[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1296":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":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"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":45,"readmeContent":46,"aiSummary":47,"trendingCount":16,"starSnapshotCount":16,"syncStatus":48,"lastSyncTime":49,"discoverSource":50},1296,"quivr","QuivrHQ\u002Fquivr","QuivrHQ","Opiniated RAG for integrating GenAI in your apps 🧠   Focus on your product rather than the RAG. Easy integration in existing products with customisation!  Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.","https:\u002F\u002Fcore.quivr.com",null,"Python",39152,3726,285,7,0,5,41,1,76.6,"Other",false,"main",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"ai","api","chatbot","chatgpt","database","docker","framework","frontend","groq","html","javascript","llm","openai","postgresql","privacy","rag","react","security","typescript","vector","2026-06-12 04:00:08","# Quivr - Your Second Brain, Empowered by Generative AI\n\n\u003Cdiv align=\"center\">\n    \u003Cimg src=\".\u002Flogo.png\" alt=\"Quivr-logo\" width=\"31%\"  style=\"border-radius: 50%; padding-bottom: 20px\"\u002F>\n\u003C\u002Fdiv>\n\n[![Discord Follow](https:\u002F\u002Fdcbadge.vercel.app\u002Fapi\u002Fserver\u002FHUpRgp2HG8?style=flat)](https:\u002F\u002Fdiscord.gg\u002FHUpRgp2HG8)\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fquivrhq\u002Fquivr?style=social)](https:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fquivr)\n[![Twitter Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FStanGirard?style=social)](https:\u002F\u002Ftwitter.com\u002F_StanGirard)\n\nQuivr, helps you build your second brain, utilizes the power of GenerativeAI to be your personal assistant !\n\n## Key Features 🎯\n\n- **Opiniated RAG**: We created a RAG that is opinionated, fast and efficient so you can focus on your product\n- **LLMs**: Quivr works with any LLM, you can use it with OpenAI, Anthropic, Mistral, Gemma, etc.\n- **Any File**: Quivr works with any file, you can use it with PDF, TXT, Markdown, etc and even add your own parsers.\n- **Customize your RAG**: Quivr allows you to customize your RAG, add internet search, add tools, etc.\n- **Integrations with Megaparse**: Quivr works with [Megaparse](https:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fmegaparse), so you can ingest your files with Megaparse and use the RAG with Quivr.\n\n>We take care of the RAG so you can focus on your product. Simply install quivr-core and add it to your project. You can now ingest your files and ask questions.*\n\n**We will be improving the RAG and adding more features, stay tuned!**\n\n\nThis is the core of Quivr, the brain of Quivr.com.\n\n\u003C!-- ## Demo Highlight 🎥\n\nhttps:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fquivr\u002Fassets\u002F19614572\u002Fa6463b73-76c7-4bc0-978d-70562dca71f5 -->\n\n## Getting Started 🚀\n\nYou can find everything on the [documentation](https:\u002F\u002Fcore.quivr.com\u002F).\n\n### Prerequisites 📋\n\nEnsure you have the following installed:\n\n- Python 3.10 or newer\n\n### 30 seconds Installation 💽\n\n\n- **Step 1**: Install the package\n\n  \n\n  ```bash\n  pip install quivr-core # Check that the installation worked\n  ```\n\n\n- **Step 2**: Create a RAG with 5 lines of code\n\n  ```python\n  import tempfile\n\n  from quivr_core import Brain\n\n  if __name__ == \"__main__\":\n      with tempfile.NamedTemporaryFile(mode=\"w\", suffix=\".txt\") as temp_file:\n          temp_file.write(\"Gold is a liquid of blue-like colour.\")\n          temp_file.flush()\n\n          brain = Brain.from_files(\n              name=\"test_brain\",\n              file_paths=[temp_file.name],\n          )\n\n          answer = brain.ask(\n              \"what is gold? asnwer in french\"\n          )\n          print(\"answer:\", answer)\n  ```\n## Configuration\n\n### Workflows\n\n#### Basic RAG\n\n![](docs\u002Fdocs\u002Fworkflows\u002Fexamples\u002Fbasic_rag.excalidraw.png)\n\n\nCreating a basic RAG workflow like the one above is simple, here are the steps:\n\n\n1. Add your API Keys to your environment variables\n```python\nimport os\nos.environ[\"OPENAI_API_KEY\"] = \"myopenai_apikey\"\n\n```\nQuivr supports APIs from Anthropic, OpenAI, and Mistral. It also supports local models using Ollama.