[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-tmc--langchaingo":3,"tool-tmc--langchaingo":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",138956,2,"2026-04-05T11:33:21",[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":80,"owner_email":81,"owner_twitter":82,"owner_website":79,"owner_url":83,"languages":84,"stars":96,"forks":97,"last_commit_at":98,"license":99,"difficulty_score":23,"env_os":100,"env_gpu":101,"env_ram":101,"env_deps":102,"category_tags":107,"github_topics":108,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":113,"updated_at":114,"faqs":115,"releases":146},3143,"tmc\u002Flangchaingo","langchaingo","LangChain for Go, the easiest way to write LLM-based programs in Go","langchaingo 是知名大语言应用开发框架 LangChain 的 Go 语言版本，旨在让开发者能够使用 Go 轻松构建基于大语言模型（LLM）的应用程序。它解决了 Go 开发者在接入各类 AI 模型时缺乏统一、高效开发工具的问题，通过模块化设计将模型调用、提示词管理、记忆存储等复杂流程标准化，极大地降低了开发门槛。\n\n这款工具主要面向熟悉 Go 语言的软件工程师和后端开发人员。如果你希望利用 Go 语言在高并发和系统性能方面的优势来打造 AI 应用，langchaingo 是理想的选择。其核心亮点在于“可组合性”，允许用户像搭积木一样灵活串联不同的组件，快速实现从简单的文本生成到复杂的智能代理等多种功能。目前，它不仅支持 OpenAI 等主流云服务模型，还兼容 Ollama、Gemini 等本地或开源模型，并拥有活跃的社区支持和丰富的实战案例。无论是想快速验证想法的原型开发，还是构建生产级服务，langchaingo 都能提供简洁而强大的技术支持。","> 🎉 **Join our new official Discord community!** Connect with other LangChain Go developers, get help and contribute: [Join Discord](https:\u002F\u002Fdiscord.gg\u002Ft9UbBQs2rG)\n\n# 🦜️🔗 LangChain Go\n\n[![go.dev reference](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fgo.dev-reference-007d9c?logo=go&logoColor=white&style=flat-square)](https:\u002F\u002Fpkg.go.dev\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n[![scorecard](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftmc_langchaingo_readme_2b4a70945b89.png)](https:\u002F\u002Fgoreportcard.com\u002Freport\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n[![](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002Ft9UbBQs2rG?compact=true&style=flat)](https:\u002F\u002Fdiscord.gg\u002Ft9UbBQs2rG)\n[![Open in Dev Containers](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https:\u002F\u002Fvscode.dev\u002Fredirect?url=vscode:\u002F\u002Fms-vscode-remote.remote-containers\u002FcloneInVolume?url=https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n[\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fcodespaces\u002Fbadge.svg\" title=\"Open in Github Codespace\" width=\"150\" height=\"20\">](https:\u002F\u002Fcodespaces.new\u002Ftmc\u002Flangchaingo)\n\n⚡ Building applications with LLMs through composability, with Go! ⚡\n\n## 🤔 What is this?\n\nThis is the Go language implementation of [LangChain](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchain).\n\n## 📖 Documentation\n\n- [Documentation Site](https:\u002F\u002Ftmc.github.io\u002Flangchaingo\u002Fdocs\u002F)\n- [API Reference](https:\u002F\u002Fpkg.go.dev\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n\n\n## 🎉 Examples\n\nSee [.\u002Fexamples](.\u002Fexamples) for example usage.\n\n```go\npackage main\n\nimport (\n  \"context\"\n  \"fmt\"\n  \"log\"\n\n  \"github.com\u002Ftmc\u002Flangchaingo\u002Fllms\"\n  \"github.com\u002Ftmc\u002Flangchaingo\u002Fllms\u002Fopenai\"\n)\n\nfunc main() {\n  ctx := context.Background()\n  llm, err := openai.New()\n  if err != nil {\n    log.Fatal(err)\n  }\n  prompt := \"What would be a good company name for a company that makes colorful socks?\"\n  completion, err := llms.GenerateFromSinglePrompt(ctx, llm, prompt)\n  if err != nil {\n    log.Fatal(err)\n  }\n  fmt.Println(completion)\n}\n```\n\n```shell\n$ go run .\nSocktastic\n```\n\n# Resources\n\nJoin the Discord server for support and discussions: [Join Discord](https:\u002F\u002Fdiscord.gg\u002F8bHGKzHBkM)\n\nHere are some links to blog posts and articles on using Langchain Go:\n\n- [Using Gemini models in Go with LangChainGo](https:\u002F\u002Feli.thegreenplace.net\u002F2024\u002Fusing-gemini-models-in-go-with-langchaingo\u002F) - Jan 2024\n- [Using Ollama with LangChainGo](https:\u002F\u002Feli.thegreenplace.net\u002F2023\u002Fusing-ollama-with-langchaingo\u002F) - Nov 2023\n- [Creating a simple ChatGPT clone with Go](https:\u002F\u002Fsausheong.com\u002Fcreating-a-simple-chatgpt-clone-with-go-c40b4bec9267?sk=53a2bcf4ce3b0cfae1a4c26897c0deb0) - Aug 2023\n- [Creating a ChatGPT Clone that Runs on Your Laptop with Go](https:\u002F\u002Fsausheong.com\u002Fcreating-a-chatgpt-clone-that-runs-on-your-laptop-with-go-bf9d41f1cf88?sk=05dc67b60fdac6effb1aca84dd2d654e) - Aug 2023\n\n\n# Contributors\n\nThere is a momentum for moving the development of langchaingo to a more community effort, if you are interested in being a maintainer or you are a contributor please join our [Discord](https:\u002F\u002Fdiscord.gg\u002F8bHGKzHBkM) and let us know.\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftmc_langchaingo_readme_632c195ab419.png\" \u002F>\n\u003C\u002Fa>\n","> 🎉 **加入我们的全新官方 Discord 社区！** 与其他 LangChain Go 开发者交流、获取帮助并参与贡献：[加入 Discord](https:\u002F\u002Fdiscord.gg\u002Ft9UbBQs2rG)\n\n# 🦜️🔗 LangChain Go\n\n[![go.dev 参考](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fgo.dev-reference-007d9c?logo=go&logoColor=white&style=flat-square)](https:\u002F\u002Fpkg.go.dev\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n[![评分卡](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftmc_langchaingo_readme_2b4a70945b89.png)](https:\u002F\u002Fgoreportcard.com\u002Freport\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n[![](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002Ft9UbBQs2rG?compact=true&style=flat)](https:\u002F\u002Fdiscord.gg\u002Ft9UbBQs2rG)\n[![在 Dev Containers 中打开](https:\u002F\u002Fimg.shields.io\u002Fstatic\u002Fv1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https:\u002F\u002Fvscode.dev\u002Fredirect?url=vscode:\u002F\u002Fms-vscode-remote.remote-containers\u002FcloneInVolume?url=https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n[\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fcodespaces\u002Fbadge.svg\" title=\"在 Github Codespace 中打开\" width=\"150\" height=\"20\">](https:\u002F\u002Fcodespaces.new\u002Ftmc\u002Flangchaingo)\n\n⚡ 使用 Go 语言，通过可组合性构建大模型应用！ ⚡\n\n## 🤔 这是什么？\n\n这是 [LangChain](https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flangchain) 的 Go 语言实现。\n\n## 📖 文档\n\n- [文档网站](https:\u002F\u002Ftmc.github.io\u002Flangchaingo\u002Fdocs\u002F)\n- [API 参考](https:\u002F\u002Fpkg.go.dev\u002Fgithub.com\u002Ftmc\u002Flangchaingo)\n\n\n## 🎉 示例\n\n示例用法请参见 [.\u002Fexamples](.\u002Fexamples)。\n\n```go\npackage main\n\nimport (\n  \"context\"\n  \"fmt\"\n  \"log\"\n\n  \"github.com\u002Ftmc\u002Flangchaingo\u002Fllms\"\n  \"github.com\u002Ftmc\u002Flangchaingo\u002Fllms\u002Fopenai\"\n)\n\nfunc main() {\n  ctx := context.Background()\n  llm, err := openai.New()\n  if err != nil {\n    log.Fatal(err)\n  }\n  prompt := \"为一家生产彩色袜子的公司起一个好名字吧？\"\n  completion, err := llms.GenerateFromSinglePrompt(ctx, llm, prompt)\n  if err != nil {\n    log.Fatal(err)\n  }\n  fmt.Println(completion)\n}\n```\n\n```shell\n$ go run .\nSocktastic\n```\n\n# 资源\n\n加入 Discord 服务器以获得支持和讨论：[加入 Discord](https:\u002F\u002Fdiscord.gg\u002F8bHGKzHBkM)\n\n以下是一些关于使用 LangChain Go 的博客文章和资料链接：\n\n- [在 Go 中使用 Gemini 模型与 LangChainGo](https:\u002F\u002Feli.thegreenplace.net\u002F2024\u002Fusing-gemini-models-in-go-with-langchaingo\u002F) - 2024 年 1 月\n- [将 Ollama 与 LangChainGo 结合使用](https:\u002F\u002Feli.thegreenplace.net\u002F2023\u002Fusing-ollama-with-langchaingo\u002F) - 2023 年 11 月\n- [用 Go 创建一个简单的 ChatGPT 克隆](https:\u002F\u002Fsausheong.com\u002Fcreating-a-simple-chatgpt-clone-with-go-c40b4bec9267?sk=53a2bcf4ce3b0cfae1a4c26897c0deb0) - 2023 年 8 月\n- [用 Go 创建一个可在笔记本电脑上运行的 ChatGPT 克隆](https:\u002F\u002Fsausheong.com\u002Fcreating-a-chatgpt-clone-that-runs-on-your-laptop-with-go-bf9d41f1cf88?sk=05dc67b60fdac6effb1aca84dd2d654e) - 2023 年 8 月\n\n\n# 贡献者\n\n目前，langchaingo 的开发正朝着更加社区化的方向发展。如果您有兴趣成为维护者或贡献者，请加入我们的 [Discord](https:\u002F\u002Fdiscord.gg\u002F8bHGKzHBkM)，并告诉我们您的想法。\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftmc_langchaingo_readme_632c195ab419.png\" \u002F>\n\u003C\u002Fa>","# LangChain Go 快速上手指南\n\nLangChain Go 是著名大语言模型应用框架 LangChain 的 Go 语言实现，旨在通过组合化的方式帮助开发者快速构建基于 LLM 的应用程序。