{"id":139378,"date":"2025-03-17T10:22:58","date_gmt":"2025-03-17T10:22:58","guid":{"rendered":"https:\/\/peraltafinancing.com\/analytics\/comparison-of-gemini-embedding-with-multilingual-e5-large-jina\/"},"modified":"2025-03-17T10:22:58","modified_gmt":"2025-03-17T10:22:58","slug":"comparison-of-gemini-embedding-with-multilingual-e5-large-jina","status":"publish","type":"post","link":"https:\/\/fivemor.com\/?p=139378","title":{"rendered":"Comparison of Gemini Embedding with Multilingual-e5-large &#038; Jina"},"content":{"rendered":"<p> <br \/>\n<\/p>\n<div id=\"article-start\">\n<p>Word embeddings for Indic languages like Hindi are crucial for advancing Natural Language Processing (NLP) tasks such as machine translation, question answering, and information retrieval. These embeddings capture semantic properties of words, enabling more accurate and context-aware NLP applications. Given the vast number of Hindi speakers and the growing digital content in Indic languages, high-quality embeddings are essential for improving NLP performance in these languages. Customized embeddings can particularly address the unique linguistic features and resource constraints of Indic languages. The <a href=\"https:\/\/developers.googleblog.com\/en\/gemini-embedding-text-model-now-available-gemini-api\/\" target=\"_blank\" rel=\"nofollow noopener\">newly released Gemini Embedding model<\/a> represents a significant advancement in multilingual text embeddings, leveraging Google\u2019s powerful Gemini AI framework to deliver state-of-the-art performance across over 100 languages. <\/p>\n<p>Gemini Embedding model excels in tasks such as classification, retrieval, and semantic search, offering enhanced efficiency and accuracy. By supporting larger input sizes and higher-dimensional outputs, Gemini Embedding provides richer text representations, making it highly versatile for diverse applications.<\/p>\n<h4 class=\"wp-block-heading\" id=\"h-learning-objectives\">Learning Objectives<\/h4>\n<ul class=\"wp-block-list\">\n<li>Introduction to Gemini Embeddings and their integration with the Gemini LLM.<\/li>\n<li>Hands-on tutorial on retrieving Hindi documents using Gemini Embeddings.<\/li>\n<li>Comparative analysis with Jina AI embeddings and Multilingual-e5-large.<\/li>\n<li>Insights into capabilities and applications in multilingual text retrieval.<\/li>\n<\/ul>\n<p><em><strong>This article was published as a part of the\u00a0<\/strong><\/em><a href=\"https:\/\/www.analyticsvidhya.com\/datahack\/blogathon\" target=\"_blank\" rel=\"noreferrer noopener\"><em><strong>Data Science Blogathon.<\/strong><\/em><\/a><\/p>\n<h2 class=\"wp-block-heading\" id=\"h-what-are-gemini-embeddings\">What are Gemini Embeddings?<\/h2>\n<p>In March 2025, Google released a new experimental Gemini Embedding text model (gemini-embedding-exp-03-07)\u00a0available in the <a href=\"https:\/\/www.analyticsvidhya.com\/blog\/2025\/03\/image-generation-with-gemini-2-0-flash-experimental\/\" target=\"_blank\" rel=\"noreferrer noopener\">Gemini<\/a> API.<br \/>Developed from the Gemini model, this advanced embedding model is claimed to have inherited Gemini\u2019s profound grasp of language and subtle contextual nuances, rendering it versatile for diverse applications. It has grabbed the top position on the <a href=\"https:\/\/huggingface.co\/spaces\/mteb\/leaderboard\" target=\"_blank\" rel=\"nofollow noopener\">MTEB Multilingual leaderboard<\/a>.<\/p>\n<p>Gemini Embedding represents text as dense vectors where semantically similar text inputs<br \/>are mapped to vectors near one another in the vector space. Currently it supports more than 100+<br \/>languages, and its embeddings can be used for various tasks such as retrieval and classification.<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-key-features-of-gemini-embeddings\">Key Features of Gemini Embeddings<\/h2>\n<ul class=\"wp-block-list\">\n<li><b>Robust multilingual capabilities<\/b>:  model showcases outstanding performance in more\u00a0than 100 languages, excelling not only\u00a0in high-resource languages like English but also in\u00a0low-resource languages such as Assamese and\u00a0Macedonian.