[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-QuivrHQ--MegaParse":3,"tool-QuivrHQ--MegaParse":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":80,"owner_twitter":81,"owner_website":82,"owner_url":83,"languages":84,"stars":97,"forks":98,"last_commit_at":99,"license":100,"difficulty_score":10,"env_os":101,"env_gpu":102,"env_ram":102,"env_deps":103,"category_tags":112,"github_topics":113,"view_count":10,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":119,"updated_at":120,"faqs":121,"releases":151},2122,"QuivrHQ\u002FMegaParse","MegaParse","File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs. ","MegaParse 是一款专为大语言模型（LLM）打造的开源文件解析工具，旨在将 PDF、Word、PPT、Excel 及 CSV 等各类文档转化为模型易于理解的高质量格式。它核心解决了传统解析过程中常见的信息丢失难题，能够精准保留文档中的表格、目录、页眉页脚甚至图片内容，确保数据完整性。\n\n对于需要构建知识库、进行文档问答或数据分析的开发者与研究人员而言，MegaParse 是理想的选择。它不仅兼容性强、处理速度快，还创新性地推出了\"MegaParse Vision\"功能，利用 GPT-4o、Claude 3.5 等多模态大模型的能力，显著提升了对复杂版面和视觉元素的解析精度。基准测试显示，其在内容还原度上优于多种主流解析方案。\n\n使用上，MegaParse 提供了简洁的 Python 接口和本地 API 服务，只需简单配置即可集成到现有工作流中。作为一个完全开源且免费的项目，它鼓励社区共同参与优化，特别适合希望高效、无损地将非结构化文档转化为 AI 可用数据的技术团队。","# MegaParse - Your Parser for every type of documents\n\n\u003Cdiv align=\"center\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FQuivrHQ_MegaParse_readme_fe7d9538b03c.png\" alt=\"Quivr-logo\" width=\"30%\"  style=\"border-radius: 50%; padding-bottom: 20px\"\u002F>\n\u003C\u002Fdiv>\n\nMegaParse is a powerful and versatile parser that can handle various types of documents with ease. Whether you're dealing with text, PDFs, Powerpoint presentations, Word documents MegaParse has got you covered. Focus on having no information loss during parsing.\n\n## Key Features 🎯\n\n- **Versatile Parser**: MegaParse is a powerful and versatile parser that can handle various types of documents with ease.\n- **No Information Loss**: Focus on having no information loss during parsing.\n- **Fast and Efficient**: Designed with speed and efficiency at its core.\n- **Wide File Compatibility**: Supports Text, PDF, Powerpoint presentations, Excel, CSV, Word documents.\n- **Open Source**: Freedom is beautiful, and so is MegaParse. Open source and free to use.\n\n## Support\n\n- Files: ✅ PDF ✅ Powerpoint ✅ Word\n- Content: ✅ Tables ✅ TOC ✅ Headers ✅ Footers ✅ Images\n\n### Example\n\nhttps:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fassets\u002F19614572\u002F1b4cdb73-8dc2-44ef-b8b4-a7509bc8d4f3\n\n## Installation\n\nrequired python version >= 3.11\n\n```bash\npip install megaparse\n```\n\n## Usage\n\n1. Add your OpenAI or Anthropic API key to the .env file\n\n2. Install poppler on your computer (images and PDFs)\n\n3. Install tesseract on your computer (images and PDFs)\n\n4. If you have a mac, you also need to install libmagic ```brew install libmagic```\n\nUse MegaParse as it is : \n```python\nfrom megaparse import MegaParse\nfrom langchain_openai import ChatOpenAI\n\nmegaparse = MegaParse()\nresponse = megaparse.load(\".\u002Ftest.pdf\")\nprint(response)\n```\n\n### Use MegaParse Vision\n\n```python\nfrom megaparse.parser.megaparse_vision import MegaParseVision\n\nmodel = ChatOpenAI(model=\"gpt-4o\", api_key=os.getenv(\"OPENAI_API_KEY\"))  # type: ignore\nparser = MegaParseVision(model=model)\nresponse = parser.convert(\".\u002Ftest.pdf\")\nprint(response)\n\n```\n**Note**: The model supported by MegaParse Vision are the multimodal ones such as claude 3.5, claude 4, gpt-4o and gpt-4.\n\n## Use as an API\nThere is a MakeFile for you, simply use :\n```make dev```\nat the root of the project and you are good to go.\n\nSee localhost:8000\u002Fdocs for more info on the different endpoints !\n\n## BenchMark\n\n\u003C!