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**：Linux, macOS 或 Windows (WSL)\n*   **Go 版本**：建议安装 Go 1.21 或更高版本\n*   **依赖项**：\n    *   已配置好的 Go 模块环境 (`go mod`)\n    *   有效的 LLM API 密钥（例如 OpenAI API Key），需设置为环境变量 `OPENAI_API_KEY`\n\n## 安装步骤\n\n在项目目录中初始化 Go 模块并安装 LangChain Go 库：\n\n```bash\ngo mod init my-langchain-app\ngo get github.com\u002Ftmc\u002Flangchaingo\n```\n\n> **提示**：如果下载速度较慢，可配置国内 GOPROXY 加速：\n> ```bash\n> export GOPROXY=https:\u002F\u002Fgoproxy.cn,direct\n> ```\n\n## 基本使用\n\n以下是一个最简单的示例，展示如何使用 OpenAI 模型生成文本。\n\n1.  创建文件 `main.go` 并粘贴以下代码：\n\n```go\npackage main\n\nimport (\n  \"context\"\n  \"fmt\"\n  \"log\"\n\n  \"github.com\u002Ftmc\u002Flangchaingo\u002Fllms\"\n  \"github.com\u002Ftmc\u002Flangchaingo\u002Fllms\u002Fopenai\"\n)\n\nfunc main() {\n  ctx := context.Background()\n  llm, err := openai.New()\n  if err != nil {\n    log.Fatal(err)\n  }\n  prompt := \"What would be a good company name for a company that makes colorful socks?\"\n  completion, err := llms.GenerateFromSinglePrompt(ctx, llm, prompt)\n  if err != nil {\n    log.Fatal(err)\n  }\n  fmt.Println(completion)\n}\n```\n\n2.  设置您的 API 密钥（以 Linux\u002FmacOS 为例）：\n\n```bash\nexport OPENAI_API_KEY=\"your-api-key-here\"\n```\n\n3.  运行程序：\n\n```shell\n$ go run .\nSocktastic\n```\n\n程序将调用 LLM 并输出生成的公司名称建议。更多高级用法和示例代码请参阅项目官方 [examples](.\u002Fexamples) 目录。","某电商初创团队的后端工程师需要为 Go 语言编写的订单系统快速集成\"AI 智能客服”功能，以自动处理用户的退换货咨询。\n\n### 没有 langchaingo 时\n- **重复造轮子**：开发者需手动封装 HTTP 请求来调用大模型 API，反复处理鉴权、超时重试和流式响应解析等底层细节。\n- **上下文管理混乱**：为了记住多轮对话历史，必须自行设计复杂的数据结构来拼接 Prompt，极易超出令牌限制或丢失关键信息。\n- **扩展成本高昂**：若想从 OpenAI 切换到本地部署的 Ollama 模型，需要重写大量网络交互代码，无法实现平滑迁移。\n- **功能开发缓慢**：实现“检索增强生成（RAG）”以便 AI 读取公司售后文档时，需从零构建向量检索与文本分块逻辑，耗时数周。\n\n### 使用 langchaingo 后\n- **开箱即用**：直接调用 `openai.New()` 或 `ollama.New()` 即可实例化模型，内置处理了所有复杂的 API 交互与错误重试机制。\n- **链式编排便捷**：利用内置的 `ConversationBuffer` 组件，仅需几行代码即可自动维护多轮对话记忆，确保回答连贯准确。\n- **模型无缝切换**：得益于统一的 LLM 接口抽象，更换底层模型只需修改初始化参数，核心业务逻辑无需任何变动。\n- **高级功能模块化**：通过组合现有的 Chains 和 Retrievers 组件，一天内即可搭建出能读取内部知识库的专业 RAG 客服系统。\n\nlangchaingo 让 Go 开发者能以原生般的流畅体验，将原本需要数周的大模型应用开发周期缩短至几天，真正实现了用 Go 高效构建 AI 应用。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ftmc_langchaingo_bf0fef95.png","tmc","Travis Cline","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Ftmc_c60f543f.jpg","🚀 ",null,"SF","travis.cline@gmail.com","traviscline","https:\u002F\u002Fgithub.com\u002Ftmc",[85,89,93],{"name":86,"color":87,"percentage":88},"Go","#00ADD8",99.6,{"name":90,"color":91,"percentage":92},"Shell","#89e051",0.2,{"name":94,"color":95,"percentage":92},"Makefile","#427819",8989,1070,"2026-04-04T05:10:17","MIT","Linux, macOS, Windows","未说明",{"notes":103,"python":104,"dependencies":105},"这是一个 Go 语言实现的 LangChain 库，因此不需要 Python 环境。具体运行需求取决于所调用的后端大模型服务（如 OpenAI API、本地 Ollama 等）。若连接本地模型，硬件需求由该模型决定；若调用云端 API，仅需基础网络环境。建议使用 VS Code Dev Containers 或 GitHub Codespaces 进行开发。","不适用",[106],"Go 1.20+",[14,13,15],[109,110,111,112],"ai","go","golang","langchain","2026-03-27T02:49:30.150509","2026-04-06T05:18:06.366361",[116,121,126,131,136,141],{"id":117,"question_zh":118,"answer_zh":119,"source_url":120},14484,"如何在 LangChainGo 中集成 Google Gemini Pro 模型？","目前已有针对 GoogleAI 的初始实现（使用 API 密钥认证），后续计划添加基于 GCP 认证的 VertexAI SDK 实现。需要注意的是，新的 GenAI SDK 暂时不支持嵌入（embeddings），因此嵌入功能目前仍会通过遗留的 PaLM 客户端处理，这对用户是透明的。虽然旧的 text-bison (PaLM) 模型仍受支持，但官方推荐使用 gemini-pro。","https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fissues\u002F410",{"id":122,"question_zh":123,"answer_zh":124,"source_url":125},14485,"网页抓取工具（web scraper）挂起或不返回响应怎么办？","该问题通常与底层依赖或配置有关。社区建议如果需要一个更稳定、生产级的解决方案，可以考虑使用基于 Chrome 的抓取工具替代现有的实现。维护者曾讨论过重写该工具以减少依赖或明确其仅作为示例工具的定位。如果遇到挂起，尝试调整 `WithParallelsNum`、`WithMaxDepth` 等参数可能无效，建议检查是否需引入无头浏览器（Headless Chrome）方案来解决动态渲染或反爬问题。","https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fissues\u002F1318",{"id":127,"question_zh":128,"answer_zh":129,"source_url":130},14486,"结构化输出解析器（Structured Parser）无法解析 JSON 数组时报错怎么办？","当尝试解析包含数组的 JSON（如 `{\"ids\": [number]}`）时，默认解析器可能会报错 `cannot unmarshal array into Go value of type string`。解决方案是将解析器的数据类型改为 `map[string]any`，或者参考 LangChain Python 版本中的 `PydanticOutputParser` 思路，利用 Go 的结构体标签（struct tagging）来定义期望的输出格式，从而更好地处理复杂数据结构。","https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fissues\u002F171",{"id":132,"question_zh":133,"answer_zh":134,"source_url":135},14487,"如何为 LangChainGo 添加 Mistral AI 平台的支持？","Mistral API 的实现方式与 OpenAI 非常相似。开发者可以参考现有的 OpenAI 实现代码，通过添加类似的标志位（flag）来支持 Mistral。社区成员已经开始了相关工作，基本结构已就绪，可以通过复用 OpenAI 客户端的逻辑并适配 Mistral 的 API 端点和认证方式来实现集成。","https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fissues\u002F486",{"id":137,"question_zh":138,"answer_zh":139,"source_url":140},14488,"在使用 Azure OpenAI Chat LLM 时，如何正确配置嵌入模型（Embedder）？","由于 PR #362 移除了部分旧的嵌入器，导致无法直接将 `openai.NewChat` 创建的 LLM 客户端传递给某些嵌入器初始化方法。解决此问题的方法是确保使用专门适配 Chat LLM 的嵌入器（如 `openAIChatEmbedder`），并在初始化 Vector Store 时正确传入该嵌入器实例。如果使用的是 Azure OpenAI，需确保在创建 Chat LLM 时正确设置了 `APITypeAzure`、`BaseURL` 以及专门的 `EmbeddingModel` 参数。","https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fissues\u002F372",{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},14489,"LangChainGo 项目推荐使用什么技术栈来构建文档站点？","虽然 Python 版 LangChain 使用 Sphinx，TypeScript 版使用 Docusaurus，但考虑到 LangChainGo 是 Go 语言项目，社区倾向于使用基于 Go 的工具链以保持技术栈一致性。Hugo 是一个被强烈推荐的选项，因为它速度快且原生支持 Go。当然，如果为了追求与官方文档风格高度一致，Docusaurus 也是一个可行的选择，尽管它基于 Node.js。","https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fissues\u002F21",[147,152,157,162,167,172,177,182,187,192,197,202,207,212,217,222,227,232,237,242],{"id":148,"version":149,"summary_zh":150,"released_at":151},81409,"v0.1.14","## 变更内容\n* anthropic：在人类消息中添加对多内容部分和图片内容的支持。由 @Neofox 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1141 中实现。\n* llms：为推理模型实现 StreamingReasoningFunc。由 @douglarek 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1125 中实现。\n* ci：将 linting 工具 golangci-lint 迁移到 v2.0.2。由 @mdelapenya 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1217 中实现。\n* vectorstore：添加 Google AlloyDB 和 Cloud SQL 的接口。由 @averikitsch 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1204 中实现。\n* memory：添加 Google AlloyDB 和 Cloud SQL 的接口。由 @averikitsch 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1205 中实现。\n* llms\u002Fopenai：在 TestMultiContentImage 中将已弃用的 gpt-4-vision-preview 替换为 gpt-4o。由 @karsharma10 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1238 中实现。\n* googleai：修复 Gemini 仅会忽略除第一个工具之外所有工具的问题。由 @jpoz 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1244 中实现。\n* vectorstores：添加 Bedrock Knowledge Bases 向量存储支持。由 @lucaronca 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1200 中实现。\n* bedrock：改进从模型 ID 中提取 Bedrock 提供商的方式。由 @lucaronca 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1135 中实现。\n* duckduckgo：提供更具描述性的错误信息。由 @lmorg 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1260 中实现。\n* examples：修复示例并完成 linting 升级。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1288 中实现。\n* httprr：添加 httprr 包。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1296 中实现。\n* all：扩大 httprr 的覆盖范围，更新依赖项，整理 go.mod 文件，并升级到 1.23。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1299 中实现。\n* googleai：在其 PaLM 客户端中将 `textembedding-gecko` 替换为 `text-embedding-005`。由 @alanrichman 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1292 中实现。\n* all：扩展测试覆盖率。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1312 中实现。\n* docs：重构文档站点的内容和结构。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1311 中实现。\n* docs：后续处理并修复搜索索引问题。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1313 中实现。\n* docs：修复拼写错误，指出 openAI 和 anthropic 应使用 withToken 而不是 wi…。由 @BowieHe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1314 中实现。\n* vectorstores：为 Azure AI Search 添加 WithEndpoint 选项。由 @thecoons 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1308 中实现。\n* deps：更新依赖项。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1319 中实现。\n* bedrockclient：添加对全新 Amazon Nova 模型的支持。由 @oryanmoshe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1083 中实现。\n* ollama：修复路径并调整新的负载要求。由 @iButcat 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1317 中实现。\n* agents：在 executor.go 中添加更健壮的响应处理机制。由 @xiazemin 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1316 中实现。\n* prompts：改进提示模板并扩充文档。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1348 中实现。\n* ollama：添加对推理模式（think 参数）的支持。