  • pytube 15.0.0
  • requests 2.*
  • rich ^13.7.1
  • scikit-learn ^1.5.2
  • scipy 1.13.*
  • tabulate ^0.9.0
  • tenacity ^8.3.0
  • tqdm >=4.64.0,<5.0.0
  • typing_extensions 4.*