[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9832":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":18,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":33,"readmeContent":34,"aiSummary":35,"trendingCount":16,"starSnapshotCount":16,"syncStatus":36,"lastSyncTime":37,"discoverSource":38},9832,"morphik-core","morphik-org\u002Fmorphik-core","morphik-org","The most accurate document search and store for building AI apps","https:\u002F\u002Fmorphik.ai\u002Fdocs",null,"Python",3609,307,17,13,0,1,5,19,65.87,"Other",false,"main",[25,26,27,28,29,30,31,32],"artificial-intelligence","cache-augmented-generation","colpali","database","litellm","multimodal","rag","rules-based-ingestion","2026-06-12 04:00:47","\u003Cp align=\"center\">\n  \u003Cimg alt=\"Morphik Logo\" src=\"assets\u002Fmorphik_logo.png\">\n\u003C\u002Fp>\n\u003Cp align=\"center\">\n  \u003Ca href='http:\u002F\u002Fmakeapullrequest.com'>\u003Cimg alt='PRs Welcome' src='https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg?style=shields'\u002F>\u003C\u002Fa>\n  \u003Cimg alt=\"GitHub commit activity\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcommit-activity\u002Fm\u002Fmorphik-org\u002Fmorphik-core\"\u002F>\n  \u003Cimg alt=\"GitHub closed issues\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues-closed\u002Fmorphik-org\u002Fmorphik-core\"\u002F>\n  \u003Cimg alt=\"PyPI - Downloads\" src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fdm\u002Fmorphik\">\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FBwMtv3Zaju\">\u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1336524712817332276?logo=discord&label=discord\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003C!-- add a roadmap! - \u003Ca href=\"https:\u002F\u002Fmorphik.ai\u002Froadmap\">Roadmap\u003C\u002Fa> - -->\n\u003C!-- Add a changelog! - \u003Ca href=\"https:\u002F\u002Fmorphik.ai\u002Fchangelog\">Changelog\u003C\u002Fa> -->\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fmorphik.ai\u002Fdocs\">Docs\u003C\u002Fa> - \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FBwMtv3Zaju\">Community\u003C\u002Fa> - \u003Ca href=\"https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fblogs\u002Fgpt-vs-morphik-multimodal\">Why Morphik?\u003C\u002Fa> - \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmorphik-org\u002Fmorphik-core\u002Fissues\u002Fnew?assignees=&labels=bug&template=bug_report.md\">Bug reports\u003C\u002Fa>\n\u003C\u002Fp>\n\n> **Migration Required for Existing Installations**: If you installed Morphik before June 22nd, 2025, we've optimized our authentication system for 70-80% faster query performance. Please run the migration script before launching Morphik:\n> ```bash\n> python scripts\u002Fmigrate_auth_columns_complete.py --postgres-uri \"postgresql+asyncpg:\u002F\u002Fuser:pass@host:port\u002Fdb\"\n> ```\n\n## Morphik is a AI-native toolset for visually rich documents and multimodal data\n\nWe are building the best way for developers to integrate context (however complex and nuanced) into their AI applications. We offer a treasure chest of tools to store, represent, and search (shallow, and deep) unstructured data. End-to-End.\n\n## Why?\n\nBuilding AI applications that interact with data shouldn't require duct-taping together a dozen different tools just to get relevant results to your LLM.\n\nTraditional RAG approaches that work in proof-of-concepts often fail spectacularly in production. Cobbling together separate systems for text extraction, OCR, embeddings, vector databases, and retrieval creates fragile pipelines that break under real-world load. Each component brings its own APIs, configurations, and failure modes - what starts as a simple demo becomes an unmaintainable mess at scale.\n\nEven worse, these pipelines fundamentally fail at understanding visually rich documents. Charts become meaningless text fragments. Critical diagrams lose their spatial relationships. Tables get mangled into unreadable strings. Technical specifications with mixed text and visuals? Forget about accuracy.\n\nThe result is AI applications that confidently return wrong answers because they never truly understood the documents. They miss crucial information embedded in images, misinterpret technical diagrams, and treat visual data as an afterthought. And performance? Watch your infrastructure costs explode as your LLM re-processes the same 500-page manual for every single query.\n\n## What?\n[Morphik](https:\u002F\u002Fmorphik.ai) provides developers the tools to ingest, search (deep and shallow), transform, and manage unstructured and multimodal documents. Some of our features include:\n\n- [Multimodal Search](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fconcepts\u002Fcolpali): We employ techniques such as ColPali to build search that actually *understands* the visual content of documents you provide. Search over images, PDFs, videos, and more with a single endpoint.