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpu","2025-10-20T05:25:26",{"id":153,"version":154,"summary_zh":155,"released_at":156},81410,"v0.1.14-pre.3","## 预发布 v0.1.14-pre.3\n\n### 亮点\n- 测试套件：100% 通过率（87\u002F87 个包）\n- 使用 gzip 压缩测试录制文件\n- 修复了 HTTP 录制的兼容性问题\n- 移除了已弃用的 VertexAI PaLM 支持\n- 更新了向量存储的测试录制文件\n\n### 变更内容\n* 测试：提升测试稳定性并更新提供商 API，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1377 中完成\n* 测试：提高测试覆盖率，并通过 gzip 压缩优化存储，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1378 中完成\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.14-pre.2...v0.1.14-pre.3","2025-08-23T17:13:57",{"id":158,"version":159,"summary_zh":160,"released_at":161},81411,"v0.1.14-pre.2","## 变更内容\n* llms\u002Fopenai：通过 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1366 中改进流式响应中的 SSE 注释处理\n* openai：添加对 max_tokens 的支持，由 @kid-icarus 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1359 中实现\n* openaiclient：在创建嵌入时添加 dimensions 选项，由 @JLugagne 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1338 中完成\n* llms\u002Fanthropic：允许使用工具的流式响应，由 @jpoz 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1343 中实现\n* llms\u002Fbedrock：添加 modelProvider 选项及 Nova 模型支持，由 @dreamans 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1346 中完成\n* 修复：确保 googleai 模式转换可处理嵌套对象和数组，由 @kid-icarus 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1326 中完成\n* 修复：为 openai 的 `GenerateContent` 函数添加 `ReasoningContent` 字段……由 @topjohncian 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1324 中完成\n* bedrock：为 Anthropic Claude 模型添加工具调用支持，由 @manishiitg 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1327 中实现\n* llms\u002Fbedrock：完成 Anthropic 工具调用支持，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1367 中完成\n* httprr：提升测试录制稳定性并添加实用工具，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1368 中实现\n* 还原“openai：添加对 max_tokens 的支持 (#1359)”更改，由 @kid-icarus 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1369 中完成\n* mongovector：修复未分词过滤器测试中的预期错误字符串，由 @matthewdale 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1331 中完成\n* googleai：修复用户提供的嵌入模型被默认模型覆盖的问题，由 @ancalabrese 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1307 中解决\n* openai：添加具有向后兼容性的 robust max_tokens 支持，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1371 中完成\n\n## 新贡献者\n* @kid-icarus 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1359 中做出了首次贡献\n* @JLugagne 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1338 中做出了首次贡献\n* @dreamans 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1346 中做出了首次贡献\n* @topjohncian 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1324 中做出了首次贡献\n* @manishiitg 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1327 中做出了首次贡献\n* @matthewdale 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1331 中做出了首次贡献\n* @ancalabrese 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1307 中做出了首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.14-pre.1...v0.1.14-pre.2","2025-08-19T17:37:46",{"id":163,"version":164,"summary_zh":165,"released_at":166},81412,"v0.1.14-pre.1","## 变更内容\n* anthropic：在人类消息中添加对多内容部分和图片内容的支持。由 @Neofox 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1141 中实现。\n* llms：为推理模型实现 StreamingReasoningFunc。由 @douglarek 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1125 中实现。\n* vectorstore：添加 Google AlloyDB 和 Cloud SQL 的接口。由 @averikitsch 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1204 中实现。\n* memory：添加 Google AlloyDB 和 Cloud SQL 的接口。由 @averikitsch 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1205 中实现。\n* llms\u002Fopenai：在 TestMultiContentImage 中将已弃用的 gpt-4-vision-preview 替换为 gpt-4o。由 @karsharma10 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1238 中实现。\n* googleai：修复 gemini 会忽略除第一个工具之外所有工具的问题。由 @jpoz 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1244 中修复。\n* vectorstores：添加 Bedrock Knowledge Bases 向量存储支持。由 @lucaronca 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1200 中实现。\n* duckduckgo：提供描述性错误信息。由 @lmorg 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1260 中实现。\n* httprr：添加 httprr 包。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1296 中实现。\n* all：扩大 httprr 的覆盖范围，更新依赖项，整理 go.mod 文件，并升级到 1.23。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1299 中完成。\n* googleai：在其 PaLM 客户端中将 `textembedding-gecko` 替换为 `text-embedding-005`。由 @alanrichman 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1292 中实现。\n* all：扩展测试覆盖率。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1312 中完成。\n* docs：重构文档站点的内容和结构。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1311 中完成。\n* docs：后续工作并修复搜索索引问题。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1313 中完成。\n* docs：修复拼写错误，指出 openAI 和 anthropic 使用 withToken 而不是 wi…。由 @BowieHe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1314 中完成。\n* vectorstores：为 Azure AI Search 添加 WithEndpoint 选项。由 @thecoons 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1308 中实现。\n* deps：更新依赖项。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1319 中完成。\n* bedrockclient：添加对新 Amazon Nova 模型的支持。由 @oryanmoshe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1083 中实现。\n* ollama：修复路径问题并调整新的负载要求。由 @iButcat 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1317 中完成。\n* agents：在 executor.go 中添加更健壮的响应处理机制。由 @xiazemin 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1316 中实现。\n* prompts：改进提示模板并扩充文档。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1348 中完成。\n* ollama：添加对推理模式（think 参数）的支持。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1349 中实现。\n* ollama：为 think 参数添加 httprr 测试记录。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1351 中完成。\n* llms\u002Fopenai：添加 OpenRouter 支持，并修复流式传输问题。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1350 中实现。\n* deps：将 Go 版本更新至 1.23.8，工具链更新至 1.24.6。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1352 中完成。\n* examples：更新","2025-08-16T18:55:17",{"id":168,"version":169,"summary_zh":170,"released_at":171},81413,"v0.1.14-pre.0","## 变更内容\n* anthropic：在人类消息中添加对多内容部分和图片内容的支持。由 @Neofox 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1141 中实现。\n* llms：为推理模型实现 StreamingReasoningFunc。由 @douglarek 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1125 中实现。\n* vectorstore：添加 Google AlloyDB 和 Cloud SQL 的接口。由 @averikitsch 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1204 中实现。\n* memory：添加 Google AlloyDB 和 Cloud SQL 的接口。由 @averikitsch 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1205 中实现。\n* llms\u002Fopenai：在 TestMultiContentImage 中，将已弃用的 gpt-4-vision-preview 替换为 gpt-4o。由 @karsharma10 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1238 中实现。\n* googleai：修复 gemini 会忽略除第一个工具之外所有工具的问题。由 @jpoz 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1244 中实现。\n* vectorstores：添加 Bedrock Knowledge Bases 向量存储支持。由 @lucaronca 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1200 中实现。\n* duckduckgo：提供更具描述性的错误信息。由 @lmorg 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1260 中实现。\n* httprr：添加 httprr 包。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1296 中实现。\n* all：扩大 httprr 的覆盖范围，更新依赖项，整理 go.mod 文件，并升级到 1.23 版本。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1299 中实现。\n* googleai：在其 PaLM 客户端中，将 `textembedding-gecko` 替换为 `text-embedding-005`。由 @alanrichman 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1292 中实现。\n* all：扩展测试覆盖率。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1312 中实现。\n* docs：重构文档站点的内容和结构。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1311 中实现。\n* docs：跟进并修复搜索索引问题。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1313 中实现。\n* docs：修复拼写错误，指出 openAI 和 anthropic 应使用 withToken 而不是 wi…。由 @BowieHe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1314 中实现。\n* vectorstores：为 Azure AI Search 添加 WithEndpoint 选项。由 @thecoons 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1308 中实现。\n* deps：更新依赖项。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1319 中实现。\n* bedrockclient：添加对亚马逊 Nova 新模型的支持。由 @oryanmoshe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1083 中实现。\n* ollama：修复路径问题，并调整新负载的要求。由 @iButcat 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1317 中实现。\n* agents：在 executor.go 中添加更健壮的响应处理机制。由 @xiazemin 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1316 中实现。\n* prompts：改进提示模板并扩充文档。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1348 中实现。\n* ollama：添加对推理模式（think 参数）的支持。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1349 中实现。\n* ollama：为 think 参数添加 httprr 测试记录。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1351 中实现。\n* llms\u002Fopenai：添加 OpenRouter 支持，并修复流式传输问题。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1350 中实现。\n* deps：将 Go 版本更新至 1.23.8，工具链更新至 1.24.6。由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpu 中实现。","2025-08-08T18:11:54",{"id":173,"version":174,"summary_zh":175,"released_at":176},81414,"v0.1.13","# v0.1.13 发行说明\n\n## 亮点：MongoDB 向量存储集成\n我们很高兴地宣布，现已全面支持 MongoDB 向量存储，这是大家呼声最高的功能之一！