{"id":145602,"date":"2025-03-20T11:45:52","date_gmt":"2025-03-20T11:45:52","guid":{"rendered":"https:\/\/peraltafinancing.com\/analytics\/top-5-rag-frameworks-for-ai-applications\/"},"modified":"2025-03-20T11:45:52","modified_gmt":"2025-03-20T11:45:52","slug":"top-5-rag-frameworks-for-ai-applications","status":"publish","type":"post","link":"https:\/\/fivemor.com\/?p=145602","title":{"rendered":"Top 5 RAG Frameworks for AI Applications"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div id=\"article-start\">\n<p>RAG has become a popular technology in 2025, it avoids the fine-tuning of the model which is expensive as well as time-consuming. There\u2019s an increased demand for RAG frameworks in the current scenario, Lets Understand what are these. Retrieval-augmented generation (RAG) frameworks are essential tools in the field of artificial intelligence. They enhance the capabilities of Large Language Models (LLMs) by allowing them to retrieve relevant information from external sources. This leads to more accurate and context-aware responses. Here, we will explore five notable RAG frameworks: LangChain, LlamaIndex, LangGraph, Haystack, and RAGFlow. Each framework offers unique features that can improve your AI projects.<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-1-langchain\"><strong>1. LangChain<\/strong><\/h2>\n<p><a href=\"https:\/\/www.langchain.com\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">LangChain<\/a> is a flexible framework that simplifies the development of applications using LLMs. It provides tools for building RAG applications, making integration straightforward.<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Key Features<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Modular design for easy customization.<\/li>\n<li>Supports various LLMs and data sources.<\/li>\n<li>Built-in tools for document retrieval and processing.<\/li>\n<li>Suitable for chatbots and virtual assistants.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Here\u2019s the hands-on:<\/p>\n<h4 class=\"wp-block-heading\" id=\"h-install-the-following-libraries\">Install the following libraries<\/h4>\n<pre class=\"wp-block-code\"><code>! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain<\/code><\/pre>\n<h4 class=\"wp-block-heading\" id=\"h-set-up-openai-api-key-and-os-environment\">Set up OpenAI API key and os environment<\/h4>\n<pre class=\"wp-block-code\"><code>from getpass import getpass\nopenai = getpass(\"OpenAI API Key:\")\nimport os\nos.environ[\"OPENAI_API_KEY\"] = openai<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-import-the-following-dependencies\">Import the following dependencies<\/h3>\n<pre class=\"wp-block-code\"><code>import bs4\nfrom langchain import hub\nfrom langchain.text_splitter import RecursiveCharacterTextSplitter\nfrom langchain_community.document_loaders import WebBaseLoader\nfrom langchain_community.vectorstores import Chroma\nfrom langchain_core.output_parsers import StrOutputParser\nfrom langchain_core.runnables import RunnablePassthrough\nfrom langchain_openai import ChatOpenAI, OpenAIEmbeddings<\/code><\/pre>\n<p>Loading the document for RAG using WebBase Loader (replace with your own Data)<\/p>\n<pre class=\"wp-block-code\"><code># Load Documents\nloader = WebBaseLoader(\n\u00a0\u00a0\u00a0web_paths=(\"https:\/\/lilianweng.github.io\/posts\/2023-06-23-agent\/\",),\n\u00a0\u00a0\u00a0bs_kwargs=dict(\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0parse_only=bs4.SoupStrainer(\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0class_=(\"post-content\", \"post-title\", \"post-header\")\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0)\n\u00a0\u00a0\u00a0),\n)\ndocs = loader.load()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-chunking-the-document-using-recursivecharactertextsplitter\">Chunking the document using RecursiveCharacterTextSplitter<\/h3>\n<pre class=\"wp-block-code\"><code># Split\ntext_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\nsplits = text_splitter.split_documents(docs)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-storing-the-vector-documents-in-chromadb\">Storing the vector documents in ChromaDB<\/h3>\n<pre class=\"wp-block-code\"><code># Embed\nvectorstore = Chroma.from_documents(documents=splits,\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0embedding=OpenAIEmbeddings())\nretriever = vectorstore.as_retriever()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-pulling-the-rag-prompt-from-the-langchain-hub-and-defining-llm\">Pulling the RAG prompt from the