[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9576":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":16,"starSnapshotCount":16,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},9576,"haystack","deepset-ai\u002Fhaystack","deepset-ai","Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","https:\u002F\u002Fhaystack.deepset.ai",null,"MDX",25534,2841,162,85,0,17,75,363,73,45,"Apache License 2.0",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"agent","agents","ai","gemini","generative-ai","gpt-4","information-retrieval","large-language-models","llm","machine-learning","nlp","orchestration","python","pytorch","question-answering","rag","retrieval-augmented-generation","semantic-search","summarization","transformers","2026-06-12 02:02:09","\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fhaystack.deepset.ai\u002F\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fdeepset-ai\u002Fhaystack\u002Fmain\u002Fimages\u002Fbanner.png\" alt=\"Blue banner with the Haystack logo and the text ‘haystack by deepset – The Open Source AI Framework for Production Ready RAG & Agents’ surrounded by abstract icons representing search, documents, agents, pipelines, and cloud systems.\">\u003C\u002Fa>\n\n|         |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |\n| ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| CI\u002FCD   | [![Tests](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Factions\u002Fworkflows\u002Ftests.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Factions\u002Fworkflows\u002Ftests.yml) [![types - Mypy](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ftypes-Mypy-blue.svg)](https:\u002F\u002Fgithub.com\u002Fpython\u002Fmypy) [![Coverage badge](https:\u002F\u002Fraw.githubusercontent.com\u002Fdeepset-ai\u002Fhaystack\u002Fpython-coverage-comment-action-data\u002Fbadge.svg)](https:\u002F\u002Fhtmlpreview.github.io\u002F?https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Fblob\u002Fpython-coverage-comment-action-data\u002Fhtmlcov\u002Findex.html) [![Ruff](https:\u002F\u002Fimg.shields.io\u002Fendpoint?url=https:\u002F\u002Fraw.githubusercontent.com\u002Fastral-sh\u002Fruff\u002Fmain\u002Fassets\u002Fbadge\u002Fv2.json)](https:\u002F\u002Fgithub.com\u002Fastral-sh\u002Fruff) |\n| Docs    | [![Website](https:\u002F\u002Fimg.shields.io\u002Fwebsite?label=documentation&up_message=online&url=https%3A%2F%2Fdocs.haystack.deepset.ai)](https:\u002F\u002Fdocs.haystack.deepset.ai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |\n| Package | [![PyPI](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fhaystack-ai)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fhaystack-ai\u002F) ![PyPI - Downloads](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fdm\u002Fhaystack-ai?color=blue&logo=pypi&logoColor=gold) ![PyPI - Python Version](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Fhaystack-ai?logo=python&logoColor=gold) [![Conda Version](https:\u002F\u002Fimg.shields.io\u002Fconda\u002Fvn\u002Fconda-forge\u002Fhaystack-ai.svg)](https:\u002F\u002Fanaconda.org\u002Fconda-forge\u002Fhaystack-ai) [![GitHub](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fdeepset-ai\u002Fhaystack?color=blue)](LICENSE) [![License Compliance](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Factions\u002Fworkflows\u002Flicense_compliance.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Factions\u002Fworkflows\u002Flicense_compliance.yml) |\n| Meta    | [![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F993534733298450452?logo=discord)](https:\u002F\u002Fdiscord.com\u002Finvite\u002FqZxjM4bAHU) [![Twitter Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002Fhaystack_ai)](https:\u002F\u002Ftwitter.com\u002Fhaystack_ai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n\u003C\u002Fdiv>\n\n[Haystack](https:\u002F\u002Fhaystack.deepset.ai\u002F) is an open-source AI orchestration framework for building production-ready LLM applications in Python.\n\nDesign modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Build scalable RAG systems, multimodal applications, semantic search, question answering, and autonomous agents, all in a transparent architecture that lets you experiment, customize deeply, and deploy with confidence.