\n* 完整的 MongoDB 向量存储实现，具备生产就绪的功能\n* 详尽的文档和示例\n* 容器化测试套件，确保可靠性\n* 升级至 mongo-go-driver v2.0.0，性能得到提升\n* 感谢 @prestonvasquez 的重大贡献！\n\n## 主要特性与改进\n* 增加了 Mistral 嵌入支持，并由 @mathiasb 提供 PGVector 示例\n* 增加了 Perplexity AI 工具集成，由 @sklinkert 贡献\n* 增加了对 OpenAI 结构化输出以及图像+文本内容的支持，由 @lifejwang11 贡献\n* 增加了用于测试的虚假 LLM 包，由 @devalexandre 贡献\n\n## 提供商更新\n### OpenAI\n* 反映了 max_token 字段的弃用\n* 在 usage 响应中增加了 completion_tokens_details\n* 为常规和流式响应都增加了推理令牌支持\n* 新增 O1-preview 示例及文档\n\n### Google AI\n* 为 Vertex 添加了系统指令支持\n* 增加了 JSONMode 和 ResponseMIMEType 支持\n* 提升了模型随机性测试的稳定性\n\n### Anthropic\n* 增加了 beta 头部支持\n* 改进了错误事件类型的处理\n\n### Mistral\n* 更新了依赖版本\n* 增加了对默认 llms.WithTools 实现的支持\n\n### DeepSeek\n* 为推理模型新增 ReasoningContent 字段，由 @semioz 贡献\n\n## 破坏性变更\n* 升级至 mongo-go-driver v2.0.0\n* 替换了示例中已弃用的 agents.Initialize\n\n## 详细变更日志\n\n### 变更内容\n* googleai：在 Vertex 中也添加了对系统指令的支持，由 @eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F930 中完成\n* googleai：对共享测试进行了一些重构，使其更能抵抗模型随机性的影响，由 @eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F936 中完成\n* googleai：更新了依赖版本，由 @eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F939 中完成\n* anthropic：增加了对 beta 头部的支持，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F967 中完成\n* anthropic：改进了对其他错误事件类型的处理，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1012 中完成\n* openai：反映了 max_token 字段的弃用，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1013 中完成\n* openai：在 usage 响应中增加了 completion_tokens_details，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1014 中完成\n* openai：将推理令牌添加到 usage 响应中，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1015 中完成\n* openai：将推理令牌添加到流式响应中，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1016 中完成\n* examples：新增 OpenAI O1-preview 示例，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1017 中完成\n* examples：改进了 O1 的 README 文件，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1020 中完成\n* examples：更新至 v0.1.13-pre.0 版本，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1021 中完成\n* llms：修复了 GenerateFromSinglePrompt 结构体中的未键字段，由 @iocron 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002F 中完成","2025-02-16T22:07:55",{"id":178,"version":179,"summary_zh":180,"released_at":181},81415,"v0.1.13-pre.1","## 变更内容\n* googleai：在 Vertex 中也添加对系统指令的支持，由 @eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F930 中实现。\n* googleai：对共享测试进行了一些重构，并使其更能应对模型的随机性，由 @eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F936 中完成。\n* googleai：更新依赖版本，由 @eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F939 中完成。\n* anthropic：添加对 beta 标头的支持，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F967 中实现。\n* anthropic：改进了对其他错误事件类型的处理，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1012 中完成。\n* openai：反映了 max_token 字段的弃用，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1013 中完成。\n* openai：在 usage 响应中添加 completion_tokens_details，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1014 中实现。\n* openai：在 usage 响应中添加 reasoning tokens，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1015 中完成。\n* openai：在流式响应中添加 reasoning tokens，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1016 中实现。\n* examples：添加 openai o1-preview 示例，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1017 中完成。\n* examples：改进 o1 的 README 文件，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1020 中完成。\n* examples：更新至 v0.1.13-pre.0，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1021 中完成。\n* llms：修复 GenerateFromSinglePrompt 结构体中的未键入字段，由 @iocron 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F926 中完成。\n* ci：升级 golangci lint 版本，由 @wangjiancn 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F928 中完成。\n* examples：添加 perplexity 完成示例，由 @sklinkert 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F977 中完成。\n* agents：优化 mrkl 提示词，由 @Alan796 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F976 中完成。\n* docs：修复 OutputParser 中缺失的 Type 方法，由 @chxru 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F972 中完成。\n* outputparser：改进 BooleanOutputParser，由 @amitaifrey 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F978 中完成。\n* outputparser：改进 DefinedOutputParser，由 @amitaifrey 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F980 中完成。\n* textsplitter：添加连接表格行的选项，由 @corani 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F981 中完成。\n* googleai：添加对 JSONMode 和 ResponseMIMEType 的支持，由 @mheck136 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F984 中完成。\n* openai：添加对聊天完成 API 发送结构化输出请求的支持，由 @takeyamakenta 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F986 中完成。\n* redisvector：修复 score threshold 选项，由 @acrmp 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1003 中完成。\n* milvus：添加 skipFlushOnWrite 选项，由 @fatedier 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F992 中完成。\n* outputparser：在结构化解析器中使用 strings.Cut，由 @anuraaga 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F997 中完成。\n* examples：替换已弃用的 agents.Initialize，由 @treywelsh 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1009 中完成。\n* bedrock：修复当流式通道关闭时出现的未检查错误，由 @lucaronca 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F998 中完成。\n* llms：添加假 pac","2025-02-05T10:38:21",{"id":183,"version":184,"summary_zh":185,"released_at":186},81416,"v0.1.13-pre.0","## 变更内容\n* googleai：@eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F930 中为 Vertex 也添加了对系统指令的支持\n* googleai：@eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F936 中对共享测试进行了一些重构，使其更能应对模型的随机性\n* googleai：@eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F939 中更新了依赖版本\n* anthropic：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F967 中添加了对 beta 标头的支持\n* anthropic：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1012 中改进了对其他错误事件类型的处理\n* openai：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1013 中反映了 max_token 字段的弃用\n* openai：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1014 中将 completion_tokens_details 添加到 usage 响应中\n* openai：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1015 中将 reasoning tokens 添加到 usage 响应中\n* openai：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1016 中将 reasoning tokens 添加到流式响应中\n* examples：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1017 中添加了 openai o1-preview 示例\n* llms：@iocron 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F926 中使 GenerateFromSinglePrompt 结构体字面量使用无键字段\n* ci：@wangjiancn 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F928 中升级了 golangci-lint 版本\n* @sklinkert 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F977 中添加了 perplexity 完成示例\n* agents：@Alan796 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F976 中优化了 mrkl 提示词\n* fix(docs)：@chxru 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F972 中修复了 OutputParser 缺少 Type 方法的问题\n* outputparser：@amitaifrey 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F978 中改进了 BooleanOutputParser\n* outputparser：@amitaifrey 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F980 中改进了 DefinedOutputParser\n* textsplitter：@corani 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F981 中添加了连接表格行的选项\n* googleai：@mheck136 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F984 中添加了对 JSONMode 和 ResponseMIMEType 的支持\n* openai：@takeyamakenta 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F986 中添加了对聊天完成 API 发送结构化输出请求的支持\n* redisvector：@acrmp 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1003 中修复了分数阈值选项的问题\n* milvus：@fatedier 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F992 中添加了 skipFlushOnWrite 选项\n* outputparser：@anuraaga 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F997 中在结构化解析器中使用 strings.Cut\n* examples：@treywelsh 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F1009 中替换了已弃用的 agents.Initialize\n* bedrock：@lucaronca 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F998 中修复了当流通道关闭时出现的未检查错误\n* llms：@devalexandre 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F935 中添加了 fake 包\n* examples：@elnoro 在 pgvector 示例的 README 中将 compose v1 替换为 compose v2","2024-09-13T05:00:35",{"id":188,"version":189,"summary_zh":190,"released_at":191},81417,"v0.1.12","## 变更内容\n* llms\u002Fgoogleai：修复 Vertex 不返回用量信息的问题，由 @wangjiancn 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F904 中完成\n* 修复：Anthropic 函数调用功能，由 @lwlee2608 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F899 中完成\n* llms\u002Fanthropic：修复 Anthropic 模型请求中内容设置错误的问题，由 @JckHoe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F908 中完成\n* llms\u002Fgoogleai：修复工具转换错误，由 @wangjiancn 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F903 中完成\n* llms\u002Fgoogleai：修复用量统计测试和最大 token 