{"id":5934,"date":"2023-10-12T10:23:00","date_gmt":"2023-10-12T04:53:00","guid":{"rendered":"https:\/\/aiplanet.com\/blog\/?p=5934"},"modified":"2023-10-27T11:48:10","modified_gmt":"2023-10-27T06:18:10","slug":"genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more","status":"publish","type":"post","link":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/","title":{"rendered":"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more"},"content":{"rendered":"\n<time datetime=\"2023-10-12 18:00:00 +0530\" class=\"published\">October 12,2023<\/time>\n\n\n\n<p class=\"wp-block-paragraph\">In this article, we will discuss the latest release stacked in GenAI Stack.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Key highlights of the latest release:&nbsp;<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Integrating <strong>LLM Cache<\/strong> <strong>(<\/strong><a href=\"https:\/\/github.com\/aiplanethub\/genai-stack\/pull\/56\"><strong>#56<\/strong><\/a><strong>)<\/strong> with VectorDatabases to reduce the number of repeated queries done by the user, thereby saving significant costs and enhancing response time on LLM requests.&nbsp;<\/li><li>Setup GenAI Stack installation with pypi and poetry setup <strong>(<\/strong><a href=\"https:\/\/github.com\/aiplanethub\/genai-stack\/pull\/78\"><strong>#78<\/strong><\/a><strong>)<\/strong>. You can now install GenAI Stack directly using pypi.&nbsp;<\/li><li>Building a server <strong>RestAPIs(<\/strong><a href=\"https:\/\/github.com\/aiplanethub\/genai-stack\/pull\/59\"><strong>#59<\/strong><\/a><strong>)<\/strong> of GenAI Stack for developers. With the GenAI Stack <strong>RestAPI\u2019s<\/strong> all the required components and stack initialization are handled internally.&nbsp;<\/li><li>GenAI Stack now supports <strong>VectorDBMemory (<\/strong><a href=\"https:\/\/github.com\/aiplanethub\/genai-stack\/pull\/92\"><strong>#92<\/strong><\/a><strong>)<\/strong>, which stores memory conversation inside VectorDB.&nbsp;<\/li><\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">For more details, keep scrolling \u2b07\ufe0f!<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img fetchpriority=\"high\" decoding=\"async\" width=\"1920\" height=\"1080\" src=\"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png\" alt=\"\" class=\"wp-image-5935\"\/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Introduced new component: LLM Cache<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">With the growing popularity of the large language model (LLM), the LLM Caching takes center stage to improve performance. The <strong>LLM Cache<\/strong> is essential because it optimizes language model performance by reducing query load and enhancing response time through efficient storage and retrieval of data, resulting in cost savings and improved user experience.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This component plays a pivotal role in reducing the number of queries made to the LLM.&nbsp;<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">How to use LLM Cache?<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Cache requires a vector database to store the LLM queries. Currently we have support for <strong>Weaviate<\/strong> and <strong>ChromaDB<\/strong>. In-order to use the cache, you have to provide the vector database component to the stack. The cache component is dependent on other components and it is not used alone.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from genai_stack.vectordb import ChromaDB\n from genai_stack.llm_cache import LLMCache\n\n\n chromadb = ChromaDB.from_kwargs(\n     search_method=\"max_marginal_relevance_search\"\n )\n llm_cache = LLMCache.from_kwargs()\n \"\"\" add llm_cache along with other components in the Stack. Look into documentation for the example\"\"\"<\/code><\/pre>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Reference: <\/strong>Example Code usage- <a href=\"https:\/\/genaistack.aiplanet.com\/components\/llm-cache\/quickstart\">LLM Cache documentation<\/a><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">GenAI Stack now supports REST APIs&nbsp;<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">From the Initial version to the 0.2.2 version release of GenAI Stack, to build an app or use case we had to manually import and initialize each component with specific configurations and then initialize the stack by passing the components instance. In order to create a new app or use case, you have to create a completely new stack or change existing stack components configurations (mainly <strong>VectorDB<\/strong> and <strong>Memory<\/strong>).&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">With the GenAI Stack RestAPI\u2019s all the required components and stack initialization are handled internally, you just have to create a <strong>stack_config.json<\/strong> which contains all the components configurations and then you can run the server and start calling endpoints.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">When you run a <strong>GenAI Stack Rest API Server<\/strong>, it internally sets up the <strong>sqlite<\/strong> database and persists some of the important and necessary configurations that isolate the apps or use case.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For example we have an endpoint called <strong>session<\/strong>, this endpoint internally creates a collection for <strong>VectorDB<\/strong>, <strong>Memory<\/strong> and<strong> LLM Cache<\/strong>, these collections isolate the context and conversations of the apps.