LangChain hub and defining LLM<\/h3>\n<pre class=\"wp-block-code\"><code># Prompt\nprompt = hub.pull(\"rlm\/rag-prompt\")\n# LLM\nllm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-processing-the-retrieved-docs-nbsp\">Processing the retrieved docs\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code># Post-processing\ndef format_docs(docs):\n\u00a0\u00a0\u00a0return \"\\n\\n\".join(doc.page_content for doc in docs)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-creating-the-rag-chain\">Creating the RAG chain<\/h3>\n<pre class=\"wp-block-code\"><code># Chain\nrag_chain = (\n\u00a0\u00a0\u00a0{\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n\u00a0\u00a0\u00a0| prompt\n\u00a0\u00a0\u00a0| llm\n\u00a0\u00a0\u00a0| StrOutputParser()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-invoking-the-chain-with-the-question\">Invoking the chain with the question<\/h3>\n<pre class=\"wp-block-code\"><code># Question\nrag_chain.invoke(\"What is Task Decomposition?\")<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-output\">Output<\/h3>\n<pre class=\"wp-block-preformatted\">\u2018Task Decomposition is a technique used to break down complex tasks into<br\/>smaller and simpler steps. This approach helps agents to plan ahead and<br\/>tackle difficult tasks more effectively. Task decomposition can be done<br\/>through various methods, including using prompting techniques, task-specific<br\/>instructions, or human inputs.\u2019<\/pre>\n<p>Also Read: <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2024\/06\/langchain-guide\/\" target=\"_blank\" rel=\"noreferrer noopener\">Find everything about LangChain Here.<\/a><\/p>\n<h2 class=\"wp-block-heading\" id=\"h-2-llamaindex\">2. LlamaIndex<\/h2>\n<p><a href=\"https:\/\/www.llamaindex.ai\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">LlamaIndex<\/a>, previously known as the GPT Index, focuses on organizing and retrieving data efficiently for LLM applications. It helps developers access and use large datasets quickly.<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Key Features<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Organizes data for fast lookups.<\/li>\n<li>Customizable components for RAG workflows.<\/li>\n<li>Supports multiple data formats, including PDFs and SQL.<\/li>\n<li>Integrates with vector stores like <a href=\"https:\/\/www.pinecone.io\/\">Pinecone<\/a> and <a href=\"https:\/\/github.com\/facebookresearch\/faiss\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">FAISS<\/a>.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Here\u2019s the hands-on:<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-install-the-following-dependencies\">Install the following dependencies<\/h3>\n<pre class=\"wp-block-code\"><code>!pip install llama-index llama-index-readers-file\n!pip install llama-index-embeddings-openai\n!pip install llama-index-llms-openai<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-import-the-following-dependencies-and-initialize-the-llm-and-embeddings\">Import the following dependencies and initialize the LLM and embeddings<\/h3>\n<pre class=\"wp-block-code\"><code>from llama_index.llms.openai import OpenAI\nfrom llama_index.embeddings.openai import OpenAIEmbedding\nllm = OpenAI(model=\"gpt-4o\")\nembed_model = OpenAIEmbedding()\nfrom llama_index.core import Settings\nSettings.llm = llm\nSettings.embed_model = embed_model<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-download-the-data-you-can-replace-it-with-your-data\">Download the data (You can replace it with your data)<\/h3>\n<pre class=\"wp-block-code\"><code>!wget 'https:\/\/raw.githubusercontent.com\/run-llama\/llama_index\/main\/docs\/docs\/examples\/data\/10k\/uber_2021.pdf' -O '.\/uber_2021.pdf'<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-read-the-data-using-simpledirectoryreader\">Read the data using SimpleDirectoryReader<\/h3>\n<pre class=\"wp-block-code\"><code>from llama_index.core import SimpleDirectoryReader\n\ndocuments = SimpleDirectoryReader(input_files=[\"\/content\/uber_2021.pdf\"]).load_data()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-chunking-the-document-using-tokentextsplitter\">Chunking the document using TokenTextSplitter<\/h3>\n<pre class=\"wp-block-code\"><code>from llama_index.core.node_parser import TokenTextSplitter\nsplitter = TokenTextSplitter(\n\u00a0\u00a0\u00a0chunk_size=512,\n\u00a0\u00a0\u00a0chunk_overlap=0,\n)\nnodes = splitter.get_nodes_from_documents(documents)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-storing-the-vector-embeddings-in-vectorstoreindex\">Storing the vector embeddings in VectorStoreIndex<\/h3>\n<pre class=\"wp-block-code\"><code>from llama_index.core import VectorStoreIndex\nindex = VectorStoreIndex(nodes)\nquery_engine = index.as_query_engine(similarity_top_k=2)\nInvoking the LLM using RAG\nresponse = query_engine.query(\"What is the revenue of Uber in 2021?