测试，并更新依赖，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F910 中完成\n* docs\u002Fgroq：由 @devalexandre 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F907 中完成\n* llms\u002Fwatsonx：更新模块，由 @h0rv 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F902 中完成\n* 文档：修复 text_splitters mdx 代码示例未正确关闭的问题，由 @4lxprime 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F900 中完成\n* textsplitter：为 Markdown 分割器添加 WithHeadingHierarchy 选项，以在分块中保留标题层级结构，由 @iwilltry42 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F898 中完成\n* 示例：将 Watsonx 示例指向当前主分支，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F911 中完成\n* outputparser：添加 `Defined` 解析器，用于从 LLM 输出中提取结构体，由 @erictse 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F856 中完成\n* anthropic：改进 Anthropic 客户端中的流式消息处理，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F912 中完成\n* googleai：确定 Google 认证环境变量名为 GOOGLE_API_KEY，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F913 中完成\n* llms：增加默认 token 数量，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F914 中完成\n* 示例：添加示例 README 文件，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F916 中完成\n* 示例：优化顶级 README 文件，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F919 中完成\n* anthropic：美化工具调用示例，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F921 中完成\n* 示例：指向 0.1.12-pre.0 版本，由 @tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F922 中完成\n\n## 新贡献者\n* @JckHoe 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F908 中完成了首次贡献\n* @4lxprime 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F900 中完成了首次贡献\n* @iwilltry42 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F898 中完成了首次贡献\n* @erictse 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F856 中完成了首次贡献\n\n**完整变更日志**：https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.11...v0.1.12","2024-06-21T05:02:10",{"id":193,"version":194,"summary_zh":195,"released_at":196},81418,"v0.1.11","## 变更内容\n* llms：@h0rv 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F577 中添加了 watsonx\n* pgvector：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F832 中恢复了 WithConnectionURL 选项\n* examples：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F833 中更新至 v0.1.10\n* agents：@AugustDev 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F831 中向 `Agent` 接口添加了 `GetTools`\n* examples：@CrazyWr 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F834 中添加了 Redis 向量存储示例\n* llms\u002Fgoogleai：@johanbrandhorst 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F825 中实现了批量嵌入调用\n* fix：@douglarek 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F839 中改进了对类似 OpenAI 流式消息中错误的处理\n* llms\u002Fgoogleai：@eliben 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F854 中升级了 genai SDK，并修复了与新版本相关的构建问题\n* fix：@ankitraj2330 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F879 中处理了 chat_prompt_template 中的空指针异常\n* httputil：@AugustDev 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F845 中调试传输层\n* llms：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F880 中添加了改进的 YAML 和 JSON 序列化功能\n* tools：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F883 中改进了工具选择的填充和解析\n* memory：@CrazyWr 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F843 中将 MongoDB 聊天历史记录移至独立模块\n* llms：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F884 中整理了序列化代码\n* anthropic：@lwlee2608 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F882 中添加了工具\u002F函数调用支持\n* milvus_vectorstore：@CrazyWr 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F844 中实现了以 JSON 数据类型存储元数据，并支持带过滤器的搜索\n* readme：@codefromthecrypt 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F846 中为 vectorstores\u002Fchroma URL 添加了 scheme\n* llms：@wgeorgecook 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F872 中修复了 ErrIncompleteEmbeddings 消息中的拼写错误\n* googleai：@johnknott 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F865 中为 convertToolSchemaType 添加了数组类型支持\n* marita：@devalexandre 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F864 中更新了授权信息\n* fix：@zhanluxianshen 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F874 中修复了 modelToContextSize 的映射键值拼写错误\n* memory：@paul-paliychuk 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F746 中添加了 Zep Cloud 集成\n* openai：@douglarek 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F853 中在 ImageURLContent 结构体中添加了 `detail` 字段\n* weaviate：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F885 中修复了 Weaviate 相关测试\n* deps：@tmc 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F886 中清理了对 zerolog 的直接依赖\n* googleai：@wangjiancn 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F888 中修复了 googleai convertTools 中的类型错误\n* openai：@wangjiancn 在 https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F887 中启用了流式响应时可选返回使用情况数据的功能\n* llms\u002Fgoogleai：Sup","2024-06-16T21:39:49",{"id":198,"version":199,"summary_zh":200,"released_at":201},81419,"v0.1.10","## What's Changed\r\n* examples: fix openai toolcall example after refactor by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F783\r\n* googleai: implement tool support by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F794\r\n* googleai: support tool calls in googleai\u002Fvertexai by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F795\r\n* googleai: add example of tool calling by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F796\r\n* examples: update langchaingo to v0.1.9 by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F800\r\n* llms: add llama3 models to bedrock by @semioz in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F805\r\n* examples: Specify embedding model when instantiating LLM in Pinecone example code by @nikhilnarayanan623 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F816\r\n* feat: support gemini pro system prompt by @douglarek in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F814\r\n* scraper: fix concurrent scraped links map access by @vdpoora in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F813\r\n* ernie: Remove ERNIE-Bot-8K Model by @sxk10812139 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F812\r\n* llms: llms\u002Fgoogleai\u002Foption.go With methods added that was not implemented yet by @Mannetjie in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F808\r\n* openai: Add metadata fields in OpenAI calls by @lowjiansheng in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F811\r\n* llms: Add usability methods to parts types by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F818\r\n* memory: Add mongodb memory implementation by @CrazyWr in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F810\r\n* examples: Add groq completion example by @sklinkert in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F804\r\n* embeddings: Add Jina by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F809\r\n* bugfix: incorrect error return in applyClientOptions function by @0xd219b in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F807\r\n* feat: bedrock anthropic stream support by @douglarek in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F821\r\n* vectorstores\u002Fpgvector: support both pgx and pgxpool. by @joeychilson in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F802\r\n* memory: add sqlite3 backend by @mvrilo in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F798\r\n* embeddings: add voyageai embedder by @joeychilson in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F792\r\n* agent: Update openai agent tool calling (#765) by @txfsxq in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F772\r\n* llms: Maritaca AI by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F762\r\n* vectorstores: add redisvector implementation by @CrazyWr in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F777\r\n* feat: add WithKeepSeparator option for RecursiveCharacter by @zhangi in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F721\r\n* docs: re-add llamafile example by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F693\r\n* openai: add toolcalls support when streaming by @ChrisCPoirier in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F763\r\n\r\n## New Contributors\r\n* @nikhilnarayanan623 made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F816\r\n* @douglarek made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F814\r\n* @vdpoora made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F813\r\n* @Mannetjie made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F808\r\n* @lowjiansheng made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F811\r\n* @sklinkert