<\/li>\n<li><b>Handle upto 8000 Input Tokens<\/b>: This substantial capacity enables the model to seamlessly handle lengthy documents or intricate queries without truncation, thereby maintaining context and meaning in a manner that surpasses many existing embedding models.<\/li>\n<li><b>Output dimensions of 3K dimensions<\/b>: The model generates embeddings with a dimensionality of up to 3,072, offering support for sub-dimensions like 768 and 1,536 to allow for task-specific optimization.<\/li>\n<li><b>Impressive Performance.<\/b> Gemini Embedding tops the Massive Text Embedding Benchmark (MTEB) with a mean task score of 68.32, surpassing its nearest competitors by a substantial margin.<\/li>\n<\/ul>\n<h2 class=\"wp-block-heading\" id=\"h-model-architecture-of-gemini-embeddings\">Model Architecture of Gemini Embeddings<\/h2>\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"605\" height=\"631\" src=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/image-59.webp\" alt=\"Transformer\" class=\"wp-image-226595\" srcset=\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/image-59.webp 605w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/image-59-288x300.webp 288w, https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/03\/image-59-150x156.webp 150w\" sizes=\"auto, (max-width: 605px) 100vw, 605px\"\/><figcaption class=\"wp-element-caption\">Source: Google<\/figcaption><\/figure>\n<\/div>\n<p>At its core, Gemini Embedding is built on a transformer architecture, initialized from the Gemini LLM. This foundation provides the model with a deep understanding of language structure and semantics. The model uses bidirectional attention mechanisms to process input sequences, allowing it to consider the full context of a word or phrase when generating embeddings.<\/p>\n<ol class=\"wp-block-list\">\n<li>An input sequence T of \ud835\udc3f tokens is processed by M, a transformer with bidirectional attention<br \/>initialized from Gemini, producing a sequence of token embeddings.<\/li>\n<li>To generate a single embedding representing all the information in the input, a pooling function is applied<\/li>\n<li>Finally, a linear projection is applied to scale the embedding to the target dimension, resulting in the final output embedding.<\/li>\n<\/ol>\n<p><b>Loss Function<\/b>. The Gemini Embedding model was trained with a noise-contrastive estimation (NCE) loss with in-batch negatives. The exact loss differs slightly depending on the stage of training. In general, a training example includes a query, a positive target and (optionally) a hard negative target.<\/p>\n<h4 class=\"wp-block-heading\" id=\"h-training-strategy\">Training Strategy<\/h4>\n<ol class=\"wp-block-list\">\n<li><b>Pre-Finetuning<\/b>: During this stage, the model is trained on a vast and varied dataset comprising query-target pairs. This exposure tunes the large language model\u2019s parameters for encoding tasks, establishing a foundation for its adaptability.<\/li>\n<li><b>Fine-Tuning: <\/b>In the second stage, the model undergoes fine-tuning using task-specific datasets that include query-positive-hard negative triples. This process employs smaller batch sizes and meticulously curated datasets to boost performance on targeted tasks.<\/li>\n<\/ol>\n<p>Also Read: <a href=\"https:\/\/www.arxiv.org\/pdf\/2503.07891\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Gemini Embedding: Generalizable Embeddings from Gemini<\/a><\/p>\n<h2 class=\"wp-block-heading\" id=\"h-comparison-with-other-multilingual-embedding-models\">Comparison with Other Multilingual Embedding Models<\/h2>\n<p>We compare the retrieval from Hindi Documents with the newly released state of the art Gemini Embeddings and then compare it against <a href=\"https:\/\/jina.ai\/embeddings\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Jina AI Embeddings<\/a> &amp; <a href=\"https:\/\/huggingface.co\/intfloat\/multilingual-e5-large\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Multilingual-e5-large embeddings<\/a>. As shown in the Table below, with respect to the number of max tokens, Gemini Embeddings and Jina AI embeddings are high, enabling the models to handle long documents or intricate queries. In terms. Also as seen from the Table below, the Gemini embeddings have a higher embedding dimension that can capture more nuanced and fine-grained semantic relationships between words, enabling models to represent complex linguistic patterns and subtle distinctions in meaning.