\")\nprint(response)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-output-0\">Output<\/h3>\n<pre class=\"wp-block-preformatted\">\u2018The revenue of Uber in 2021 was $171.7 million.<\/pre>\n<h2 class=\"wp-block-heading\" id=\"h-3-langgraph\">3. LangGraph<\/h2>\n<p><a href=\"https:\/\/www.langchain.com\/langgraph\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">LangGraph<\/a> connects LLMs with graph-based data structures. This framework is useful for applications that require complex data relationships.<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Key Features<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Efficiently retrieves data from graph structures.<\/li>\n<li>Combines LLMs with graph data for better context.<\/li>\n<li>Allows customization of the retrieval process.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h3 class=\"wp-block-heading\" id=\"h-code\">Code<\/h3>\n<h3 class=\"wp-block-heading\" id=\"h-install-the-following-dependencies-0\">Install the following dependencies<\/h3>\n<pre class=\"wp-block-code\"><code>%pip install --quiet --upgrade langchain-text-splitters langchain-community langgraph langchain-openai<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-initialise-the-model-embeddings-and-vector-database\">Initialise the model, embeddings and Vector database<\/h3>\n<pre class=\"wp-block-code\"><code>from langchain.chat_models import init_chat_model\nllm = init_chat_model(\"gpt-4o-mini\", model_provider=\"openai\")\nfrom langchain_openai import OpenAIEmbeddings\nembeddings = OpenAIEmbeddings(model=\"text-embedding-3-large\")\nfrom langchain_core.vectorstores import InMemoryVectorStore\nvector_store = InMemoryVectorStore(embeddings)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-import-the-following-dependencies-nbsp\">Import the following dependencies\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code>import bs4\nfrom langchain import hub\nfrom langchain_community.document_loaders import WebBaseLoader\nfrom langchain_core.documents import Document\nfrom langchain_text_splitters import RecursiveCharacterTextSplitter\nfrom langgraph.graph import START, StateGraph\nfrom typing_extensions import List, TypedDict<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-download-the-dataset-using-webbaseloader-replace-it-with-your-own-dataset\">Download the dataset using WebBaseLoader(replace it with your own dataset)<\/h3>\n<pre class=\"wp-block-code\"><code># Load and chunk contents of the blog\nloader = WebBaseLoader(\n\u00a0\u00a0\u00a0web_paths=(\"https:\/\/lilianweng.github.io\/posts\/2023-06-23-agent\/\",),\n\u00a0\u00a0\u00a0bs_kwargs=dict(\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0parse_only=bs4.SoupStrainer(\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0class_=(\"post-content\", \"post-title\", \"post-header\")\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0)\n\u00a0\u00a0\u00a0),\n)\ndocs = loader.load()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-chunking-of-the-document-using-recursivecharactertextsplitter\">Chunking of the document using RecursiveCharacterTextSplitter<\/h3>\n<pre class=\"wp-block-code\"><code>text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\nall_splits = text_splitter.split_documents(docs)\n# Index chunks\n_ = vector_store.add_documents(documents=all_splits)<\/code><\/pre>\n<pre class=\"wp-block-code\"><code># Define prompt for question-answering\nprompt = hub.pull(\"rlm\/rag-prompt\")\nDefining the State, Nodes and edges in Langgraph\nDefine state for application\nclass State(TypedDict):\n\u00a0\u00a0\u00a0question: str\n\u00a0\u00a0\u00a0context: List[Document]\n\u00a0\u00a0\u00a0answer: str\n# Define application steps\ndef retrieve(state: State):\n\u00a0\u00a0\u00a0retrieved_docs = vector_store.similarity_search(state[\"question\"])\n\u00a0\u00a0\u00a0return {\"context\": retrieved_docs}\ndef generate(state: State):\n\u00a0\u00a0\u00a0docs_content = \"\\n\\n\".join(doc.page_content for doc in state[\"context\"])\n\u00a0\u00a0\u00a0messages = prompt.invoke({\"question\": state[\"question\"], \"context\": docs_content})\n\u00a0\u00a0\u00a0response = llm.invoke(messages)\n\u00a0\u00a0\u00a0return {\"answer\": response.content}<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-compiling-the-graph-nbsp\">Compiling the Graph\u00a0<\/h3>\n<pre class=\"wp-block-code\"><code># Compile application and test\ngraph_builder = StateGraph(State).add_sequence([retrieve, generate])\ngraph_builder.add_edge(START, \"retrieve\")\ngraph = graph_builder.compile()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-invoking-the-llm-for-rag\">Invoking the LLM for RAG<\/h3>\n<pre class=\"wp-block-code\"><code>response = graph.invoke({\"question\": \"What is Task Decomposition?