---BENCHMARK-->\n| Parser                        | similarity_ratio |\n| ----------------------------- | ---------------- |\n| megaparse_vision              | 0.87             |\n| unstructured_with_check_table | 0.77             |\n| unstructured                  | 0.59             |\n| llama_parser                  | 0.33             |\n\u003C!---END_BENCHMARK-->\n\n_Higher the better_\n\nNote: Want to evaluate and compare your Megaparse module with ours ? Please add your config in ```evaluations\u002Fscript.py``` and then run ```python evaluations\u002Fscript.py```. If it is better, do a PR, I mean, let's go higher together .\n\n## In Construction 🚧\n- Improve table checker\n- Create Checkers to add **modular postprocessing** ⚙️\n- Add Structured output, **let's get computer talking** 🤖\n\n\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FQuivrHQ_MegaParse_readme_415c0f2cac1f.png)](https:\u002F\u002Fstar-history.com\u002F#QuivrHQ\u002FMegaParse&Date)\n","# MegaParse - 您的各类文档解析器\n\n\u003Cdiv align=\"center\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FQuivrHQ_MegaParse_readme_fe7d9538b03c.png\" alt=\"Quivr-logo\" width=\"30%\"  style=\"border-radius: 50%; padding-bottom: 20px\"\u002F>\n\u003C\u002Fdiv>\n\nMegaParse 是一款功能强大且多用途的解析器，能够轻松处理各种类型的文档。无论您面对的是文本、PDF、PowerPoint 演示文稿还是 Word 文档，MegaParse 都能胜任。其核心目标是在解析过程中确保信息零丢失。\n\n## 核心特性 🎯\n\n- **多功能解析器**：MegaParse 是一款功能强大且多用途的解析器，能够轻松处理各种类型的文档。\n- **无信息丢失**：专注于在解析过程中不丢失任何信息。\n- **快速高效**：以速度和效率为核心设计。\n- **广泛的文件兼容性**：支持文本、PDF、PowerPoint 演示文稿、Excel、CSV 和 Word 文档。\n- **开源**：自由是美好的，MegaParse 也是如此。完全开源且免费使用。\n\n## 支持范围\n\n- 文件格式：✅ PDF ✅ PowerPoint ✅ Word\n- 内容类型：✅ 表格 ✅ 目录 ✅ 页眉 ✅ 页脚 ✅ 图片\n\n### 示例\n\nhttps:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fassets\u002F19614572\u002F1b4cdb73-8dc2-44ef-b8b4-a7509bc8d4f3\n\n## 安装\n\n需要 Python 版本 ≥ 3.11\n\n```bash\npip install megaparse\n```\n\n## 使用方法\n\n1. 将您的 OpenAI 或 Anthropic API 密钥添加到 `.env` 文件中。\n\n2. 在您的计算机上安装 Poppler（用于处理图片和 PDF）。\n\n3. 在您的计算机上安装 Tesseract（用于处理图片和 PDF）。\n\n4. 如果您使用的是 Mac，还需要安装 libmagic：`brew install libmagic`。\n\n直接使用 MegaParse：\n\n```python\nfrom megaparse import MegaParse\nfrom langchain_openai import ChatOpenAI\n\nmegaparse = MegaParse()\nresponse = megaparse.load(\".\u002Ftest.pdf\")\nprint(response)\n```\n\n### 使用 MegaParse Vision\n\n```python\nfrom megaparse.parser.megaparse_vision import MegaParseVision\n\nmodel = ChatOpenAI(model=\"gpt-4o\", api_key=os.getenv(\"OPENAI_API_KEY\"))  # type: ignore\nparser = MegaParseVision(model=model)\nresponse = parser.convert(\".\u002Ftest.pdf\")\nprint(response)\n```\n\n**注意**：MegaParse Vision 支持的模型为多模态模型，例如 Claude 3.5、Claude 4、GPT-4o 和 GPT-4。\n\n## 作为 API 使用\n我们为您准备了一个 Makefile，只需在项目根目录下运行：\n\n```make dev\n```\n\n即可启动服务。更多关于不同接口的信息，请访问 `localhost:8000\u002Fdocs`！\n\n## 基准测试\n\n\u003C!---BENCHMARK-->\n| 解析器                        | 相似度比率 |\n| ----------------------------- | ---------- |\n| megaparse_vision              | 0.87       |\n| unstructured_with_check_table | 0.77       |\n| unstructured                  | 0.59       |\n| llama_parser                  | 0.33       |\n\u003C!---END_BENCHMARK-->\n\n_数值越高越好_\n\n注：想评估并对比您自己的 Megaparse 模块与我们的表现吗？请将您的配置添加到 `evaluations\u002Fscript.py` 中，然后运行 `python evaluations\u002Fscript.py`。如果效果更好，请提交 PR——让我们一起不断进步！\n\n## 正在建设中 🚧\n- 改进表格检测功能\n- 创建检查器以实现 **模块化后处理** ⚙️\n- 添加结构化输出，**让计算机开口说话** 🤖\n\n\n\n## 星级历史\n\n[![星级历史图表](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FQuivrHQ_MegaParse_readme_415c0f2cac1f.png)](https:\u002F\u002Fstar-history.com\u002F#QuivrHQ\u002FMegaParse&Date)","# MegaParse 快速上手指南\n\nMegaParse 是一款功能强大的开源文档解析工具，支持 PDF、Word、PPT、Excel、CSV 及纯文本等多种格式。