made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F804\r\n* @0xd219b made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F807\r\n* @txfsxq made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F772\r\n* @zhangi made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F721\r\n* @ChrisCPoirier made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F763\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.9...v0.1.10\r\n","2024-05-07T05:01:42",{"id":203,"version":204,"summary_zh":205,"released_at":206},81420,"v0.1.9","## What's Changed\r\n* googleai: vertex - upgrade dep version and increase default max tokens by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F742\r\n* googleai: combine options for googleai and vertex by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F743\r\n* googleai: add safety\u002Fharm threshold settings by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F744\r\n* github: update lint workflow to newer version of Go by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F745\r\n* vectorstores\u002Fmilvus: Update testcontainer image by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F741\r\n* tools\u002Fsqldataase: update postgres image by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F740\r\n* chains: Update mysql testcontainer image by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F739\r\n* vectorstores\u002Fqdrant: Update testcontainer image  by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F737\r\n* doc: fix typo by @XiaoConstantine in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F758\r\n* examples: clarify openai-function-call-example by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F751\r\n* schema: move Chat* types to llms by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F757\r\n* examples: remove 'replace' lines in go.mod files by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F782\r\n* schema: remove leftover doc comment part by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F784\r\n* vectorstores\u002Fpinecone: update to latest v0.4.1 by @andrewyang17 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F789\r\n* llms\u002Fopenai: Fixed no response when streaming func with tools calling by @shawti in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F788\r\n* llms\u002Follama: support 'keep_alive' parameter by @CrazyWr in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F787\r\n* fix: fix example path by @LooJee in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F780\r\n* tools: serpapi api key option by @AugustDev in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F773\r\n* Fix OpenAI createChat bug by @Pramodh-G in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F759\r\n* docs: resolve rendering issue with code block in getting started docs by @schneedotdev in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F754\r\n\r\n## New Contributors\r\n* @XiaoConstantine made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F758\r\n* @andrewyang17 made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F789\r\n* @CrazyWr made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F787\r\n* @LooJee made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F780\r\n* @AugustDev made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F773\r\n* @Pramodh-G made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F759\r\n* @schneedotdev made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F754\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.8...v0.1.9","2024-04-18T21:03:37",{"id":208,"version":209,"summary_zh":210,"released_at":211},81421,"v0.1.8","## What's Changed\r\n* Improvements on agents package API by @haochunchang in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F551\r\n* llms: add caching functionality for Models by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F564\r\n* httputil: Add httputil package to provide some common helpers by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F702\r\n* examples: Use new debugging helper in example by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F703\r\n* examples: Fix up import in openai debugging example by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F704\r\n* tests: Perform env-var checking skips sooner as to speed up tests by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F706\r\n* llms\u002Fanthropic: adds full support for messages api by @joeychilson in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F707\r\n* llms\u002Fbedrock: Fixed error when using Claude3 model and giving MessageContent with images by @mashiike in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F713\r\n* readme: Include contributors by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F714\r\n* llms\u002Fcloudflare: Implement Cloudflare Workers AI LLM by @rajaiswal in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F679\r\n* add new example for OCR using Claude3's Vision feature with Bedrock by @mashiike in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F715\r\n* llms: Add mistral hosted inference llm implementation by @aannirajpatel in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F717\r\n* vectorstores\u002Fweaviate: Update testcontainer image by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F719\r\n* tooling: Update minimum go version to 1.22, update golangci-lint by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F722\r\n* openai: Render single text content parts directly by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F734\r\n* all: set explicit 1.22 version in go.mod by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F727\r\n* googleai: increase default max tokens setting by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F726\r\n* examples: Fix and tidy examples, add nvidia example by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F735\r\n* llms: Implement tool calling, including parallel tool call request support by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F709\r\n* openai:  WithEmbeddingModel option is incorrectly designating the desired model to use for embedding by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F731\r\n* llms: Add Seed option to all supporting backends  by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F732\r\n\r\n## New Contributors\r\n* @joeychilson made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F707\r\n* @mashiike made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F713\r\n* @rajaiswal made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F679\r\n* @aannirajpatel made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F717\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.7...v0.1.8","2024-03-31T23:45:46",{"id":213,"version":214,"summary_zh":215,"released_at":216},81422,"v0.1.7","## What's Changed\r\n* llms\u002Fopenai: Azure: add check for `model` parameter by @janezkenda in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F691\r\n* llms\u002Fopenai: Optionally supply ResponseFormat by @shawti in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F690\r\n\r\n## New Contributors\r\n* @janezkenda made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F691\r\n* @shawti made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F690\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.6...v0.1.7","2024-03-19T22:56:57",{"id":218,"version":219,"summary_zh":220,"released_at":221},81423,"v0.1.6","## What's Changed\r\n* feat: add new textspliter option: lenfunc by @whyiug in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F609\r\n* googleai: fix options need add default value by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F625\r\n* chains: add test with GoogleAI by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F628\r\n* chains: fix issue with overriding defaults in chainCallOption by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F632\r\n* chains: Update comments, bump example dependencies and clarify chain example by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F633\r\n* examples: Fix llm_math_chain example by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F634\r\n* chains: fix add ignore StreamingFunc by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F639\r\n* chore: Pinning chroma-go ahead of major new release by @tazarov in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F640\r\n* docs: Add huggingface documentation by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F641\r\n* agents: Fix agent stream callback by @devinyf in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F614\r\n* feat: add JSON format option to ollama by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F647\r\n* feat: run integration tests for vector databases using testcontainers-go modules by @mdelapenya in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F648\r\n* embeddings: Add Amazon Bedrock embeddings by @sansmoraxz in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F643\r\n* vectorstores: Add support for OpenAI Organization ID header in Chroma by @AshDevFr in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F646\r\n* change mrkl-prompt to python version by @devinyf in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F653\r\n* examples: Point examples to v0.1.5 by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F656\r\n* vectorstores: fix pgvector issues and add more test by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F617\r\n* googleai: return err not log.Fatal when stream get error by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F663\r\n* docs: fixup a bunch of links by @codyoss in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F659\r\n* docs: Add example about retriever by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F651\r\n* Create FUNDING.yml by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F669\r\n* docs: Add documentation for splitters by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F649\r\n* tool: sql_database generate sql-query filter redundant text by @devinyf in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F612\r\n* llms\u002Fanthropic: Implement WithBaseURL and WithHTTPClient for Anthropic LLM by @GRVYDEV in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F671\r\n* This example hangs if the JSON data is either marked as human or AI, it only works for me when marked as system by @timmattison in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F670\r\n* vectorstores\u002Fmilvus: add WithMetricType by @chenquan in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F674\r\n* chore: Chroma dependency update by @tazarov in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F676\r\n* vectorstores\u002Fmilvus: fixed the bug that the collection was created in… by @chenquan in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F675\r\n* Implementation proposal for using llamafile by @devalexandre in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F677\r\n* documentloaders: add AssemblyAI document loader by @marcusolsson in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F668\r\n* llms\u002Fbedrock: Add AWS Bedrock LLMs by @sansmoraxz in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F666\r\n\r\n## New Contributors\r\n* @tazarov made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F640\r\n* @devalexandre made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F641\r\n* @sansmoraxz made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F643\r\n* @AshDevFr made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F646\r\n* @codyoss made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F659\r\n* @GRVYDEV made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F671\r\n* @timmattison made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F670\r\n* @chenquan made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F674\r\n* @marcusolsson made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F668\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.5...v0.1.6","2024-03-19T01:33:56",{"id":223,"version":224,"summary_zh":225,"released_at":226},81424,"v0.1.5","## What's Changed\r\n* docs: Fix vertex example refs by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F595\r\n* agents: [OneShotZeroAgent] Change regex to allow multi-line inputs by @terwey in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F593\r\n* vectorstores: Added the option to specify a HNSW index for improving performance by @pieterclaerhout in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F589\r\n* callbacks: Implement logging for text types, fixes #596 by @terwey in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F597\r\n* vectorstores: fix pgvector return nothing when embedding table has ve… by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F548\r\n* agents: improve TestConversationalWithMemory testing by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F602\r\n* README: add link to new blog post about langchaingo by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F606\r\n* fix: stackoverflow caused by textsplitter by @whyiug in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F608\r\n* chroma: update chroma-go functions to pass context by @dddbliss in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F610\r\n* tools: run integration tests with testcontainers-go by @mdelapenya in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F519\r\n* llms: Remove omitempty from temperature params by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F621\r\n\r\n## New Contributors\r\n* @terwey made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F593\r\n* @dddbliss made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F610\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.4...v0.1.5","2024-03-08T01:30:18",{"id":228,"version":229,"summary_zh":230,"released_at":231},81425,"v0.1.4","## What's Changed\r\n* Add GenerationInfo to GenerateContent by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F488\r\n* Clean up GeneratePrompt -- unused code, and simplify caller by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F489\r\n* fix unmarshalling of chatmessage by @ctrlaltdel121 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F491\r\n* feature: add new gemini llm supporting new experimental interface by @mrothroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F497\r\n* Add Ollama test and remove custom prompt for chat by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F495\r\n* ollama: Clean up Ollama options by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F496\r\n* googleai: set up options and embeddings by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F498\r\n* Extend Model \u002F GenerateContent interface to support multi-content chats by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F500\r\n* Add multi-turn tests for new GenerateContent capabilities by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F501\r\n* ollama: implement Model interface with GenerateContent by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F502\r\n* Test streaming support in GenerateContent in openai and ollama by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F503\r\n* googleai: implement streaming and some generation options by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F504\r\n* Add function invocation into GenerateContent responses by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F512\r\n* googleai: fix streaming termination by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F515\r\n* Add callback handler method for GenerateContent start and end by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F514\r\n* Finalize the majority of the model\u002FLLM interface refactoring by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F521\r\n* all: clean up now unused types Generation and LLMResult by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F523\r\n* all: clean up and update comments by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F524\r\n* docs: add example to embeddings by @haochunchang in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F518\r\n* Deprecate the LLM interface by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F525\r\n* googleai: fix test comparisons to use case-insensitive regexps by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F528\r\n* googleai: add more model parameters and update comments by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F529\r\n* googleai: move downloadImageData to separate file by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F530\r\n* Link to LangChain Python (deserves credit) by @carsonkahn-external in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F509\r\n* vectorstores: Weaviate make additional