\"})\nprint(response[\"answer\"])<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-output-1\">Output<\/h3>\n<pre class=\"wp-block-preformatted\">Task Decomposition is the process of breaking down a complicated task into<br\/>smaller, manageable steps. This can be achieved using techniques like Chain<br\/>of Thought (CoT) or Tree of Thoughts, which guide models to reason step by<br\/>step or evaluate multiple possibilities. The goal is to simplify complex<br\/>tasks and enhance understanding of the reasoning process.<\/pre>\n<h2 class=\"wp-block-heading\" id=\"h-4-haystack\">4. Haystack<\/h2>\n<p><a href=\"https:\/\/haystack.deepset.ai\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Haystack<\/a> is an end-to-end framework for developing applications powered by LLMs and transformer models. It excels in document search and question answering.<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Key Features<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Combines document search with <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2025\/03\/top-sota-llms\/\" target=\"_blank\" rel=\"noreferrer noopener\">LLM<\/a> capabilities.<\/li>\n<li>Uses various retrieval methods for optimal results.<\/li>\n<li>Offers pre-built pipelines for quick development.<\/li>\n<li>Compatible with Elasticsearch and OpenSearch.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Here\u2019s the hands-on:<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-install-the-following-dependencies-1\">Install the following Dependencies<\/h3>\n<pre class=\"wp-block-code\"><code>!pip install haystack-ai\n!pip install \"datasets&gt;=2.6.1\"\n!pip install \"sentence-transformers&gt;=3.0.0\"\nImport the VectorStore and initialise it\nfrom haystack.document_stores.in_memory import InMemoryDocumentStore\ndocument_store = InMemoryDocumentStore()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-loading-the-inbuilt-dataset-from-the-dataset-library\">Loading the inbuilt dataset from the dataset library<\/h3>\n<pre class=\"wp-block-code\"><code>from datasets import load_dataset\nfrom haystack import Document\ndataset = load_dataset(\"bilgeyucel\/seven-wonders\", split=\"train\")\ndocs = [Document(content=doc[\"content\"], meta=doc[\"meta\"]) for doc in dataset]<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-downloading-the-embedding-model-you-can-replace-it-with-openai-embeddings-also\">Downloading the Embedding model (you can replace it with OpenAI embeddings also)<\/h3>\n<pre class=\"wp-block-code\"><code>from haystack.components.embedders import SentenceTransformersDocumentEmbedder\ndoc_embedder = SentenceTransformersDocumentEmbedder(model=\"sentence-transformers\/all-MiniLM-L6-v2\")\ndoc_embedder.warm_up()\ndocs_with_embeddings = doc_embedder.run(docs)\ndocument_store.write_documents(docs_with_embeddings[\"documents\"])<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-storing-the-embeddings-in-vectorstore\">Storing the embeddings in VectorStore<\/h3>\n<pre class=\"wp-block-code\"><code>from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever\nretriever = InMemoryEmbeddingRetriever(document_store)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-defining-the-prompt-for-rag\">Defining the prompt for RAG<\/h3>\n<pre class=\"wp-block-code\"><code>from haystack.components.builders import ChatPromptBuilder\nfrom haystack.dataclasses import ChatMessage\ntemplate = [\n\u00a0\u00a0\u00a0ChatMessage.from_user(\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"\"\"\nGiven the following information, answer the question.