\n\n## Table of Contents\n\n- [Installation](#installation)\n- [Documentation](#documentation)\n- [Features](#features)\n- [Haystack Enterprise: Support & Platform](#haystack-enterprise-support--platform)\n- [Telemetry](#telemetry)\n- [🖖 Community](#-community)\n- [Contributing to Haystack](#contributing-to-haystack)\n- [Organizations using Haystack](#organizations-using-haystack)\n\n\n## Installation\n\nThe simplest way to get Haystack is via pip:\n\n```sh\npip install haystack-ai\n```\n\nInstall nightly pre-releases to try the newest features:\n```sh\npip install --pre haystack-ai\n```\n\nHaystack supports multiple installation methods, including Docker images. For a comprehensive guide, please refer\nto the [documentation](https:\u002F\u002Fdocs.haystack.deepset.ai\u002Fdocs\u002Finstallation).\n\n## Documentation\n\nIf you're new to the project, check out [\"What is Haystack?\"](https:\u002F\u002Fhaystack.deepset.ai\u002Foverview\u002Fintro) then go\nthrough the [\"Get Started Guide\"](https:\u002F\u002Fhaystack.deepset.ai\u002Foverview\u002Fquick-start) and build your first LLM application\nin a matter of minutes. Keep learning with the [tutorials](https:\u002F\u002Fhaystack.deepset.ai\u002Ftutorials). For more advanced\nuse cases, or just to get some inspiration, you can browse our Haystack recipes in the\n[Cookbook](https:\u002F\u002Fhaystack.deepset.ai\u002Fcookbook).\n\nAt any given point, hit the [documentation](https:\u002F\u002Fdocs.haystack.deepset.ai\u002Fdocs\u002Fintro) to learn more about Haystack, what it can do for you, and the technology behind.\n\n## Features\n\n**Built for context engineering**  \nDesign flexible systems with explicit control over how information is retrieved, ranked, filtered, combined, structured, and routed before it reaches the model. Define pipelines and agent workflows where retrieval, memory, tools, and generation are transparent and traceable.\n\n**Model- and vendor-agnostic**  \nIntegrate with OpenAI, Mistral, Anthropic, Cohere, Hugging Face, Azure OpenAI, AWS Bedrock, local models, and many others. Swap models or infrastructure components without rewriting your system.\n\n**Modular and customizable**  \nUse built-in components for retrieval, indexing, tool calling, memory, and evaluation, or create your own. Add loops, branches, and conditional logic to precisely control how context moves through your pipelines and agent workflows.\n\n**Extensible ecosystem**  \nBuild and share custom components through a consistent interface that makes it easy for the community and third parties to extend Haystack and contribute to an open ecosystem.\n\n> [!TIP]\n>\n> Would you like to deploy and serve Haystack pipelines as **REST APIs** or **MCP servers**? [Hayhooks](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhayhooks) provides a simple way for you to wrap pipelines and agents with custom logic and expose them through HTTP endpoints or MCP. It also supports OpenAI-compatible chat completion endpoints and works with chat UIs like [open-webui](https:\u002F\u002Fopenwebui.com\u002F).\n\n## Haystack Enterprise: Support & Platform\n\nGet expert support from the Haystack team, build faster with enterprise-grade templates, and scale securely with deployment guides for cloud and on-prem environments with **Haystack Enterprise Starter**. Read more about it in the [announcement post](https:\u002F\u002Fhaystack.deepset.ai\u002Fblog\u002Fannouncing-haystack-enterprise).\n\n👉 [Get Haystack Enterprise Starter](https:\u002F\u002Fwww.deepset.ai\u002Fproducts-and-services\u002Fhaystack-enterprise-starter?utm_source=github.com&utm_medium=referral&utm_campaign=haystack_enterprise)\n\nNeed a managed production setup for Haystack? The **Haystack Enterprise Platform** helps you build, test, deploy and operate Haystack pipelines with built-in observability, collaboration, governance, and access controls. It’s available as a managed cloud service or as a self-hosted solution.\n\n👉 Learn more about [Haystack Enterprise Platform](https:\u002F\u002Fwww.deepset.ai\u002Fproducts-and-services\u002Fhaystack-enterprise-platform?utm_campaign=developer-relations&utm_source=haystack&utm_medium=readme) or [try it free](https:\u002F\u002Fwww.deepset.ai\u002Fhaystack-enterprise-platform-trial?utm_campaign=developer-relations&utm_source=haystack&utm_medium=readme)\n\n## Telemetry\n\nHaystack collects **anonymous** usage statistics of pipeline components. We receive an event every time these components are initialized. This way, we know which components are most relevant to our community.