其核心优势在于解析过程中**零信息丢失**，能够精准提取表格、目录、页眉页脚及图片内容，并针对多模态大模型进行了优化。\n\n## 环境准备\n\n在开始之前，请确保满足以下系统要求和前置依赖：\n\n*   **Python 版本**：>= 3.11\n*   **API Key**：需准备 OpenAI 或 Anthropic 的 API Key（用于高级解析功能）。\n*   **系统依赖**：\n    *   **Poppler**：用于处理 PDF 和图片（所有平台必需）。\n    *   **Tesseract**：用于 OCR 文字识别（所有平台必需）。\n    *   **libmagic**：**macOS 用户必需**，可通过 `brew install libmagic` 安装。\n\n> **提示**：Linux 用户通常可通过包管理器安装依赖，例如 Ubuntu\u002FDebian：\n> `sudo apt-get install poppler-utils tesseract-ocr`\n\n## 安装步骤\n\n1.  **配置环境变量**\n    在项目根目录创建 `.env` 文件，并填入你的 API Key：\n    ```bash\n    OPENAI_API_KEY=your_openai_api_key\n    # 或\n    ANTHROPIC_API_KEY=your_anthropic_api_key\n    ```\n\n2.  **安装 Python 包**\n    使用 pip 安装 MegaParse：\n    ```bash\n    pip install megaparse\n    ```\n    *(国内用户如遇下载缓慢，可添加清华源：`pip install megaparse -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple`)*\n\n## 基本使用\n\n### 1. 标准解析模式\n适用于大多数文档解析场景，自动处理文本、表格和结构。\n\n```python\nfrom megaparse import MegaParse\nfrom langchain_openai import ChatOpenAI\n\n# 初始化解析器\nmegaparse = MegaParse()\n\n# 加载并解析文档 (支持 .pdf, .docx, .pptx 等)\nresponse = megaparse.load(\".\u002Ftest.pdf\")\n\n# 输出解析结果\nprint(response)\n```\n\n### 2. 视觉增强模式 (MegaParse Vision)\n适用于包含复杂图表、扫描件或需要高精度理解的文档。此模式调用多模态大模型（如 GPT-4o, Claude 3.5\u002F4）。\n\n```python\nfrom megaparse.parser.megaparse_vision import MegaParseVision\nfrom langchain_openai import ChatOpenAI\nimport os\n\n# 初始化多模态模型\nmodel = ChatOpenAI(model=\"gpt-4o\", api_key=os.getenv(\"OPENAI_API_KEY\"))\n\n# 初始化视觉解析器\nparser = MegaParseVision(model=model)\n\n# 转换文档\nresponse = parser.convert(\".\u002Ftest.pdf\")\n\nprint(response)\n```\n\n> **注意**：视觉模式支持的模型包括 `claude-3-5-sonnet`, `claude-4`, `gpt-4o`, `gpt-4` 等多模态模型。\n\n---\n*如需以 API 服务形式运行，可在项目根目录执行 `make dev`，随后访问 `localhost:8000\u002Fdocs` 查看接口文档。*","某金融分析团队需要构建一个智能投研助手，要求系统能精准理解并回答关于上市公司财报（PDF）、路演纪要（Word）及行业分析报告（PPT）中的复杂问题。\n\n### 没有 MegaParse 时\n- **关键数据丢失**：传统解析器在处理财报中的复杂表格时，往往将行列结构打散为纯文本，导致营收、利润等核心数值与对应科目错位，大模型无法正确计算同比环比。\n- **图文信息割裂**：包含趋势分析的图表被忽略或仅提取文件名，大模型缺失了可视化数据背后的关键洞察，回答缺乏深度。\n- **格式噪声干扰**：页眉、页脚和页码被错误混入正文，干扰了文档的逻辑分段，使得基于目录（TOC）的精准定位经常失效。\n- **多格式适配困难**：团队需为 PDF、Docx 和 PPTx 分别编写不同的清洗脚本，维护成本高且难以保证统一的数据质量标准。\n\n### 使用 MegaParse 后\n- **表格完美还原**：MegaParse 专有的表格检查机制完整保留了行列关系，大模型能直接基于结构化数据进行准确的财务比率分析和趋势判断。\n- **多模态内容融合**：利用 MegaParse Vision 能力，图表中的趋势线和关键标注被转化为详细的文字描述，确保大模型不遗漏任何视觉信息。\n- **纯净逻辑流**：自动识别并剔除页眉页脚等噪声，同时精准保留目录层级，让大模型能快速锁定章节内容，大幅提升检索增强生成（RAG）的准确率。\n- **统一高效接入**：一套代码即可无缝处理所有格式的文档，基准测试显示其信息保留相似度高达 0.87，显著优于其他开源方案，极大缩短了数据预处理周期。\n\nMegaParse 通过“零信息损耗”的解析能力，将非结构化文档转化为大模型真正“读得懂、算得准”的高质量语料，彻底释放了企业私有知识库的价值。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FQuivrHQ_MegaParse_90e31415.png","QuivrHQ","Quivr","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FQuivrHQ_5499d22e.png","",null,"stan@quivr.app","quivr_brain","https:\u002F\u002Fquivr.app","https:\u002F\u002Fgithub.com\u002FQuivrHQ",[85,89,93],{"name":86,"color":87,"percentage":88},"Python","#3572A5",98.9,{"name":90,"color":91,"percentage":92},"Dockerfile","#384d54",0.7,{"name":94,"color":95,"percentage":96},"Makefile","#427819",0.4,7346,417,"2026-04-05T09:39:43","Apache-2.0","Linux, macOS, Windows","未说明",{"notes":104,"python":105,"dependencies":106},"需要安装系统级依赖：Poppler（用于处理 PDF 和图片）、Tesseract（用于 OCR）。macOS 用户需额外通过 brew 安装 libmagic。使用 MegaParse Vision 功能需配置 OpenAI 或 Anthropic API Key，并支持多模态模型（如 gpt-4o, claude 3.5 等）。可通过 'make dev' 启动本地 API 服务。",">=3.11",[107,108,109,110,111],"megaparse","langchain_openai","poppler","tesseract","libmagic (macOS)",[13,26],[114,115,116,117,118],"docx","llm","parser","pdf","powerpoint","2026-03-27T02:49:30.150509","2026-04-06T10:24:05.093913",[122,127,132,137,142,147],{"id":123,"question_zh":124,"answer_zh":125,"source_url":126},9753,"为什么 megaparse.load() 返回空字符串而不是解析后的内容？","这通常是由于 `unstructured` 库依赖的 NLTK 模型下载失败导致的。