\nContext:\n{% for document in documents %}\n\u00a0\u00a0\u00a0{{ document.content }}\n{% endfor %}\nQuestion: {{question}}\nAnswer:\n\"\"\"\n\u00a0\u00a0\u00a0)\n]\nprompt_builder = ChatPromptBuilder(template=template)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-initializing-the-llm\">Initializing the LLM<\/h3>\n<pre class=\"wp-block-code\"><code>from haystack.components.generators.chat import OpenAIChatGenerator\nchat_generator = OpenAIChatGenerator(model=\"gpt-4o-mini\")<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-defining-the-pipeline-nodes\">Defining the Pipeline nodes<\/h3>\n<pre class=\"wp-block-code\"><code>from haystack import Pipeline\nbasic_rag_pipeline = Pipeline()\n# Add components to your pipeline\nbasic_rag_pipeline.add_component(\"text_embedder\", text_embedder)\nbasic_rag_pipeline.add_component(\"retriever\", retriever)\nbasic_rag_pipeline.add_component(\"prompt_builder\", prompt_builder)\nbasic_rag_pipeline.add_component(\"llm\", chat_generator)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-connecting-the-nodes-to-each-other\">Connecting the nodes to each other<\/h3>\n<pre class=\"wp-block-code\"><code># Now, connect the components to each other\nbasic_rag_pipeline.connect(\"text_embedder.embedding\", \"retriever.query_embedding\")\nbasic_rag_pipeline.connect(\"retriever\", \"prompt_builder\")\nbasic_rag_pipeline.connect(\"prompt_builder.prompt\", \"llm.messages\")<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-invoking-the-llm-using-rag\">Invoking the LLM using RAG<\/h3>\n<pre class=\"wp-block-code\"><code>question = \"What does Rhodes Statue look like?\"\nresponse = basic_rag_pipeline.run({\"text_embedder\": {\"text\": question}, \"prompt_builder\": {\"question\": question}})\nprint(response[\"llm\"][\"replies\"][0].text)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-output-2\">Output<\/h3>\n<pre class=\"wp-block-preformatted\">Batches:\u2007100%<p>\u20071\/1\u2007[00:00<\/p><p>\u2018The Colossus of Rhodes, a statue of the Greek sun-god Helios, is believed to<br\/>have stood approximately 33 meters (108 feet) tall and was constructed with<br\/>iron tie bars and brass plates forming its skin, filled with stone blocks.<br\/>Although the specific details of its appearance are not definitively known,<br\/>contemporary accounts suggest that it had curly hair with bronze or silver<br\/>spikes radiating like flames on the head. The statue likely depicted Helios<br\/>in a powerful, commanding pose, possibly with one hand shielding his eyes,<br\/>similar to other representations of the sun god from the time. Overall, it<br\/>was designed to project strength and radiance, celebrating Rhodes' victory<br\/>over its enemies.\u2019<\/p><\/pre>\n<h2 class=\"wp-block-heading\" id=\"h-5-ragflow\">5. RAGFlow<\/h2>\n<p><a href=\"https:\/\/ragflow.io\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">RAGFlow<\/a> focuses on integrating retrieval and generation processes. It streamlines the development of RAG applications.<\/p>\n<ul class=\"wp-block-list\">\n<li><strong>Key Features<\/strong>:\n<ul class=\"wp-block-list\">\n<li>Simplifies the connection between retrieval and generation.<\/li>\n<li>Allows for tailored workflows to meet project needs.<\/li>\n<li>Integrates easily with various databases and document formats.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>Here\u2019s the hands-on:<\/p>\n<p>Sign up at the <a href=\"https:\/\/ragflow.io\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">RAGFlow<\/a> and then Click on Try RAGFlow<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img fetchpriority=\"high\" decoding=\"async\" width=\"1600\" height=\"639\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132813.253.webp\" alt=\"RagFlow\" class=\"wp-image-227157\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132813.253.webp 1600w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132813.253-300x120.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132813.253-768x307.webp 768w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132813.253-1536x613.webp 1536w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132813.253-150x60.webp 150w\" sizes=\"(max-width: 1600px) 100vw, 1600px\"\/><\/figure>\n<\/div>\n<p>Then Click on Create Knowledge Base<\/p>\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1600\" height=\"424\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132852.651.webp\" alt=\"Then Click on Create Knowledge Base\" class=\"wp-image-227159\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132852.651.webp 1600w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132852.651-300x80.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132852.651-768x204.webp 768w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132852.651-1536x407.webp 1536w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132852.651-150x40.webp 150w\" sizes=\"auto, (max-width: 1600px) 100vw, 1600px\"\/><\/figure>\n<p>Then Go to Model Providers and select the <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2024\/07\/local-llm-deployment-with-ollama\/\" target=\"_blank\" rel=\"noreferrer noopener\">LLM model<\/a> that you want to use, We are using Groq here and paste its API key.