\n\nRead more about telemetry in Haystack or how you can opt out in [Haystack docs](https:\u002F\u002Fdocs.haystack.deepset.ai\u002Fdocs\u002Ftelemetry).\n\n## 🖖 Community\n\nIf you have a feature request or a bug report, feel free to open an [issue in GitHub](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Fissues). We regularly check these, so you can expect a quick response. If you'd like to discuss a topic or get more general advice on how to make Haystack work for your project, you can start a thread in [Github Discussions](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Fdiscussions) or our [Discord channel](https:\u002F\u002Fdiscord.com\u002Finvite\u002FVBpFzsgRVF). We also check [𝕏 (Twitter)](https:\u002F\u002Ftwitter.com\u002Fhaystack_ai) and [Stack Overflow](https:\u002F\u002Fstackoverflow.com\u002Fquestions\u002Ftagged\u002Fhaystack).\n\n## Contributing to Haystack\n\nWe are very open to the community's contributions - be it a quick fix of a typo, or a completely new feature! You don't need to be a Haystack expert to provide meaningful improvements. To learn how to get started, check out our [Contributor Guidelines](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Fblob\u002Fmain\u002FCONTRIBUTING.md) first.\n\nThere are several ways you can contribute to Haystack:\n- Contribute to the main Haystack project\n- Contribute an integration on [haystack-core-integrations](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack-core-integrations)\n- Contribute to the documentation in [haystack\u002Fdocs-website](https:\u002F\u002Fgithub.com\u002Fdeepset-ai\u002Fhaystack\u002Ftree\u002Fmain\u002Fdocs-website)\n\n> [!TIP]\n>👉 **[Check out the full list of issues that are open to contributions](https:\u002F\u002Fgithub.com\u002Forgs\u002Fdeepset-ai\u002Fprojects\u002F14)**\n\n## Organizations using Haystack\n\nHaystack is used by thousands of teams building production AI systems across industries, including:\n\n- **Technology & AI Infrastructure**: [Apple](https:\u002F\u002Fwww.apple.com\u002F), [Meta](https:\u002F\u002Fwww.meta.com\u002Fabout), [Databricks](https:\u002F\u002Fwww.databricks.com\u002F), [NVIDIA](https:\u002F\u002Fdeveloper.nvidia.com\u002Fblog\u002Freducing-development-time-for-intelligent-virtual-assistants-in-contact-centers\u002F), [Intel](https:\u002F\u002Fgithub.com\u002Fintel\u002Fopen-domain-question-and-answer#readme)\n- **Public Sector AI Initiatives**: [European Commission](https:\u002F\u002Fcommission.europa.eu\u002Findex_en), [German Federal Ministry of Research, Technology, and Space (BMFTR)](https:\u002F\u002Fwww.deepset.ai\u002Fcase-studies\u002Fgerman-federal-ministry-research-technology-space-bmftr), [PD, Baden-Württemberg State](https:\u002F\u002Fwww.pd-g.de\u002F)\n- **Enterprise & Industrial AI Applications**: [Airbus](https:\u002F\u002Fwww.deepset.ai\u002Fcase-studies\u002Fairbus), [Lufthansa Industry Solutions](https:\u002F\u002Fhaystack.deepset.ai\u002Fblog\u002Flufthansa-user-story), [Infineon](https:\u002F\u002Fwww.infineon.com\u002F), [LEGO](https:\u002F\u002Fgithub.com\u002Flarsbaunwall\u002Fbricky#readme), [Comcast](https:\u002F\u002Farxiv.org\u002Fhtml\u002F2405.00801v2), [Accenture](https:\u002F\u002Fwww.accenture.com\u002F), [TELUS Agriculture & Consumer Goods](https:\u002F\u002Fwww.telus.com\u002Fagcg\u002Fen)\n- **Knowledge & Content Platforms**: [Netflix](https:\u002F\u002Fnetflix.com), [ZEIT Online](https:\u002F\u002Fwww.deepset.ai\u002Fcase-studies\u002Fzeit-online), [Rakuten](https:\u002F\u002Fwww.rakuten.com\u002F), [Oxford University Press](https:\u002F\u002Fcorp.oup.com\u002F), [Manz](https:\u002F\u002Fwww.deepset.ai\u002Fcase-studies\u002Fmanz), [YPulse](https:\u002F\u002Fwww.deepset.ai\u002Fcase-studies\u002Fypulse)\n\n\nAre you also using Haystack? Open a PR or [tell us your story](https:\u002F\u002Fforms.gle\u002FMm3G1aEST3GAH2rn8)\n","Haystack 是一个开源的AI编排框架，用于构建具备上下文理解能力、可投入生产的大型语言模型应用。它支持设计模块化的管道和代理工作流，提供对检索、路由、记忆和生成的显式控制，适用于开发可扩展的代理、检索增强生成（RAG）、多模态应用、语义搜索以及对话系统等场景。基于Python和PyTorch技术栈，Haystack 为开发者提供了强大的工具集来整合最新的NLP研究成果于实际产品中，特别适合需要高性能信息检索与处理的企业级解决方案。",2,"2026-06-11 03:23:29","top_topic"]