请尝试运行以下命令手动下载所有 NLTK 数据：\n```bash\npython3 -m nltk.downloader all\n```\n此外，确保 `unstructured` 版本兼容（megaparse 0.0.53 需要 unstructured==0.15.0），如果版本冲突，可以尝试卸载后重新安装指定版本。","https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F223",{"id":128,"question_zh":129,"answer_zh":130,"source_url":131},9754,"解析文件时遇到 \"HTTP ERROR 403\" 或 OpenAI 端点错误怎么办？","这通常是因为 OpenAI 的 API 端点暂时饱和或服务不稳定导致的。如果遇到此错误，建议稍后重试。如果问题持续，请检查您的网络连接以及 OPENAI_API_KEY 是否正确配置。维护者确认此类问题通常是暂时性的，更新到最新版本或等待服务恢复即可解决。","https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F199",{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},9755,"如何在 Jupyter Notebook 或已有事件循环的环境中避免 \"This event loop is already running\" 错误？","该问题在 PR #202 中已得到修复。如果您使用的是旧版本（如 0.0.48），请升级到最新的 megaparse 版本以解决此异步事件循环冲突问题。维护者确认该修复即将发布或已包含在最新版本中。","https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F200",{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},9756,"如何获取提取文本对应的页码信息？","默认情况下，如果 `page_range` 显示为整个文档范围而非单页，可能是因为元数据未正确分配。MegaParse 通过 `metadata.page_number` 设置页码范围。确保在转换过程中每个元素的元数据被正确填充。代码逻辑应类似：\n```python\npage_range=(metadata.page_number, metadata.page_number) if metadata.page_number else None\n```\n如果仍然无法获取，可能需要检查底层 `process_file` 方法是否正确处理了分页图像转换。","https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F226",{"id":143,"question_zh":144,"answer_zh":145,"source_url":146},9757,"解析 PDF 时出现奇怪的 \"(cid:xxx)\" 标签代替正常字符（如字母 'e'）怎么办？","这通常是由于 PDF 字体编码问题导致的，特别是在使用某些工具（如 OnlyOffice）生成的 PDF 中。尝试在配置中使用高分辨率策略（HI_RES）来改善解析效果。可以通过以下代码设置：\n```python\nfrom megaparse_sdk.schema.parser_config import ParseFileConfig, StrategyEnum\nconfig = ParseFileConfig(strategy=StrategyEnum.HI_RES)\n```\n这将启用更强大的解析模式来处理复杂的字体映射。","https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F225",{"id":148,"question_zh":149,"answer_zh":150,"source_url":131},9758,"遇到 \"Field 'model_name' has conflict with protected namespace 'model_'\" 警告如何处理？","这是 Pydantic 版本的兼容性警告，通常不影响程序运行。如果需要消除警告，可以在初始化相关配置时设置 `model_config['protected_namespaces'] = ()`。不过，大多数情况下您可以忽略此警告，因为它不会阻碍文件的正常解析。确保您使用的 `unstructured` 和 `megaparse` 版本是匹配的也可以减少此类警告。",[152,157,162,167,172,177,182,187,192,197,202,207,212,217,222,227,232,237,242,247],{"id":153,"version":154,"summary_zh":155,"released_at":156},116746,"megaparse-v0.0.55","## [0.0.55](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.54...megaparse-v0.0.55) (2025-02-14)\n\n\n### Features\n\n* remove tensorrt ([#230](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F230)) ([8b8abbc](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F8b8abbc6a2a1b33d4e921d55d2519b773ec062c8))","2025-02-14T09:24:42",{"id":158,"version":159,"summary_zh":160,"released_at":161},116747,"megaparse-sdk-v0.1.12","## [0.1.12](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.11...megaparse-sdk-v0.1.12) (2025-02-13)\n\n\n### Features\n\n* add layout detection ([#228](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F228)) ([77f7040](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F77f7040c9c221a17effce089be7ec575cdd83468))","2025-02-14T08:15:47",{"id":163,"version":164,"summary_zh":165,"released_at":166},116748,"megaparse-v0.0.54","## [0.0.54](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.53...megaparse-v0.0.54) (2025-02-11)\n\n\n### Features\n\n* add_layout_detection ([#220](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F220)) ([2d2d0b4](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F2d2d0b42bba4c883db423568e932eda42edd60d7))","2025-02-11T16:37:18",{"id":168,"version":169,"summary_zh":170,"released_at":171},116749,"megaparse-sdk-v0.1.11","## [0.1.11](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.10...megaparse-sdk-v0.1.11) (2025-02-11)\n\n\n### Features\n\n* add_layout_detection ([#220](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F220)) ([2d2d0b4](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F2d2d0b42bba4c883db423568e932eda42edd60d7))\n* Text detection in auto strategy ([#209](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F209)) ([03c7ada](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F03c7ada1dc245e13ef41ffd6fa3a8ed869269d37))\n\n\n### Bug Fixes\n\n* Add EngineConfig & StrategyHandler ([#211](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F211)) ([2e1c6dd](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F2e1c6ddd676227d1cbc4cff9771b20595259ba38))\n* add parse tests for every supported extensions ([#198](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F198)) ([9dff0de](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F9dff0de0c1de848151fe9a6519b658f0924c1228))\n* Strategy heuristic test & fix ([#203](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F203)) ([7b7fb40](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F7b7fb40cae4ed380a5f0ca0035a7bd2bcc9147c3))","2025-02-11T16:38:44",{"id":173,"version":174,"summary_zh":175,"released_at":176},116750,"megaparse-v0.0.53","## [0.0.53](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.52...megaparse-v0.0.53) (2025-01-16)\n\n\n### Features\n\n* modular parser and formatter v0 ([#175](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F175)) ([1f4dcf8](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F1f4dcf88a5901c5a2682cb79284a0dbb08034cb2))\n* Text detection in auto strategy ([#209](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F209)) ([03c7ada](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F03c7ada1dc245e13ef41ffd6fa3a8ed869269d37))\n* type strategy output ([#216](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F216)) ([deb8765](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fdeb8765a4df8917a4857f51a02025243192d5cf8))\n\n\n### Bug Fixes\n\n* Add EngineConfig & StrategyHandler ([#211](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F211)) ([2e1c6dd](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F2e1c6ddd676227d1cbc4cff9771b20595259ba38))\n* add parse tests for every supported extensions ([#198](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F198)) ([9dff0de](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F9dff0de0c1de848151fe9a6519b658f0924c1228))\n* logging error ([#218](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F218)) ([a2170d7](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fa2170d7c711a5d7a0531f03aa9576937ddd6576e))\n* megaparse.load & add tests ([#202](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F202)) ([13c2677](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F13c2677bdadb4ba985a1abf9bafeb70548ab59f9))\n* Strategy heuristic test & fix ([#203](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F203)) ([7b7fb40](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F7b7fb40cae4ed380a5f0ca0035a7bd2bcc9147c3))\n* sync convert to parsers ([#186](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F186)) ([fbb7d36](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Ffbb7d365fbaf710a687fdc6becacd6d301c09707))","2025-01-16T20:56:19",{"id":178,"version":179,"summary_zh":180,"released_at":181},116751,"megaparse-v0.0.52","## [0.0.52](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.51...megaparse-v0.0.52) (2024-12-16)\n\n\n### Bug