<\/p>\n<p>Then Go to System Model settings and select the chat model from there.<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1600\" height=\"773\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132929.136.webp\" alt=\"System Model settings\" class=\"wp-image-227160\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132929.136.webp 1600w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132929.136-300x145.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132929.136-768x371.webp 768w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132929.136-1536x742.webp 1536w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T132929.136-150x72.webp 150w\" sizes=\"auto, (max-width: 1600px) 100vw, 1600px\"\/><\/figure>\n<\/div>\n<p>Now go to datasets and upload the pdf you want, then click on the Play button near the Parsing status column and wait for the pdf to get parsed.<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1600\" height=\"838\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133010.200.webp\" alt=\"Dataset\" class=\"wp-image-227161\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133010.200.webp 1600w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133010.200-300x157.webp 300w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133010.200-768x402.webp 768w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133010.200-1536x804.webp 1536w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133010.200-150x79.webp 150w\" sizes=\"auto, (max-width: 1600px) 100vw, 1600px\"\/><\/figure>\n<\/div>\n<p>Now go to the chat section create an assistant there, Give it a name and also select the knowledge base that you created.<\/p>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"695\" height=\"962\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133059.001.webp\" alt=\"Chat Configurations\" class=\"wp-image-227162\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133059.001.webp 695w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133059.001-217x300.webp 217w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/unnamed-2025-03-20T133059.001-150x208.webp 150w\" sizes=\"auto, (max-width: 695px) 100vw, 695px\"\/><\/figure>\n<\/div>\n<p>Then create a new chat and ask the question it will perform RAG over your knowledge base and answer accordingly.<\/p>\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1468\" height=\"1088\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/337628841-2f6baa3e-1092-4f11-866d-36f6a9d075e5.gif\" alt=\"\" class=\"wp-image-227156\"\/><\/figure>\n<h2 class=\"wp-block-heading\" id=\"h-conclusion\">Conclusion<\/h2>\n<p><a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2025\/02\/types-of-chunking-for-rag-systems\/\" target=\"_blank\" rel=\"noreferrer noopener\">RAG<\/a> has become an important technology for custom enterprise datasets in recent times, hence the need for RAG frameworks has increased drastically. Frameworks like LangChain, LlamaIndex, LangGraph, Haystack, and RAGFlow represent significant advancements in AI applications. By using these frameworks, developers can create systems that provide accurate and relevant information. As AI continues to evolve, these tools will play an important role in shaping intelligent applications.<\/p>\n<div class=\"border-top py-3 author-info my-4\">\n<div class=\"author-card d-flex align-items-center\">\n<div class=\"flex-shrink-0 overflow-hidden\">\n                                    <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/author\/harsh9480979\/\" class=\"text-decoration-none active-avatar\"><br \/>\n                                                                       <img decoding=\"async\" src=\"https:\/\/av-eks-lekhak.s3.amazonaws.com\/media\/lekhak-profile-images\/converted_image_0fBqNLi.webp\" width=\"48\" height=\"48\" alt=\"Harsh Mishra\" loading=\"lazy\" class=\"rounded-circle\"\/><\/p>\n<p>                                <\/a>\n                                <\/div>\n<\/p><\/div>\n<p>Harsh Mishra is an AI\/ML Engineer who spends more time talking to Large Language Models than actual humans. Passionate about GenAI, NLP, and making machines smarter (so they don\u2019t replace him just yet). When not optimizing models, he\u2019s probably optimizing his coffee intake. \ud83d\ude80\u2615<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<p><h4 class=\"fs-24 text-dark\">Login to continue reading and enjoy expert-curated content.