<\/p>\n<div class=\"table-responsive mb-3\">\n<table class=\"table table-bordered border-black table-striped\">\n<thead\/>\n<tbody>\n<tr>\n<td>\u00a0<\/td>\n<td><b>Number of Parameters<\/b><\/td>\n<td><b>Embedding Dimension<\/b><\/td>\n<td><b>Max Tokens<\/b><\/td>\n<td><b>Number of Languages<\/b><\/td>\n<td><b>Matryoshka Embeddings<\/b><\/td>\n<\/tr>\n<tr>\n<td><b>gemini-embedding-exp-03-07<\/b><\/td>\n<td>Unknown<\/td>\n<td>3072<\/td>\n<td>8192<\/td>\n<td>100<\/td>\n<td>\u00a0Enables truncation to various sizes, such as 2048, 1024, 512, 256, and 128 dimensions,<\/td>\n<\/tr>\n<tr>\n<td><b>jinaai\/jina-embeddings-v3<\/b><\/td>\n<td>572M<\/td>\n<td>1024<\/td>\n<td>8194<\/td>\n<td>100<\/td>\n<td>\u00a0 Supports flexible embedding sizes (32, 64, 128, 256, 512, 768, 1024), allowing for truncating embeddings to fit your application\u00a0 \u00a0\u00a0<\/td>\n<\/tr>\n<tr>\n<td><b>multilingual-e5-large-instruct<\/b><\/td>\n<td>560M<\/td>\n<td>1024<\/td>\n<td>514<\/td>\n<td>94<\/td>\n<td>NA<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h2 class=\"wp-block-heading\" id=\"h-retrieval-with-gemini-embeddings-amp-comparison-with-jina-ai-embeddings-amp-multilingual-e5-large\">Retrieval with Gemini Embeddings &amp; Comparison with Jina AI Embeddings &amp; Multilingual-e5-large<\/h2>\n<p>In the following hands on tutorial, we will compare retrieval from Hindi Documents with the newly released state of the art Gemini Embeddings and then compare it against Jina AI Embeddings &amp; Multilingual-e5-large embeddings.<\/p>\n<h3 class=\"wp-block-heading\" id=\"h-step-1-install-necessary-libraries\">Step 1. Install Necessary Libraries<\/h3>\n<pre class=\"wp-block-code\"><code>!pip install langchain-community\n!pip install chromadb<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-step-2-loading-the-data\">Step 2. Loading the Data<\/h3>\n<p>We use Hindi data from a <a href=\"https:\/\/ckbirlahospitals.com\/rbh\/blog\/pregnancy-early-symptoms-in-hindi\" target=\"_blank\" rel=\"nofollow noopener\">website<\/a> to assess how the Gemini Embeddings perform with respect to retrieval in Hindi Language.<\/p>\n<pre class=\"wp-block-code\"><code>from langchain_community.document_loaders import WebBaseLoader\n\nloader = WebBaseLoader(\"https:\/\/ckbirlahospitals.com\/rbh\/blog\/pregnancy-early-symptoms-in-hindi\")\ndata = loader.load()<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-step-3-chunking-the-data\">Step 3. Chunking the Data<\/h3>\n<p>The code below uses the\u00a0RecursiveCharacterTextSplitter\u00a0to split large text documents into smaller chunks of 500 characters each, with no overlap. It then applies this splitting to the\u00a0data\u00a0variable and stores the results in\u00a0all_splits. We use only 10 of the splits because of the rate limits in Gemini Embedding API.<\/p>\n<pre class=\"wp-block-code\"><code>from langchain_text_splitters import RecursiveCharacterTextSplitter\n\ntext_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\nall_splits = text_splitter.split_documents(data)\nall_splits = all_splits[:10]<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-step-4-storing-the-data-in-a-vector-db\">Step 4. Storing the Data in a Vector DB<\/h3>\n<p>We first create a class \u201cGeminiEmbeddingFunction\u201d that helps in querying the Gemini Embedding API and returns the values of the embeddings for the input query. We then create a function \u201ccreate_chroma_db\u201d for creating a collection in ChromaDB that will store the data along with the embeddings.