\n- [Fast and Scalable Metadata Extraction](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fconcepts\u002Frules-processing): Extract metadata from documents - including bounding boxes, labeling, classification, and more.\n- [Integrations](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fintegrations): Integrate with existing tools and workflows. Including (but not limited to) Google Suite, Slack, and Confluence.\n\nThe best part? Morphik has a [free tier](https:\u002F\u002Fwww.morphik.ai\u002Fpricing)! Get started by signing up at [Morphik](https:\u002F\u002Fwww.morphik.ai\u002Fsignup).\n\n## Table of Contents\n- [Getting Started with Morphik](#getting-started-with-morphik-recommended)\n- [Self-hosting Morphik](#self-hosting-the-open-source-version)\n- [Using Morphik](#using-morphik)\n- [Contributing](#contributing)\n- [Open source vs paid](#License)\n\n## Getting Started with Morphik (Recommended)\n\nThe fastest and easiest way to get started with Morphik is by signing up for free at [Morphik](https:\u002F\u002Fwww.morphik.ai\u002Fsignup). We have a generous free tier and transparent, compute-usage based pricing if you're looking to ingest a lot of data.\n\n## Self-hosting Morphik\nIf you'd like to self-host Morphik, you can find the dedicated instruction [here](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fgetting-started). We offer options for direct installation and installation via docker.\n\n**Important**: Due to limited resources, we cannot provide full support for self-hosted deployments. We have an installation guide, and a [Discord community](https:\u002F\u002Fdiscord.gg\u002FBwMtv3Zaju) to help, but we can't guarantee full support.\n\n## Using Morphik\n\nOnce you've signed up for Morphik, you can get started with ingesting and searching your data right away.\n\n\n### Code (Example: Python SDK)\nFor programmers, we offer a [Python SDK](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fpython-sdk\u002Fmorphik) and a [REST API](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fapi-reference\u002Fhealth-check). Ingesting a file is as simple as:\n\n```python\nfrom morphik import Morphik\n\nmorphik = Morphik(\"\u003Cyour-morphik-uri>\")\nmorphik.ingest_file(\"path\u002Fto\u002Fyour\u002Fsuper\u002Fcomplex\u002Ffile.pdf\")\n```\n\nSimilarly, searching and querying your data is easy too:\n\n```python\nmorphik.query(\"What's the height of screw 14-A in the chair assembly instructions?\")\n```\n\n### Morphik Console\n\nYou can also interact with Morphik via the Morphik Console. This is a web-based interface that allows you to ingest, search, and query your data. You can upload files, connect to different data sources, and chat with your data all within the same place.\n\n### Model Context Protocol\n\nFinally, you can also access Morphik via MCP. Instructions are available [here](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fusing-morphik\u002Fmcp).\n\n\n## Contributing\nYou're welcome to contribute to the project! We love:\n- Bug reports via [GitHub issues](https:\u002F\u002Fgithub.com\u002Fmorphik-org\u002Fmorphik-core\u002Fissues)\n- Feature requests via [GitHub issues](https:\u002F\u002Fgithub.com\u002Fmorphik-org\u002Fmorphik-core\u002Fissues)\n- Pull requests\n\nCurrently, we're focused on improving speed, integrating with more tools, and finding the research papers that provide the most value to our users. If you have thoughts, let us know in the discord or in GitHub!\n\n## License\n\nMorphik Core is **source-available** under the [Business Source License 1.1](.\u002FLICENSE).\n\n- **Personal \u002F Indie use**: free.\n- **Commercial production use**: free if your Morphik deployment generates \u003C $2 000\u002Fmonth in gross revenue.\n  Otherwise purchase a commercial key at \u003Chttps:\u002F\u002Fmorphik.ai\u002Fpricing>.\n- **Future open source**: each code version automatically re-licenses to Apache 2.0 exactly four years after its first release.\n\nSee the full licence text for details.\n\n\n## Contributors\n\nVisit our [special thanks page](https:\u002F\u002Fmorphik.ai\u002Fdocs\u002Fspecial-thanks) dedicated to our contributors.\n","Morphik 是一个用于构建AI应用的文档搜索和存储工具，特别针对视觉丰富的文档和多模态数据进行了优化。它提供了一套完整的工具集，能够高效地存储、表示和检索非结构化数据，支持从浅层到深层的数据处理。项目采用Python语言开发，具有强大的缓存增强生成技术和基于规则的数据摄入功能，旨在解决传统RAG方法在实际生产环境中遇到的问题，如文本提取、OCR、嵌入向量数据库等组件间的复杂集成问题。Morphik适用于需要处理包含图表、技术图纸等视觉元素的复杂文档场景，为开发者提供了一个统一且高效的解决方案，以提高AI应用对上下文理解的准确性和可靠性。",2,"2026-06-11 03:24:57","top_topic"]