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A sample usage of <strong>stack_config.json<\/strong>:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>{\n    \"components\": {\n        \"vectordb\": {\n            \"name\": \"weaviate_db\",\n            \"config\": {\n                \"url\": \"http:\/\/localhost:8080\/\",\n                \"index_name\": \"Testing\",\n                \"text_key\": \"test\",\n                \"attributes\": &#91;\"page\", \"path\"]\n            }\n        },\n        \"memory\": {\n            \"name\": \"langchain\",\n            \"config\": {}\n        },\n        \"llm_cache\": {\n            \"name\": \"cache\",\n            \"config\": {}\n        },\n        \"model\": {\n            \"name\": \"gpt3.5\",\n            \"config\": {\n                \"parameters\": {\n                    \"openai_api_key\": \"your_api_key_here\"\n                }\n            }\n        },\n        \"embedding\": {\n            \"name\": \"langchain\",\n            \"config\": {\n                \"name\": \"HuggingFaceEmbeddings\",\n                \"fields\": {\n                    \"model_name\": \"sentence-transformers\/all-mpnet-base-v2\",\n                    \"model_kwargs\": { \"device\": \"cpu\" },\n                    \"encode_kwargs\": { \"normalize_embeddings\": false }\n                }\n            }\n        },\n        \"prompt_engine\": {\n            \"name\": \"engine\",\n            \"config\": {\n                \"should_validate\": true\n            }\n        },\n        \"retriever\": {\n            \"name\": \"langchain\",\n            \"config\": {}\n        }\n    }\n}<\/code><\/pre>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>Read More<\/strong><\/h4>\n\n\n\n<p class=\"wp-block-paragraph\">Setup Server : <a href=\"https:\/\/genaistack.aiplanet.com\/advanced-guide\/genai_stack_server\">https:\/\/genaistack.aiplanet.com\/advanced-guide\/genai_stack_server<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">API Endpoint Reference : <a href=\"https:\/\/genaistack.aiplanet.com\/advanced-guide\/openapi\">https:\/\/genaistack.aiplanet.com\/advanced-guide\/openapi<\/a><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Memory integration in VectorDB <a href=\"https:\/\/github.com\/aiplanethub\/genai-stack\/pull\/92\">#92<\/a><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">In our latest release, we now support a memory for the Vector databases. <strong>VectorDBMemory<\/strong> supports both <strong>ChromaDB<\/strong> and <strong>Weaviate<\/strong>, which one is used to store the conversations totally depends on the vector database that is initialized and passed to the <strong>Stack<\/strong> for storing the documents.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Why is this important?<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>VectorDBMemory<\/strong> stores memories in a VectorDB and queries the <strong>top-K most salient<\/strong> docs every time it is called. This approach helps in managing long-term memory in Large Language Model applications.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">It provides a way to persist and retrieve relevant documents from a vector store database, which can be useful for maintaining conversation history or other types of memory in an LLM application.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">How to use VectorDBMemory?<\/h3>\n\n\n\n<pre class=\"wp-block-code\"><code>from genai_stack.vectordb import ChromaDB, Weaviate\nfrom genai_stack.memory import VectorDBMemory\n\nvectordb = ChromaDB.from_kwargs()\n#or \nvectordb = Weaviate.from_kwargs(\n    url=\"http:\/\/localhost:8080\/\", index_name=\"Testing\", text_key=\"test\"\n)\n\nmemory = VectorDBMemory.from_kwargs(index_name = \"Conversations\")\n\nstack = Stack(\n    vectordb=vectordb,\n    memory=memory\n)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\">Conclusion<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">GenAI Stack being an Open Source project, we strive for continuous improvements, enhancements in features and bug fixes. The best part of the open-source project to directly be involved with the community.&nbsp;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Langchain is a framework to work with Large Language models which eventually is a sub-field of Deep learning. We personally feel GenAI Stack is focused on both Machine Learning and development, making it comfortable for the beginners to contribute to open source.&nbsp;<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What&#8217;s next<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Check out Getting Started with <a href=\"https:\/\/colab.research.google.com\/drive\/1y6_0MoNWjS9wugv0askP1Jb7zrY_sQT-?usp=sharing\"><strong>GenAI Stack demo notebook<\/strong><\/a>, and begin building amazing chatbots with GenAI Stack.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">You can reach out to us on Discord community forum: <a href=\"https:\/\/discord.com\/invite\/E2XfSEYm2W\"><strong>https:\/\/discord.com\/invite\/E2XfSEYm2W<\/strong><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">You can follow the project on <a href=\"https:\/\/github.com\/aiplanethub\/genai-stack\"><strong>GitHub<\/strong><\/a>. Don\u2019t forget to give us a \u2b50\ufe0f while you are there!