{"id":24037,"date":"2024-11-29T01:25:11","date_gmt":"2024-11-28T17:25:11","guid":{"rendered":"https:\/\/www.1ai.net\/?p=24037"},"modified":"2024-11-28T21:26:27","modified_gmt":"2024-11-28T13:26:27","slug":"gpt-4o-%e7%b3%bb%e5%88%97-ai-%e6%a8%a1%e5%9e%8b%e5%8a%a0%e6%8c%81%ef%bc%8c%e5%be%ae%e8%bd%af-llamaparse-%e6%96%87%e6%a1%a3%e8%a7%a3%e6%9e%90%e8%83%bd%e5%8a%9b%e5%85%a8%e9%9d%a2%e5%8d%87%e7%ba%a7","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/24037.html","title":{"rendered":"Microsoft LlamaParse Document Parsing Capabilities Upgraded with GPT-4o Series AI Models"},"content":{"rendered":"<p><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%be%ae%e8%bd%af\" title=\"[View articles tagged with [Microsoft]]\" target=\"_blank\" >Microsoft<\/a>published a blog post on November 26, announcing that in its <a href=\"https:\/\/www.1ai.net\/en\/tag\/llamaparse\" title=\"[Sees articles with [LlamaParse] label]\" target=\"_blank\" >LlamaParse<\/a> Integration of Azure OpenAI endpoints in the <a href=\"https:\/\/www.1ai.net\/en\/tag\/gpt-4o\" title=\"[View articles tagged with [GPT-4o]]\" target=\"_blank\" >GPT-4o<\/a> series of models.<strong>Enhance extraction of unstructured data and parsing of multimodal documents, and seamlessly interface with Azure AI Search vector databases to build complete retrieval augmentation generation (RAG) workflows.<\/strong><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-24038\" title=\"e56e8af5j00snnxao0063d000v900hkp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/11\/e56e8af5j00snnxao0063d000v900hkp.jpg\" alt=\"e56e8af5j00snnxao0063d000v900hkp\" width=\"1125\" height=\"632\" \/><\/p>\n<p><strong>Introduction to LlamaParse<\/strong><\/p>\n<p>Microsoft LlamaParse is a document parser designed for Generative Artificial Intelligence (GenAI), whose main goal is to parse and clean a wide variety of document data to ensure data quality before passing it on to downstream Large Language Models (LLMs).<\/p>\n<p>Adding Azure OpenAI endpoints<\/p>\n<p>Microsoft LlamaParse, with this integration, enables users to call Azure OpenAI's GPT-4o family of models to extract unstructured data and document transformations. This integration capitalizes on the strengths of both<strong>LlamaParse for efficient parsing and Azure OpenAI for powerful language modeling capabilities<\/strong>, ultimately enabling more accurate and smarter document processing.<\/p>\n<p>Citing the media report, 1AI attached the update as follows:<\/p>\n<ul>\n<li>Directly connect to models such as GPT-4o and GPT-4o-mini for Azure OpenAI<\/li>\n<li>Multimodal document parsing in LlamaParse, with multimodal support via Azure OpenAI<\/li>\n<li>LLM-optimized output for enhanced retrieval and semantic searching<\/li>\n<li>Seamless ingestion into Azure AI Search's vector repository via LlamaIndex<\/li>\n<li>Enterprise-grade security and compliance for sensitive workloads<\/li>\n<\/ul>\n<p>Users can leverage LlamaCloud, Azure AI Search, and Azure OpenAI to build a complete RAG workflow in a number of steps:<\/p>\n<ul>\n<li>Parsing and Enrichment: Advanced document extraction using LlamaParse Premium and Azure OpenAI to generate LLM-optimized output in multiple formats such as Markdown, LaTeX, and Mermaid charts.<\/li>\n<li>Chunking and Embedding: Use Azure AI Search as a vector store and leverage the embedding model in the Azure AI Model Catalog to chunk, embed, and index the parsed content.<\/li>\n<li>Search &amp; Generate: Leverage Azure AI Search's query rewriting and semantic reordering capabilities to improve retrieval quality. Finally, build generative AI applications by orchestrating Azure AI Search and Azure OpenAI with Llamaindex.<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>In a November 26th blog post, Microsoft announced the integration of Azure OpenAI endpoints in its LlamaParse to leverage the GPT-4o family of models to enhance the extraction of unstructured data and parsing of multimodal documents, and to seamlessly interface with the Azure AI Search Vector Database to build a complete Retrieval Augmented Generation (RAG) workflow. Introduction to LlamaParse Microsoft LlamaParse is a document parser designed for Generative Artificial Intelligence (GenAI), with the primary goal of parsing and cleansing a wide range of document data to ensure data quality before passing it on to downstream Large Language Models (LLMs). Addition of Azure OpenAI Endpoints<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[2582,5076,280],"collection":[],"class_list":["post-24037","post","type-post","status-publish","format-standard","hentry","category-news","tag-gpt-4o","tag-llamaparse","tag-280"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/24037","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=24037"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/24037\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=24037"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=24037"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=24037"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=24037"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}