<\/p>\n<pre class=\"wp-block-code\"><code>import chromadb\nfrom chromadb import Documents, EmbeddingFunction, Embeddings\n\nclass GeminiEmbeddingFunction(EmbeddingFunction):\n  def __call__(self, input: Documents) -&gt; Embeddings:\n    title = \"Custom query\"  \n    return client.models.embed_content(\n        model=\"gemini-embedding-exp-03-07\",\n        contents=input).embeddings[0].values\n        \n \n\ndef create_chroma_db(documents, name):\n  chroma_client = chromadb.Client()\n  db = chroma_client.create_collection(name=name, embedding_function=GeminiEmbeddingFunction())\n  for i, d in enumerate(documents):\n    db.add(\n      documents=d.page_content,\n      ids=str(i)\n    )\n  return db\n\ndb = create_chroma_db(all_splits, \"datab\")<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-step-5-querying-the-db\">Step 5. Querying the DB<\/h3>\n<pre class=\"wp-block-code\"><code>def get_relevant_passage(query, db):\n  passage = db.query(query_texts=[query], n_results=1)['documents'][0][0]\n\n  return passage\n\npassage = get_relevant_passage(\"\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\", db)\nprint(passage)<\/code><\/pre>\n<h3 class=\"wp-block-heading\" id=\"h-step-6-comparing-with-jina-ai-embeddings\">Step 6. Comparing with Jina AI Embeddings<\/h3>\n<p>The code below defines a custom embedding function using a Hugging Face transformer model and a method for processing text inputs to generate embeddings.<\/p>\n<ol class=\"wp-block-list\">\n<li>The AutoTokenizer and AutoModel from transformers are used to load a pretrained model (jinaai\/jina-embeddings-v3) and EmbeddingFunction from chromadb is imported for creating custom embeddings.<\/li>\n<li>average_pool function: This function aggregates the hidden states from the model by performing a pooling operation on them, averaging over the sequence length while considering the attention mask (ignoring padding tokens).<\/li>\n<li>CustomHuggingFace class: It tokenizes the text, feeds it through the model, and computes the embeddings using the average_pool function. The result is returned as a list of embeddings.<\/li>\n<\/ol>\n<pre class=\"wp-block-code\"><code>from transformers import AutoTokenizer, AutoModel\nfrom chromadb import EmbeddingFunction\n\n\ntokenizer = AutoTokenizer.from_pretrained('jinaai\/jina-embeddings-v3')\nmodel = AutoModel.from_pretrained('jinaai\/jina-embeddings-v3')\n\n\n# the model returns many hidden states per document so we must aggregate them\ndef average_pool(last_hidden_states, attention_mask):\n    last_hidden = last_hidden_states.masked_fill(~attention_mask[...,None].bool(), 0.0)\n    return last_hidden.sum(dim=1) \/ attention_mask.sum(dim=1)[...,None]\n\nclass CustomHuggingFace(EmbeddingFunction):\n    def __call__(self, texts):\n        queries    = [f'query: {text}' for text in texts]         \n        batch_dict = tokenizer(texts, max_length=512, padding=True, truncation=True, return_tensors=\"pt\")\n        outputs    = model(**batch_dict)        \n        embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])\n        return embeddings.tolist()<\/code><\/pre>\n<p><b>Querying<\/b><\/p>\n<pre class=\"wp-block-code\"><code>def get_relevant_passage(query, db):\n  passage = db.query(query_texts=[query], n_results=1)['documents'][0][0]\n\n  return passage\n\npassage = get_relevant_passage(\"\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\", db)\nprint(passage)<\/code><\/pre>\n<p>\u00a0 For selecting the <b>Multilingual-e5-large embeddings<\/b>, we can just replace the tokenizer and model as \u201cintfloat\/multilingual-e5-large-instruct\u201d\u00a0\u00a0<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-comparison-of-outputs-in-retrieval-from-the-embeddings\">Comparison of Outputs in Retrieval From the Embeddings<\/h2>\n<div class=\"table-responsive mb-3\">\n<table class=\"table table-bordered border-black table-striped\">\n<thead\/>\n<tbody>\n<tr>\n<td><b>Question Number<\/b><\/td>\n<td><b>Query<\/b><\/td>\n<td><b>Gemini Embeddings<\/b><\/td>\n<td><b>jinaai\/jina-embeddings-v3<\/b><\/td>\n<td><b>intfloat\/multilingual-e5-large-instruct<\/b><\/td>\n<\/tr>\n<tr>\n<td>1<\/td>\n<td><b>\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?