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>October 12,2023 In this article, we will discuss the latest release stacked in GenAI Stack. Key highlights of the latest release:&nbsp; Integrating LLM Cache (#56) with VectorDatabases to reduce the number of repeated queries done by the user, thereby saving significant costs and enhancing response time on LLM requests.&nbsp; Setup GenAI Stack installation with pypi [&hellip;]<\/p>\n","protected":false},"author":11896,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[172],"tags":[141,176,175,174,173],"class_list":["post-5934","post","type-post","status-publish","format-standard","hentry","category-genai_stack","tag-ai","tag-chatgpt","tag-genai_stack","tag-langchain","tag-llm"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more - AI Planet<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more - AI Planet\" \/>\n<meta property=\"og:description\" content=\"October 12,2023 In this article, we will discuss the latest release stacked in GenAI Stack. Key highlights of the latest release:&nbsp; Integrating LLM Cache (#56) with VectorDatabases to reduce the number of repeated queries done by the user, thereby saving significant costs and enhancing response time on LLM requests.&nbsp; Setup GenAI Stack installation with pypi [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/\" \/>\n<meta property=\"og:site_name\" content=\"AI Planet\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/aiplanet\/\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-12T04:53:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-27T06:18:10+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png\" \/>\n<meta name=\"author\" content=\"tarunjain\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"tarunjain\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/\"},\"author\":{\"name\":\"tarunjain\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#\\\/schema\\\/person\\\/fcd5354495f9ff097301b3e3137c2345\"},\"headline\":\"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more\",\"datePublished\":\"2023-10-12T04:53:00+00:00\",\"dateModified\":\"2023-10-27T06:18:10+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/\"},\"wordCount\":723,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/GenAI-Stack-release.png\",\"keywords\":[\"ai\",\"chatgpt\",\"genai_stack\",\"langchain\",\"llm\"],\"articleSection\":[\"genai_stack\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/\",\"url\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/\",\"name\":\"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more - AI Planet\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/GenAI-Stack-release.png\",\"datePublished\":\"2023-10-12T04:53:00+00:00\",\"dateModified\":\"2023-10-27T06:18:10+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#primaryimage\",\"url\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/GenAI-Stack-release.png\",\"contentUrl\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/GenAI-Stack-release.png\",\"width\":1920,\"height\":1080},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/\",\"name\":\"AI Planet, Formerly DPhi\",\"description\":\"AI Planet (formerly DPhi) is a global ecosystem that aims to educate and empower individuals and organizations to build and utilize artificial intelligence (AI). With a community of over 300,000 AI specialists and enthusiasts, we offer a range of products and have helped drive innovative solutions for various industries. Our ultimate goal is to make AI education accessible to everyone and use AI to tackle important business and social challenges.\",\"publisher\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#organization\",\"name\":\"AI Planet, Formerly DPhi\",\"url\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/wp-content\\\/uploads\\\/2022\\\/11\\\/Size48-Large-1.png\",\"contentUrl\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/wp-content\\\/uploads\\\/2022\\\/11\\\/Size48-Large-1.png\",\"width\":48,\"height\":48,\"caption\":\"AI Planet, Formerly DPhi\"},\"image\":{\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/aiplanet\\\/\",\"https:\\\/\\\/www.instagram.com\\\/aiplanet_community\\\/\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/aiplanet\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@aiplanet\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/#\\\/schema\\\/person\\\/fcd5354495f9ff097301b3e3137c2345\",\"name\":\"tarunjain\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/91f63b6544d710332f6a34af89c0fd7180773a2baaf3e498838b79ce8d3ddfbe?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/91f63b6544d710332f6a34af89c0fd7180773a2baaf3e498838b79ce8d3ddfbe?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/91f63b6544d710332f6a34af89c0fd7180773a2baaf3e498838b79ce8d3ddfbe?s=96&d=mm&r=g\",\"caption\":\"tarunjain\"},\"url\":\"https:\\\/\\\/aiplanet.com\\\/blog\\\/author\\\/tarunjain\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more - AI Planet","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/","og_locale":"en_US","og_type":"article","og_title":"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more - AI Planet","og_description":"October 12,2023 In this article, we will discuss the latest release stacked in GenAI Stack. Key highlights of the latest release:&nbsp; Integrating LLM Cache (#56) with VectorDatabases to reduce the number of repeated queries done by the user, thereby saving significant costs and enhancing response time on LLM requests.