<\/h4>\n<p>                        <button class=\"btn btn-primary mx-auto d-table\" data-bs-toggle=\"modal\" data-bs-target=\"#loginModal\" id=\"readMoreBtn\">Keep Reading for Free<\/button>\n                    <\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>RAG has become a popular technology in 2025, it avoids the fine-tuning of the model which is expensive as well as time-consuming. There\u2019s an increased demand for RAG frameworks in the current scenario, Lets Understand what are these. Retrieval-augmented generation (RAG) frameworks are essential tools in the field of artificial intelligence. They enhance the capabilities [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":145603,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[12033],"tags":[15834,20840,32726,213],"dealstore":[],"offerexpiration":[],"class_list":["post-145602","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-analytics","tag-applications","tag-frameworks","tag-rag","tag-top"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Top 5 RAG Frameworks for AI Applications - Som2ny Network<\/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:\/\/fivemor.com\/?p=145602\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Top 5 RAG Frameworks for AI Applications - Som2ny Network\" \/>\n<meta property=\"og:description\" content=\"RAG has become a popular technology in 2025, it avoids the fine-tuning of the model which is expensive as well as time-consuming. There\u2019s an increased demand for RAG frameworks in the current scenario, Lets Understand what are these. Retrieval-augmented generation (RAG) frameworks are essential tools in the field of artificial intelligence. They enhance the capabilities [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/fivemor.com\/?p=145602\" \/>\n<meta property=\"og:site_name\" content=\"Som2ny Network\" \/>\n<meta property=\"article:published_time\" content=\"2025-03-20T11:45:52+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"872\" \/>\n\t<meta property=\"og:image:height\" content=\"473\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"9 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/fivemor.com\/?p=145602#article\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/?p=145602\"},\"author\":{\"name\":\"admin\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\"},\"headline\":\"Top 5 RAG Frameworks for AI Applications\",\"datePublished\":\"2025-03-20T11:45:52+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=145602\"},\"wordCount\":824,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=145602#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp\",\"keywords\":[\"Applications\",\"Frameworks\",\"RAG\",\"Top\"],\"articleSection\":[\"Analytics\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/fivemor.com\/?p=145602#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/fivemor.com\/?p=145602\",\"url\":\"https:\/\/fivemor.com\/?p=145602\",\"name\":\"Top 5 RAG Frameworks for AI Applications - Som2ny Network\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=145602#primaryimage\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=145602#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp\",\"datePublished\":\"2025-03-20T11:45:52+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/fivemor.com\/?p=145602#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/fivemor.com\/?p=145602\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/?p=145602#primaryimage\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp\",\"width\":872,\"height\":473},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/fivemor.com\/?p=145602#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/fivemor.com\/?bp_activities=1\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Top 5 RAG Frameworks for AI Applications\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/fivemor.com\/#website\",\"url\":\"https:\/\/fivemor.com\/\",\"name\":\"Som2ny Network\",\"description\":\"Daily Deals\",\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/fivemor.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/fivemor.com\/#organization\",\"name\":\"Som2ny Network\",\"url\":\"https:\/\/fivemor.