<\/b><\/td>\n<td>\u00a0 \u092f\u0926\u093f \u0906\u092a \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 (early symptoms of pregnancy) \u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0935\u093f\u0938\u094d\u0924\u093e\u0930 \u0938\u0947 \u091c\u093e\u0928\u0928\u093e \u091a\u093e\u0939\u0924\u0947 \u0939\u0948\u0902, \u0924\u094b \u092f\u0939 \u092c\u094d\u0932\u0949\u0917 \u0906\u092a\u0915\u0947 \u0932\u093f\u090f \u0959\u093e\u0938 \u0939\u0948\u0964<br \/>\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f? \u2013 <b>WRONG<\/b><\/td>\n<td>\u00a0 \u092f\u0926\u093f \u0906\u092a \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 (early symptoms of pregnancy) \u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0935\u093f\u0938\u094d\u0924\u093e\u0930 \u0938\u0947 \u091c\u093e\u0928\u0928\u093e \u091a\u093e\u0939\u0924\u0947 \u0939\u0948\u0902, \u0924\u094b \u092f\u0939 \u092c\u094d\u0932\u0949\u0917 \u0906\u092a\u0915\u0947 \u0932\u093f\u090f \u0959\u093e\u0938 \u0939\u0948\u0964\\n\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f? \u2013 <b>WRONG<\/b><\/td>\n<td>\u00a0 \u092f\u0926\u093f \u0906\u092a \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 (early symptoms of pregnancy) \u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0935\u093f\u0938\u094d\u0924\u093e\u0930 \u0938\u0947 \u091c\u093e\u0928\u0928\u093e \u091a\u093e\u0939\u0924\u0947 \u0939\u0948\u0902, \u0924\u094b \u092f\u0939 \u092c\u094d\u0932\u0949\u0917 \u0906\u092a\u0915\u0947 \u0932\u093f\u090f \u0959\u093e\u0938 \u0939\u0948\u0964<br \/>\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f? \u2013 <b>WRONG<\/b><\/td>\n<\/tr>\n<tr>\n<td>2<\/td>\n<td><b>Pregnancy \u0915\u0947 kuch symptoms \u0915\u094d\u092f\u093e \u0939\u094b\u0924\u0947 \u0939\u0948\u0902?<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0915\u0908 \u0939\u093e\u0930\u094d\u092e\u094b\u0928\u0932 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u092e\u0947\u0902 \u091c\u0940 \u092e\u091a\u0932\u0928\u093e, \u0909\u0932\u094d\u091f\u0940 \u0906\u0928\u093e, \u092c\u093e\u0930-\u092c\u093e\u0930 \u092a\u0947\u0936\u093e\u092c \u0906\u0928\u093e, \u0914\u0930 \u0925\u0915\u093e\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0936\u093e\u092e\u093f\u0932 \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u092e \u0907\u0938 \u092c\u094d\u0932\u0949\u0917 \u092e\u0947\u0902 \u092c\u093e\u0924 \u092d\u0940 \u0915\u0930\u0928\u0947 \u0935\u093e\u0932\u0947 \u0939\u0948\u0902\u0964 \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0938\u0902\u0915\u0947\u0924: \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u0915\u0940 \u092a\u0942\u0930\u0940 \u091c\u093e\u0928\u0915\u093e\u0930\u0940! Home Quick Enquiry Patient LoginCall Us: 08062136530 Emergency No: 07340054470 Open main menuServicesPatients &amp; VisitorsInternational Patients About Us Book an Appointment Call BackWhatsApp \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0942\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u091c\u093e\u0928\u0947\u0964Obstetrics and Gynaecology |by Dr. C. P. Dadhich| Published on 06\/02\/2025Table of Contents\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u2013 <b>WRONG<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0915\u0908 \u0939\u093e\u0930\u094d\u092e\u094b\u0928\u0932 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u092e\u0947\u0902 \u091c\u0940 \u092e\u091a\u0932\u0928\u093e, \u0909\u0932\u094d\u091f\u0940 \u0906\u0928\u093e, \u092c\u093e\u0930-\u092c\u093e\u0930 \u092a\u0947\u0936\u093e\u092c \u0906\u0928\u093e, \u0914\u0930 \u0925\u0915\u093e\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0936\u093e\u092e\u093f\u0932 \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u092e \u0907\u0938 \u092c\u094d\u0932\u0949\u0917 \u092e\u0947\u0902 \u092c\u093e\u0924 \u092d\u0940 \u0915\u0930\u0928\u0947 \u0935\u093e\u0932\u0947 \u0939\u0948\u0902\u0964 \u2013 <b>CORRECT<\/b><\/td>\n<\/tr>\n<tr>\n<td>3<\/td>\n<td><b>\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u090f\u0902\u091f\u0940\u092c\u093e\u092f\u094b\u091f\u093f\u0915 \u0926\u0935\u093e \u0932\u0947\u0928\u0947 \u0938\u0947 \u0915\u092c \u092c\u091a\u0928\u093e \u091a\u093e\u0939\u093f\u090f?