&nbsp; Setup GenAI Stack installation with pypi [&hellip;]","og_url":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/","og_site_name":"AI Planet","article_publisher":"https:\/\/www.facebook.com\/aiplanet\/","article_published_time":"2023-10-12T04:53:00+00:00","article_modified_time":"2023-10-27T06:18:10+00:00","og_image":[{"url":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png","type":"","width":"","height":""}],"author":"tarunjain","twitter_card":"summary_large_image","twitter_misc":{"Written by":"tarunjain","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#article","isPartOf":{"@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/"},"author":{"name":"tarunjain","@id":"https:\/\/aiplanet.com\/blog\/#\/schema\/person\/fcd5354495f9ff097301b3e3137c2345"},"headline":"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more","datePublished":"2023-10-12T04:53:00+00:00","dateModified":"2023-10-27T06:18:10+00:00","mainEntityOfPage":{"@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/"},"wordCount":723,"commentCount":0,"publisher":{"@id":"https:\/\/aiplanet.com\/blog\/#organization"},"image":{"@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#primaryimage"},"thumbnailUrl":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png","keywords":["ai","chatgpt","genai_stack","langchain","llm"],"articleSection":["genai_stack"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/","url":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/","name":"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more - AI Planet","isPartOf":{"@id":"https:\/\/aiplanet.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#primaryimage"},"image":{"@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#primaryimage"},"thumbnailUrl":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png","datePublished":"2023-10-12T04:53:00+00:00","dateModified":"2023-10-27T06:18:10+00:00","breadcrumb":{"@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#primaryimage","url":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png","contentUrl":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2023\/10\/GenAI-Stack-release.png","width":1920,"height":1080},{"@type":"BreadcrumbList","@id":"https:\/\/aiplanet.com\/blog\/genai-stack-version-0-2-is-here-with-llm-caching-rest-apis-vectordb-memory-and-more\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/aiplanet.com\/blog\/"},{"@type":"ListItem","position":2,"name":"GenAI Stack Version 0.2 is here with LLM Caching, Rest APIs, VectorDB Memory and more"}]},{"@type":"WebSite","@id":"https:\/\/aiplanet.com\/blog\/#website","url":"https:\/\/aiplanet.com\/blog\/","name":"AI Planet, Formerly DPhi","description":"AI Planet (formerly DPhi) is a global ecosystem that aims to educate and empower individuals and organizations to build and utilize artificial intelligence (AI). With a community of over 300,000 AI specialists and enthusiasts, we offer a range of products and have helped drive innovative solutions for various industries. Our ultimate goal is to make AI education accessible to everyone and use AI to tackle important business and social challenges.","publisher":{"@id":"https:\/\/aiplanet.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/aiplanet.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/aiplanet.com\/blog\/#organization","name":"AI Planet, Formerly DPhi","url":"https:\/\/aiplanet.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/aiplanet.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2022\/11\/Size48-Large-1.png","contentUrl":"https:\/\/aiplanet.com\/blog\/wp-content\/uploads\/2022\/11\/Size48-Large-1.png","width":48,"height":48,"caption":"AI Planet, Formerly DPhi"},"image":{"@id":"https:\/\/aiplanet.com\/blog\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/aiplanet\/","https:\/\/www.instagram.com\/aiplanet_community\/","https:\/\/www.linkedin.com\/company\/aiplanet\/","https:\/\/www.youtube.com\/@aiplanet"]},{"@type":"Person","@id":"https:\/\/aiplanet.com\/blog\/#\/schema\/person\/fcd5354495f9ff097301b3e3137c2345","name":"tarunjain","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/91f63b6544d710332f6a34af89c0fd7180773a2baaf3e498838b79ce8d3ddfbe?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/91f63b6544d710332f6a34af89c0fd7180773a2baaf3e498838b79ce8d3ddfbe?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/91f63b6544d710332f6a34af89c0fd7180773a2baaf3e498838b79ce8d3ddfbe?s=96&d=mm&r=g","caption":"tarunjain"},"url":"https:\/\/aiplanet.com\/blog\/author\/tarunjain\/"}]}},"_links":{"self":[{"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/posts\/5934","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/users\/11896"}],"replies":[{"embeddable":true,"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/comments?post=5934"}],"version-history":[{"count":3,"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/posts\/5934\/revisions"}],"predecessor-version":[{"id":5938,"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/posts\/5934\/revisions\/5938"}],"wp:attachment":[{"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/media?parent=5934"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/categories?post=5934"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aiplanet.com\/blog\/wp-json\/wp\/v2\/tags?post=5934"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}