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png\",\"width\":300,\"height\":86,\"caption\":\"Som2ny Network\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png\",\"caption\":\"admin\"},\"sameAs\":[\"https:\/\/fivemor.com\"],\"url\":\"https:\/\/fivemor.com\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Top 5 RAG Frameworks for AI Applications - Som2ny Network","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:\/\/fivemor.com\/?p=145602","og_locale":"en_US","og_type":"article","og_title":"Top 5 RAG Frameworks for AI Applications - Som2ny Network","og_description":"RAG has become a popular technology in 2025, it avoids the fine-tuning of the model which is expensive as well as time-consuming. There\u2019s an increased demand for RAG frameworks in the current scenario, Lets Understand what are these. Retrieval-augmented generation (RAG) frameworks are essential tools in the field of artificial intelligence. They enhance the capabilities [&hellip;]","og_url":"https:\/\/fivemor.com\/?p=145602","og_site_name":"Som2ny Network","article_published_time":"2025-03-20T11:45:52+00:00","og_image":[{"width":872,"height":473,"url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp","type":"image\/webp"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Est. reading time":"9 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/fivemor.com\/?p=145602#article","isPartOf":{"@id":"https:\/\/fivemor.com\/?p=145602"},"author":{"name":"admin","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371"},"headline":"Top 5 RAG Frameworks for AI Applications","datePublished":"2025-03-20T11:45:52+00:00","mainEntityOfPage":{"@id":"https:\/\/fivemor.com\/?p=145602"},"wordCount":824,"commentCount":0,"publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"image":{"@id":"https:\/\/fivemor.com\/?p=145602#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp","keywords":["Applications","Frameworks","RAG","Top"],"articleSection":["Analytics"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/fivemor.com\/?p=145602#respond"]}]},{"@type":"WebPage","@id":"https:\/\/fivemor.com\/?p=145602","url":"https:\/\/fivemor.com\/?p=145602","name":"Top 5 RAG Frameworks for AI Applications - Som2ny Network","isPartOf":{"@id":"https:\/\/fivemor.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/fivemor.com\/?p=145602#primaryimage"},"image":{"@id":"https:\/\/fivemor.com\/?p=145602#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp","datePublished":"2025-03-20T11:45:52+00:00","breadcrumb":{"@id":"https:\/\/fivemor.com\/?p=145602#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/fivemor.com\/?p=145602"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/?p=145602#primaryimage","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Collage.webp.webp","width":872,"height":473},{"@type":"BreadcrumbList","@id":"https:\/\/fivemor.com\/?p=145602#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/fivemor.com\/?bp_activities=1"},{"@type":"ListItem","position":2,"name":"Top 5 RAG Frameworks for AI Applications"}]},{"@type":"WebSite","@id":"https:\/\/fivemor.com\/#website","url":"https:\/\/fivemor.com\/","name":"Som2ny Network","description":"Daily Deals","publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/fivemor.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/fivemor.com\/#organization","name":"Som2ny Network","url":"https:\/\/fivemor.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/#\/schema\/logo\/image\/","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2026\/07\/4a0953c4-logo-300x86-1.png","width":300,"height":86,"caption":"Som2ny Network"},"image":{"@id":"https:\/\/fivemor.com\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371","name":"admin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/729ae85bf62b9917e93538db2f2688ca?s=96&r=g&default=https%3A%2F%2Ffivemor.com%2Fwp-content%2Fplugins%2Fbuddypress-first-letter-avatar%2Fimages%2Fdefault%2F96%2Flatin_a.png","caption":"admin"},"sameAs":["https:\/\/fivemor.com"],"url":"https:\/\/fivemor.com\/?author=1"}]}},"_links":{"self":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/145602","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=145602"}],"version-history":[{"count":0,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/145602\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/media\/145603"}],"wp:attachment":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=145602"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=145602"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=145602"},{"taxonomy":"dealstore","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fdealstore&post=145602"},{"taxonomy":"offerexpiration","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fofferexpiration&post=145602"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}