Fixes\n\n* hatchling version ([#193](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F193)) ([f6070a5](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Ff6070a5483a20eeb83751a2dcfc01b7f0fb14473))","2024-12-16T14:33:04",{"id":183,"version":184,"summary_zh":185,"released_at":186},116752,"megaparse-v0.0.51","## [0.0.51](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.50...megaparse-v0.0.51) (2024-12-16)\n\n\n### Features\n\n* updating langchain version ([#187](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F187)) ([0f1f597](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F0f1f5977df147e6b8c65d55445ccd86ef6f1a862))","2024-12-16T11:28:36",{"id":188,"version":189,"summary_zh":190,"released_at":191},116753,"megaparse-sdk-v0.1.10","## [0.1.10](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.9...megaparse-sdk-v0.1.10) (2024-12-16)\n\n\n### Bug Fixes\n\n* hatchling version ([#193](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F193)) ([f6070a5](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Ff6070a5483a20eeb83751a2dcfc01b7f0fb14473))","2024-12-16T14:33:59",{"id":193,"version":194,"summary_zh":195,"released_at":196},116754,"megaparse-v0.0.50","## [0.0.50](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.49...megaparse-v0.0.50) (2024-12-13)\n\n\n### Features\n\n* small fixes ([#181](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F181)) ([004afe2](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F004afe2f170570075bbebcd32dec5d15ddba4609))","2024-12-13T11:36:58",{"id":198,"version":199,"summary_zh":200,"released_at":201},116755,"megaparse-sdk-v0.1.9","## [0.1.9](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.8...megaparse-sdk-v0.1.9) (2024-12-13)\n\n\n### Features\n\n* small fixes ([#181](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F181)) ([004afe2](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F004afe2f170570075bbebcd32dec5d15ddba4609))","2024-12-13T11:37:42",{"id":203,"version":204,"summary_zh":205,"released_at":206},116756,"megaparse-v0.0.49","## [0.0.49](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.48...megaparse-v0.0.49) (2024-12-12)\n\n\n### Features\n\n* custom auto ([#131](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F131)) ([3cb5be4](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F3cb5be4a8c8eeb6dd6e9b87d7bbca24491db4c29))\n* faster ocr ([#180](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F180)) ([5661cb2](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F5661cb2d52d959cbca0f41339791129cd35d4036))","2024-12-12T14:02:25",{"id":208,"version":209,"summary_zh":210,"released_at":211},116757,"megaparse-sdk-v0.1.8","## [0.1.8](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.7...megaparse-sdk-v0.1.8) (2024-12-12)\n\n\n### Features\n\n* custom auto ([#131](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F131)) ([3cb5be4](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F3cb5be4a8c8eeb6dd6e9b87d7bbca24491db4c29))\n* faster ocr ([#180](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F180)) ([5661cb2](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F5661cb2d52d959cbca0f41339791129cd35d4036))","2024-12-12T14:03:28",{"id":213,"version":214,"summary_zh":215,"released_at":216},116758,"megaparse-v0.0.48","## [0.0.48](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.47...megaparse-v0.0.48) (2024-12-03)\n\n\n### Features\n\n* Update imports and parsers in README.md ([#156](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F156)) ([33e0303](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F33e0303821691c4b1fc821e6b33b874bd332d430))","2024-12-03T12:44:18",{"id":218,"version":219,"summary_zh":220,"released_at":221},116759,"megaparse-sdk-v0.1.7","## [0.1.7](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.6...megaparse-sdk-v0.1.7) (2024-11-25)\n\n\n### Bug Fixes\n\n* Update README.md ([#154](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F154)) ([a103393](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fa1033938184e20c24b0e54ee0db088b28075fd14))","2024-11-25T11:26:49",{"id":223,"version":224,"summary_zh":225,"released_at":226},116760,"megaparse-sdk-v0.1.6","## [0.1.6](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.5...megaparse-sdk-v0.1.6) (2024-11-25)\n\n\n### Features\n\n* megaparse sdk tests ([#148](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F148)) ([e030285](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fe0302853fc2c1526b8e912bf3ef85b970a5b89bc))","2024-11-25T09:27:43",{"id":228,"version":229,"summary_zh":230,"released_at":231},116761,"megaparse-v0.0.47","## [0.0.47](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.46...megaparse-v0.0.47) (2024-11-21)\n\n\n### Features\n\n* refacto megaparse for service ([#132](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F132)) ([ab9ad7f](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fab9ad7fb7db580a04a998d144dd2ba3407068334))\n* release plz ([#134](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F134)) ([d8a221e](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fd8a221e23f6e15e969c1328f183da3582d0d7925))","2024-11-21T14:35:24",{"id":233,"version":234,"summary_zh":235,"released_at":236},116762,"megaparse-v0.0.46","## [0.0.46](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.45...megaparse-v0.0.46) (2024-11-21)\n\n\n### Features\n\n* refacto megaparse for service ([#132](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F132)) ([ab9ad7f](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fab9ad7fb7db580a04a998d144dd2ba3407068334))","2024-11-21T10:40:39",{"id":238,"version":239,"summary_zh":240,"released_at":241},116763,"megaparse-sdk-v0.1.5","## [0.1.5](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-sdk-v0.1.4...megaparse-sdk-v0.1.5) (2024-11-21)\n\n\n### Features\n\n* refacto megaparse for service ([#132](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F132)) ([ab9ad7f](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fab9ad7fb7db580a04a998d144dd2ba3407068334))\n* release plz ([#134](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F134)) ([d8a221e](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002Fd8a221e23f6e15e969c1328f183da3582d0d7925))","2024-11-21T14:38:20",{"id":243,"version":244,"summary_zh":245,"released_at":246},116764,"megaparse-v0.0.45","## [0.0.45](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.44...megaparse-v0.0.45) (2024-11-19)\n\n\n### Bug Fixes\n\n* small fixes from backlogs ([#128](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F128)) ([954554c](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F954554c5abaa7b0513e9ff3f6bbaff393d36cf03))","2024-11-19T09:26:24",{"id":248,"version":249,"summary_zh":250,"released_at":251},116765,"megaparse-v0.0.44","## [0.0.44](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcompare\u002Fmegaparse-v0.0.43...megaparse-v0.0.44) (2024-11-18)\n\n\n### Bug Fixes\n\n* fixing the wrong passing of arguments to the parse_file endpoint ([#123](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fissues\u002F123)) ([9105672](https:\u002F\u002Fgithub.com\u002FQuivrHQ\u002FMegaParse\u002Fcommit\u002F9105672abc0942f26785e494053112d486e8d2d9))","2024-11-18T15:27:48"]