fields configurable by @jvgrootveld in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F522\r\n* ollama: add WithHttpClient option by @elnoro in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F505\r\n* googleai: propagate more options and add test by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F532\r\n* llms: configure multiple response candidates for models that support them by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F533\r\n* vectorstores: added pgvector example by @elnoro in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F534\r\n* weaviate: add option to deduplicate documents while adding by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F527\r\n* weaviate: honor vectorstores.WithEmbedder by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F526\r\n* vectorstores: pgvector add option WithConn by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F499\r\n* memory: fix cutMessages in ConversationWindowBuffer by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F506\r\n* textsplitter: render code blocks and reference links by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F493\r\n* templates: Add f-string based templating implementation by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F479\r\n* agents: add openai functions agent by @lujingxuansc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F459\r\n* bug fix: openai_functions_agent not compatible with the new llms.Model interface by @DevinYF in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F536\r\n* llms: rename convenience function to GenerateFromSinglePrompt by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F537\r\n* googleai: test GenerateFromSinglePrompt convenience function by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F538\r\n* docs: add pgvector page by @elnoro in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F535\r\n* googleai: add initial Vertex (GCP) implementation of Model by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F540\r\n* googleai: move the PaLM provider into googleai by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F541\r\n* embeddings: add cybertron local embeddings by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F531\r\n* googleai: add embeddings to vertex by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F546\r\n* googleai: refactor to better separate generate","2024-01-31T18:55:16",{"id":233,"version":234,"summary_zh":235,"released_at":236},81426,"v0.1.3","## What's Changed\r\n* prompts: move prompts to embedded text files by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F451\r\n* vectorstores: Add ids to the return when adding documents in any vectorstore by @jaylalakiya in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F448\r\n* Skip tests that are currently failing (#415) by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F466\r\n* Refactor LanguageModel interface away by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F468\r\n* templates: Fix up gonja\u002Fjinja2 handling by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F469\r\n* vectorstores: Add opensearch by @ThomasP1988 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F464\r\n* Run go.mod tidy to make IDE happy by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F470\r\n* vectorstores: Add azureaisearch by @ThomasP1988 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F462\r\n* textsplitter: handle singular markdown tokens in markdown_splitter by @corani in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F467\r\n* Remove duplicated and unused LLMResult type from schema by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F472\r\n* Remove unused schema types by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F473\r\n* embeddings: Fix issue caused by new implementation of BatchTexts function by @jaylalakiya in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F475\r\n* GenerateContent - initial experimental API with OpenAI implementation by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F480\r\n* Docs: fix jinja typo by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F478\r\n* Fix: Add error handle for Chat Generate by @NileZhou in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F481\r\n* support agent finish callback by @h3l in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F476\r\n* Clear out GetNumTokens by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F483\r\n* Remove use of GetNumToken from example (followup on #483) by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F484\r\n* chore: bump chroma-go to latest version by @bjwswang in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F485\r\n\r\n## New Contributors\r\n* @ThomasP1988 made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F464\r\n* @corani made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F467\r\n* @NileZhou made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F481\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.2...v0.1.3","2024-01-04T04:21:40",{"id":238,"version":239,"summary_zh":240,"released_at":241},81427,"v0.1.2","## What's Changed\r\n* embeddings: Fix BatchTexts function by @jaylalakiya in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F453\r\n* vectorstores: fix chroma not return score from SimilaritySearch by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F449\r\n* Feat: use chains callback as streaming func by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F447\r\n* fix: avoid panic when call openai.NewChat() and openai.New() by @h3l in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F460\r\n* support callback handler to llm chain by @h3l in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F461\r\n* add StopReason field in Generation struct. by @me020523 in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F458\r\n* feat: callbacks.Handler support handle error by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F457\r\n* vectorstores: fix weaviate not return score from SimilaritySearch by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F454\r\n* Feat: support render prompt template with jinjia2 by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F450\r\n* memory: add ConversationWindowBuffer by @Abirdcfly in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F411\r\n* feat: support combine multi callbacks by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F446\r\n\r\n## New Contributors\r\n* @jaylalakiya made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F453\r\n* @h3l made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F460\r\n* @me020523 made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F458\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.1...v0.1.2","2023-12-29T01:00:42",{"id":243,"version":244,"summary_zh":245,"released_at":246},81428,"v0.1.1","Updates dependencies, adds some pgvector improvements, test improvements.\r\n\r\n## What's Changed\r\n* Clean up comments in chat_message_history by @eliben in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F413\r\n* test: fix api chain test error (#414) by @byebyebruce in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F434\r\n* pgvector: support postgres schema by @Tecnologer in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F439\r\n* pgvector: Fix DropTable Function by @mehulmshah in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F441\r\n* fix: remove suffix slash from openai base url by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F436\r\n* feat: use WithCallback to set openai callback option by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F438\r\n* feat: read OPENAI_API_BASE env to compatible with langchain by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F437\r\n* Docs: fix comment typo by @chyroc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F442\r\n* deps: Update x\u002Fcrypto by @tmc in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F444\r\n\r\n## New Contributors\r\n* @Tecnologer made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F439\r\n* @mehulmshah made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F441\r\n* @chyroc made their first contribution in https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fpull\u002F436\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Ftmc\u002Flangchaingo\u002Fcompare\u002Fv0.1.0...v0.1.1","2023-12-20T21:35:44"]