\n\n1. Create the YAML file ``basic_rag_workflow.yaml`` and copy the following content in it\n```yaml\nworkflow_config:\n  name: \"standard RAG\"\n  nodes:\n    - name: \"START\"\n      edges: [\"filter_history\"]\n\n    - name: \"filter_history\"\n      edges: [\"rewrite\"]\n\n    - name: \"rewrite\"\n      edges: [\"retrieve\"]\n\n    - name: \"retrieve\"\n      edges: [\"generate_rag\"]\n\n    - name: \"generate_rag\" # the name of the last node, from which we want to stream the answer to the user\n      edges: [\"END\"]\n\n# Maximum number of previous conversation iterations\n# to include in the context of the answer\nmax_history: 10\n\n# Reranker configuration\nreranker_config:\n  # The reranker supplier to use\n  supplier: \"cohere\"\n\n  # The model to use for the reranker for the given supplier\n  model: \"rerank-multilingual-v3.0\"\n\n  # Number of chunks returned by the reranker\n  top_n: 5\n\n# Configuration for the LLM\nllm_config:\n\n  # maximum number of tokens passed to the LLM to generate the answer\n  max_input_tokens: 4000\n\n  # temperature for the LLM\n  temperature: 0.7\n```\n\n3. Create a Brain with the default configuration\n```python\nfrom quivr_core import Brain\n\nbrain = Brain.from_files(name = \"my smart brain\",\n                        file_paths = [\".\u002Fmy_first_doc.pdf\", \".\u002Fmy_second_doc.txt\"],\n                        )\n\n```\n\n4. Launch a Chat\n```python\nbrain.print_info()\n\nfrom rich.console import Console\nfrom rich.panel import Panel\nfrom rich.prompt import Prompt\nfrom quivr_core.config import RetrievalConfig\n\nconfig_file_name = \".\u002Fbasic_rag_workflow.yaml\"\n\nretrieval_config = RetrievalConfig.from_yaml(config_file_name)\n\nconsole = Console()\nconsole.print(Panel.fit(\"Ask your brain !\", style=\"bold magenta\"))\n\nwhile True:\n    # Get user input\n    question = Prompt.ask(\"[bold cyan]Question[\u002Fbold cyan]\")\n\n    # Check if user wants to exit\n    if question.lower() == \"exit\":\n        console.print(Panel(\"Goodbye!\", style=\"bold yellow\"))\n        break\n\n    answer = brain.ask(question, retrieval_config=retrieval_config)\n    # Print the answer with typing effect\n    console.print(f\"[bold green]Quivr Assistant[\u002Fbold green]: {answer.answer}\")\n\n    console.print(\"-\" * console.width)\n\nbrain.print_info()\n```\n\n5. You are now all set up to talk with your brain and test different retrieval strategies by simply changing the configuration file!\n\n## Go further\n\nYou can go further with Quivr by adding internet search, adding tools, etc. Check the [documentation](https:\u002F\u002Fcore.quivr.com\u002F) for more information.\n\n\n## Contributors ✨\n\nThanks go to these wonderful people:\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fquivr\u002Fgraphs\u002Fcontributors\">\n\u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=quivrhq\u002Fquivr\" \u002F>\n\u003C\u002Fa>\n\n## Contribute 🤝\n\nDid you get a pull request? Open it, and we'll review it as soon as possible. Check out our project board [here](https:\u002F\u002Fgithub.com\u002Fusers\u002FStanGirard\u002Fprojects\u002F5) to see what we're currently focused on, and feel free to bring your fresh ideas to the table!\n\n- [Open Issues](https:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fquivr\u002Fissues)\n- [Open Pull Requests](https:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fquivr\u002Fpulls)\n- [Good First Issues](https:\u002F\u002Fgithub.com\u002Fquivrhq\u002Fquivr\u002Fissues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22)\n\n## Partners ❤️\n\nThis project would not be possible without the support of our partners. Thank you for your support!\n\n\n\u003Ca href=\"https:\u002F\u002Fycombinator.com\u002F\">\n    \u003Cimg src=\"https:\u002F\u002Fupload.wikimedia.org\u002Fwikipedia\u002Fcommons\u002Fthumb\u002Fb\u002Fb2\u002FY_Combinator_logo.svg\u002F1200px-Y_Combinator_logo.svg.png\" alt=\"YCombinator\" style=\"padding: 10px\" width=\"70px\">\n\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fwww.theodo.fr\u002F\">\n  \u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F332041?s=200&v=4\" alt=\"Theodo\" style=\"padding: 10px\" width=\"70px\">\n\u003C\u002Fa>\n\n## License 📄\n\nThis project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details\n","Quivr 是一个帮助构建个人第二大脑的工具，利用生成式AI作为你的私人助手。它提供了一个快速高效的RAG（Retrieval-Augmented Generation）框架，支持多种语言模型（如GPT-4、Groq、Llama等）和向量存储（如PGVector、Faiss）。用户可以轻松地将任何类型的文件（PDF、TXT、Markdown等）集成到系统中，并且能够自定义RAG以添加互联网搜索、工具等功能。Quivr 适用于需要在现有产品中快速集成智能对话或信息检索功能的开发者，尤其是那些希望专注于核心产品而非底层技术细节的团队。",2,"2026-06-11 02:42:53","top_all"]