{"id":2734,"date":"2024-05-21T17:59:47","date_gmt":"2024-05-21T09:59:47","guid":{"rendered":"https:\/\/infernews.com\/?p=2734"},"modified":"2024-05-23T18:29:45","modified_gmt":"2024-05-23T10:29:45","slug":"weaviate-verba-retrieval-augmented-generation-rag-chatbot-powered-by-weaviate","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/weaviate-verba-retrieval-augmented-generation-rag-chatbot-powered-by-weaviate\/","title":{"rendered":"Verba: \u8d85\u7c21\u6613\u672c\u6a5f RAG chatbot"},"content":{"rendered":"<div class=\"vlp-link-container vlp-layout-spotlight-clone wp-block-visual-link-preview-link\"><a href=\"https:\/\/github.com\/weaviate\/Verba\" class=\"vlp-link\" title=\"(\u82f1) \u7d50\u5408Llama3 \u505a\u767e\u5206\u767e\u7684\u672c\u6a5f RAG\" rel=\"nofollow\" target=\"_blank\"><\/a><div class=\"vlp-layout-zone-main\"><span class=\"vlp-block-0 vlp-link-title\">(\u82f1) \u7d50\u5408Llama3 \u505a\u767e\u5206\u767e\u7684\u672c\u6a5f RAG<\/span><div class=\"vlp-block-1 vlp-link-summary\">Retrieval Augmented Generation (RAG) chatbot powered by Weaviate &#8211; weaviate\/Verba<\/div><div class=\"vlp-block-2 vlp-link-image\"><img decoding=\"async\" src=\"https:\/\/opengraph.githubassets.com\/9899afb91c2b1caa7ffb3e191da4e1c62a7b201255a6e15a8f1ab9884d430c50\/weaviate\/Verba\" style=\"max-width: 1024px; max-height: 1024px\" \/><\/div><\/div><\/div>\n\n\n<p>Golden RAGtriever \u662f\u4e00\u6b3e\u958b\u6e90\u61c9\u7528\u7a0b\u5e8f\uff0c\u65e8\u5728\u70ba\u958b\u7bb1\u5373\u7528\u7684\u6aa2\u7d22\u589e\u5f37\u751f\u6210 (RAG) \u63d0\u4f9b\u7aef\u5230\u7aef\u3001\u7c21\u5316\u4e14\u7528\u6236\u53cb\u597d\u7684\u4ecb\u9762\u3002\u53ea\u9700\u5e7e\u500b\u7c21\u55ae\u7684\u6b65\u9a5f\uff0c\u5373\u53ef\u5728\u672c\u5730\u900f\u904e HuggingFace \u548c Ollama \u6216\u900f\u904e OpenAI\u3001Cohere \u548c Google \u7b49 LLM \u4f9b\u61c9\u5546\u63a2\u7d22\u60a8\u7684\u8cc7\u6599\u96c6\u4e26\u8f15\u9b06\u63d0\u53d6\u898b\u89e3\u3002<\/p>\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"Open Source RAG running LLMs locally with Ollama\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_swKKRdLBhas\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FswKKRdLBhas%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/swKKRdLBhas\" \/><meta itemprop=\"duration\" content=\"PT10M\" \/><meta itemprop=\"uploadDate\" content=\"2024-05-16T14:05:48Z\" \/><\/div><div id=\"lyte_swKKRdLBhas\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FswKKRdLBhas%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">Open Source RAG running LLMs locally with Ollama<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/swKKRdLBhas\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FswKKRdLBhas%2F0.jpg\" alt=\"Open Source RAG running LLMs locally with Ollama\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"We&#039;ve taken Verba, our open-source Retrieval Augmented Generation (RAG) app, to the next level with the newly released version 1.0. Run LLMs fully free and open with the new Ollama model integration, completely customize the UI, and enjoy many other feature updates like cached conversation, better logging and full transparency. Philip, Edward, and Victoria will take you through all the updates, show you how to set it up locally and help you get started using advanced RAG on your own data in just a couple minutes. GitHub: https:\/\/github.com\/weaviate\/verba Demo: https:\/\/verba.weaviate.io Join Leonie, Femke, Philip, Edward, Ajit and Victoria at Weaviate - we&#039;re hiring: https:\/\/weaviate.io\/company\/careers And remember - all your vector embeddings are belong to you: https:\/\/www.youtube.com\/watch?v=Qra1oWdJQPs Thanks to the Merantix AI Campus for hosting us in Berlin! https:\/\/www.merantix-aicampus.com\/ \u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac CONNECT WITH US \u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac\u25ac Visit weaviate.io Star us on GitHub https:\/\/github.com\/weaviate\/weaviate Stay updated and subscribe to our newsletter: https:\/\/newsletter.weaviate.io\/ Try out Weaviate Cloud Services for free here: https:\/\/console.weaviate.cloud\/ Got a questions? Forum: https:\/\/forum.weaviate.io\/ Slack: https:\/\/weaviate.io\/slack Connect with us on Twitter: https:\/\/twitter.com\/weaviate_io LinkedIn: https:\/\/www.linkedin.com\/company\/weaviate-io\/ Music: Nebulosity - Brendon Moeller Aubergene - Brendon Moeller 00:00 - Introduction 01:17 - Ollama Integration 01:53 - Customization 03:14 - RAG in Healthcare 04:54 - RAG in Weaviate 06:20 - Installation 08:54 - Outro 09:19 - Easter Egg\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"Verba: This Easy-to-Install RAG Chatbot is better than ChatGPT (works w\/ Ollama, OpenAI, Gemini)\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_0bPBUjlc3dE\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F0bPBUjlc3dE%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/0bPBUjlc3dE\" \/><meta itemprop=\"duration\" content=\"PT8M8S\" \/><meta itemprop=\"uploadDate\" content=\"2024-05-20T09:52:28Z\" \/><\/div><div id=\"lyte_0bPBUjlc3dE\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F0bPBUjlc3dE%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">Verba: This Easy-to-Install RAG Chatbot is better than ChatGPT (works w\/ Ollama, OpenAI, Gemini)<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/0bPBUjlc3dE\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F0bPBUjlc3dE%2F0.jpg\" alt=\"Verba: This Easy-to-Install RAG Chatbot is better than ChatGPT (works w\/ Ollama, OpenAI, Gemini)\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"In this video, I&#039;ll be telling you about Verba which is an Opensource project made by the team of Weviate. This is an easy to use RAG-Chatbot or AI Assistant. With this you can chat with PDFs, DOCs, Spreadsheets and everything you can imagine. It is very easy to install just like Jan. You can get started with it in seconds. It works with Ollama (for Local models), OpenAI, Groq, HuggingFace, Gemini and much more. You can also use it with GPT-4O, Gemini 1.5 Pro &amp; Gemini 1.5 Flash. You can also use it with Mistral AI&#039;s Mixtral 8x22b, LLaMa, Gemini and OpenAI API. [Resources] Verba&#039;s Github Repo : https:\/\/github.com\/weaviate\/Verba [Key Takeaways] \ud83d\udd0d Open-Source Excellence: Verba is an open-source RAG chatbot developed by the team at Weaviate, a leading name in AI vector databases. \ud83d\ude80 Seamless Integration: Verba offers a streamlined interface for Retrieval-Augmented Generation (RAG), making it easy for users to integrate and use. \ud83d\udcc2 Versatile Document Support: It supports PDF, CSV, and Excel ingesting, allowing you to analyze unstructured documents efficiently. \ud83d\udca1 Hybrid &amp; Semantic Search: Verba employs hybrid and semantic search to ensure only relevant context is fed to the LLM, enhancing performance. \ud83d\udda5\ufe0f User-Friendly UI: The application boasts a great-looking UI and features like auto-complete suggestions and semantic caching for improved user experience. \ud83c\udf10 Multiple Model Providers: Verba can be used with various model providers like OpenAI, Google, Cohere, Hugging Face, and Ollama, providing flexibility and local deployment options. \u2699\ufe0f Production Ready: With features like customizable logos and live demos, Verba can be easily deployed in production environments.\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>","protected":false},"excerpt":{"rendered":"<p>Golden RAGtriever \u662f\u4e00\u6b3e\u958b\u6e90\u61c9\u7528\u7a0b\u5e8f\uff0c\u65e8\u5728\u70ba\u958b\u7bb1\u5373\u7528\u7684\u6aa2\u7d22\u589e\u5f37\u751f\u6210 (RAG) \u63d0\u4f9b\u7aef\u5230\u7aef\u3001\u7c21\u5316\u4e14\u7528\u6236\u53cb\u597d\u7684\u4ecb\u9762\u3002\u53ea\u9700\u5e7e\u500b\u7c21\u55ae\u7684\u6b65\u9a5f\uff0c\u5373\u53ef\u5728\u672c\u5730\u900f\u904e HuggingFace \u548c Ollama \u6216\u900f\u904e OpenAI\u3001Cohere \u548c Google \u7b49 LLM \u4f9b\u61c9\u5546\u63a2\u7d22\u60a8\u7684\u8cc7\u6599\u96c6\u4e26\u8f15\u9b06\u63d0\u53d6\u898b\u89e3\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"categories":[38,27],"tags":[44,59,45],"class_list":["post-2734","post","type-post","status-publish","format-standard","hentry","category-38","category-paper","tag-github","tag-llm","tag-45"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/2734","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=2734"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/2734\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=2734"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=2734"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=2734"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}