<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u092a\u0939\u0932\u0947 \u0915\u0941\u091b \u0926\u093f\u0928\u094b\u0902 \u092e\u0947\u0902 \u0905\u0902\u0921\u093e \u0938\u094d\u092a\u0930\u094d\u092e \u0938\u0947 \u092b\u0930\u094d\u091f\u093f\u0932\u093e\u0907\u091c \u0939\u094b\u0924\u093e \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u0915\u093e\u0930\u0923 \u092c\u094d\u0932\u0940\u0921\u093f\u0902\u0917 \u0914\u0930 \u092a\u0947\u091f \u092e\u0947\u0902 \u0910\u0902\u0920\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0926\u093f\u0916\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938 \u0926\u094c\u0930\u093e\u0928 \u0938\u094d\u0935\u0938\u094d\u0925 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0932\u093f\u090f \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948 \u0915\u093f \u0935\u0939 \u090f\u0902\u091f\u0940\u092c\u093e\u092f\u094b\u091f\u093f\u0915 \u0926\u0935\u093e \u0932\u0947\u0928\u0947 \u0938\u0947 \u092c\u091a\u0947\u0902, \u0915\u094d\u092f\u094b\u0902\u0915\u093f \u0907\u0938\u0938\u0947 \u092e\u093e\u0902 \u0914\u0930 \u092c\u091a\u094d\u091a\u0947 \u0926\u094b\u0928\u094b\u0902 \u0915\u094b \u0939\u0940 \u0916\u0924\u0930\u093e \u0939\u094b \u0938\u0915\u0924\u093e \u0939\u0948\u0964\u00a0<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923<br \/>\u0939\u092e\u0947\u0936\u093e \u092a\u0940\u0930\u093f\u092f\u0921 \u0915\u093e \u092e\u093f\u0938 \u0939\u094b\u0928\u093e \u092f\u093e \u0909\u0932\u094d\u091f\u0940 \u0939\u094b\u0928\u093e \u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0928\u0939\u0940\u0902 \u0939\u094b\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938\u0915\u0947 \u0905\u0924\u093f\u0930\u093f\u0915\u094d\u0924 \u0905\u0928\u094d\u092f \u0932\u0915\u094d\u0937\u0923 \u092d\u0940 \u0939\u094b \u0938\u0915\u0924\u0947 \u0939\u0948\u0902, \u091c\u093f\u0928 \u092a\u0930 \u0927\u094d\u092f\u093e\u0928 \u0926\u0947\u0928\u093e \u092c\u0939\u0941\u0924 \u091c\u094d\u092f\u093e\u0926\u093e \u091c\u0930\u0942\u0930\u0940 \u0939\u094b\u0924\u093e \u0939\u0948 \u091c\u0948\u0938\u0947 \u0915\u093f \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u092a\u0939\u0932\u0947 \u0915\u0941\u091b \u0926\u093f\u0928\u094b\u0902 \u092e\u0947\u0902 \u0905\u0902\u0921\u093e \u0938\u094d\u092a\u0930\u094d\u092e \u0938\u0947 \u092b\u0930\u094d\u091f\u093f\u0932\u093e\u0907\u091c \u0939\u094b\u0924\u093e \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u0915\u093e\u0930\u0923 \u092c\u094d\u0932\u0940\u0921\u093f\u0902\u0917 \u0914\u0930 \u092a\u0947\u091f \u092e\u0947\u0902 \u0910\u0902\u0920\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0926\u093f\u0916\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938 \u0926\u094c\u0930\u093e\u0928 \u0938\u094d\u0935\u0938\u094d\u0925 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0932\u093f\u090f \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948 \u0915\u093f \u0935\u0939 \u090f\u0902\u091f\u0940\u092c\u093e\u092f\u094b\u091f\u093f\u0915 \u0926\u0935\u093e \u0932\u0947\u0928\u0947 \u0938\u0947 \u092c\u091a\u0947\u0902, \u0915\u094d\u092f\u094b\u0902\u0915\u093f \u0907\u0938\u0938\u0947 \u092e\u093e\u0902 \u0914\u0930 \u092c\u091a\u094d\u091a\u0947 \u0926\u094b\u0928\u094b\u0902 \u0915\u094b \u0939\u0940 \u0916\u0924\u0930\u093e \u0939\u094b \u0938\u0915\u0924\u093e \u0939\u0948\u0964\u00a0<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923<br \/>\u0939\u092e\u0947\u0936\u093e \u092a\u0940\u0930\u093f\u092f\u0921 \u0915\u093e \u092e\u093f\u0938 \u0939\u094b\u0928\u093e \u092f\u093e \u0909\u0932\u094d\u091f\u0940 \u0939\u094b\u0928\u093e \u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0928\u0939\u0940\u0902 \u0939\u094b\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938\u0915\u0947 \u0905\u0924\u093f\u0930\u093f\u0915\u094d\u0924 \u0905\u0928\u094d\u092f \u0932\u0915\u094d\u0937\u0923 \u092d\u0940 \u0939\u094b \u0938\u0915\u0924\u0947 \u0939\u0948\u0902, \u091c\u093f\u0928 \u092a\u0930 \u0927\u094d\u092f\u093e\u0928 \u0926\u0947\u0928\u093e \u092c\u0939\u0941\u0924 \u091c\u094d\u092f\u093e\u0926\u093e \u091c\u0930\u0942\u0930\u0940 \u0939\u094b\u0924\u093e \u0939\u0948 \u091c\u0948\u0938\u0947 \u0915\u093f \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u091c\u093f\u0928\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u0930 \u092e\u0939\u093f\u0932\u093e \u0915\u094b \u092a\u0924\u093e \u0939\u094b\u0928\u093e \u091a\u093e\u0939\u093f\u090f\u0964 \u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u0938\u0902\u092c\u0902\u0927 \u092e\u0947\u0902 \u0915\u093f\u0938\u0940 \u092d\u0940 \u092a\u094d\u0930\u0915\u093e\u0930 \u0915\u0940 \u0938\u092e\u0938\u094d\u092f\u093e \u0915\u0947 \u0932\u093f\u090f \u0939\u092e \u0906\u092a\u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0947\u0902\u0917\u0947 \u0915\u093f \u0906\u092a \u0939\u092e\u093e\u0930\u0947 \u0938\u094d\u0924\u094d\u0930\u0940 \u0930\u094b\u0917 \u0935\u093f\u0936\u0947\u0937\u091c\u094d\u091e \u0938\u0947 \u0938\u0902\u092a\u0930\u094d\u0915 \u0915\u0930\u0947\u0902 \u0914\u0930 \u0939\u0930 \u092a\u094d\u0930\u0915\u093e\u0930 \u0915\u0940 \u091c\u091f\u093f\u0932\u0924\u093e\u0913\u0902 \u0915\u094b \u0926\u0942\u0930 \u092d\u0917\u093e\u090f\u0902\u0964 \u2013 <b>WRONG<\/b><\/td>\n<\/tr>\n<tr>\n<td>4<\/td>\n<td><b>\u0915\u092c \u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u092e\u0947\u0902 \u090f\u0902\u091f\u0940\u092c\u093e\u092f\u094b\u091f\u093f\u0915 \u0926\u0935\u093e \u0932\u0947\u0928\u0947 \u0938\u0947 \u092c\u091a\u093e\u092f\u093e \u091c\u093e\u090f?<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u092a\u0939\u0932\u0947 \u0915\u0941\u091b \u0926\u093f\u0928\u094b\u0902 \u092e\u0947\u0902 \u0905\u0902\u0921\u093e \u0938\u094d\u092a\u0930\u094d\u092e \u0938\u0947 \u092b\u0930\u094d\u091f\u093f\u0932\u093e\u0907\u091c \u0939\u094b\u0924\u093e \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u0915\u093e\u0930\u0923 \u092c\u094d\u0932\u0940\u0921\u093f\u0902\u0917 \u0914\u0930 \u092a\u0947\u091f \u092e\u0947\u0902 \u0910\u0902\u0920\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0926\u093f\u0916\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938 \u0926\u094c\u0930\u093e\u0928 \u0938\u094d\u0935\u0938\u094d\u0925 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0932\u093f\u090f \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948 \u0915\u093f \u0935\u0939 \u090f\u0902\u091f\u0940\u092c\u093e\u092f\u094b\u091f\u093f\u0915 \u0926\u0935\u093e \u0932\u0947\u0928\u0947 \u0938\u0947 \u092c\u091a\u0947\u0902, \u0915\u094d\u092f\u094b\u0902\u0915\u093f \u0907\u0938\u0938\u0947 \u092e\u093e\u0902 \u0914\u0930 \u092c\u091a\u094d\u091a\u0947 \u0926\u094b\u0928\u094b\u0902 \u0915\u094b \u0939\u0940 \u0916\u0924\u0930\u093e \u0939\u094b \u0938\u0915\u0924\u093e \u0939\u0948\u0964\u00a0<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923<br \/>\u0939\u092e\u0947\u0936\u093e \u092a\u0940\u0930\u093f\u092f\u0921 \u0915\u093e \u092e\u093f\u0938 \u0939\u094b\u0928\u093e \u092f\u093e \u0909\u0932\u094d\u091f\u0940 \u0939\u094b\u0928\u093e \u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0928\u0939\u0940\u0902 \u0939\u094b\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938\u0915\u0947 \u0905\u0924\u093f\u0930\u093f\u0915\u094d\u0924 \u0905\u0928\u094d\u092f \u0932\u0915\u094d\u0937\u0923 \u092d\u0940 \u0939\u094b \u0938\u0915\u0924\u0947 \u0939\u0948\u0902, \u091c\u093f\u0928 \u092a\u0930 \u0927\u094d\u092f\u093e\u0928 \u0926\u0947\u0928\u093e \u092c\u0939\u0941\u0924 \u091c\u094d\u092f\u093e\u0926\u093e \u091c\u0930\u0942\u0930\u0940 \u0939\u094b\u0924\u093e \u0939\u0948 \u091c\u0948\u0938\u0947 \u0915\u093f \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u092a\u0939\u0932\u0947 \u0915\u0941\u091b \u0926\u093f\u0928\u094b\u0902 \u092e\u0947\u0902 \u0905\u0902\u0921\u093e \u0938\u094d\u092a\u0930\u094d\u092e \u0938\u0947 \u092b\u0930\u094d\u091f\u093f\u0932\u093e\u0907\u091c \u0939\u094b\u0924\u093e \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u0915\u093e\u0930\u0923 \u092c\u094d\u0932\u0940\u0921\u093f\u0902\u0917 \u0914\u0930 \u092a\u0947\u091f \u092e\u0947\u0902 \u0910\u0902\u0920\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0926\u093f\u0916\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938 \u0926\u094c\u0930\u093e\u0928 \u0938\u094d\u0935\u0938\u094d\u0925 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0932\u093f\u090f \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948 \u0915\u093f \u0935\u0939 \u090f\u0902\u091f\u0940\u092c\u093e\u092f\u094b\u091f\u093f\u0915 \u0926\u0935\u093e \u0932\u0947\u0928\u0947 \u0938\u0947 \u092c\u091a\u0947\u0902, \u0915\u094d\u092f\u094b\u0902\u0915\u093f \u0907\u0938\u0938\u0947 \u092e\u093e\u0902 \u0914\u0930 \u092c\u091a\u094d\u091a\u0947 \u0926\u094b\u0928\u094b\u0902 \u0915\u094b \u0939\u0940 \u0916\u0924\u0930\u093e \u0939\u094b \u0938\u0915\u0924\u093e \u0939\u0948\u0964\u00a0<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923<br \/>\u0939\u092e\u0947\u0936\u093e \u092a\u0940\u0930\u093f\u092f\u0921 \u0915\u093e \u092e\u093f\u0938 \u0939\u094b\u0928\u093e \u092f\u093e \u0909\u0932\u094d\u091f\u0940 \u0939\u094b\u0928\u093e \u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0928\u0939\u0940\u0902 \u0939\u094b\u0924\u0947 \u0939\u0948\u0902\u0964 \u0907\u0938\u0915\u0947 \u0905\u0924\u093f\u0930\u093f\u0915\u094d\u0924 \u0905\u0928\u094d\u092f \u0932\u0915\u094d\u0937\u0923 \u092d\u0940 \u0939\u094b \u0938\u0915\u0924\u0947 \u0939\u0948\u0902, \u091c\u093f\u0928 \u092a\u0930 \u0927\u094d\u092f\u093e\u0928 \u0926\u0947\u0928\u093e \u092c\u0939\u0941\u0924 \u091c\u094d\u092f\u093e\u0926\u093e \u091c\u0930\u0942\u0930\u0940 \u0939\u094b\u0924\u093e \u0939\u0948 \u091c\u0948\u0938\u0947 \u0915\u093f \u2013 <b>CORRECT<\/b><\/td>\n<td>\u091c\u093f\u0928\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u0930 \u092e\u0939\u093f\u0932\u093e \u0915\u094b \u092a\u0924\u093e \u0939\u094b\u0928\u093e \u091a\u093e\u0939\u093f\u090f\u0964 \u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u0938\u0902\u092c\u0902\u0927 \u092e\u0947\u0902 \u0915\u093f\u0938\u0940 \u092d\u0940 \u092a\u094d\u0930\u0915\u093e\u0930 \u0915\u0940 \u0938\u092e\u0938\u094d\u092f\u093e \u0915\u0947 \u0932\u093f\u090f \u0939\u092e \u0906\u092a\u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0947\u0902\u0917\u0947 \u0915\u093f \u0906\u092a \u0939\u092e\u093e\u0930\u0947 \u0938\u094d\u0924\u094d\u0930\u0940 \u0930\u094b\u0917 \u0935\u093f\u0936\u0947\u0937\u091c\u094d\u091e \u0938\u0947 \u0938\u0902\u092a\u0930\u094d\u0915 \u0915\u0930\u0947\u0902 \u0914\u0930 \u0939\u0930 \u092a\u094d\u0930\u0915\u093e\u0930 \u0915\u0940 \u091c\u091f\u093f\u0932\u0924\u093e\u0913\u0902 \u0915\u094b \u0926\u0942\u0930 \u092d\u0917\u093e\u090f\u0902\u0964 \u2013 <b>WRONG<\/b><\/td>\n<\/tr>\n<tr>\n<td>5<\/td>\n<td><b>\u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u093e \u0938\u092c\u0938\u0947 \u092a\u0939\u0932\u093e \u0938\u093e\u092e\u093e\u0928\u094d\u092f \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?<\/b><\/td>\n<td>\u00a0 \u092a\u0940\u0930\u093f\u092f\u0921 \u0915\u093e \u092e\u093f\u0938 \u0939\u094b\u0928\u093e: \u092f\u0939 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u093e \u0938\u092c\u0938\u0947 \u092a\u0939\u0932\u093e \u0914\u0930 \u0938\u093e\u092e\u093e\u0928\u094d\u092f \u0932\u0915\u094d\u0937\u0923 \u0939\u0948\u0964 \u0938\u093f\u0930\u094d\u092b \u0907\u0938 \u0932\u0915\u094d\u0937\u0923 \u0915\u0947 \u0906\u0927\u093e\u0930 \u092a\u0930 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0940 \u092a\u0941\u0937\u094d\u091f\u093f \u0915\u0930\u0928\u093e \u092c\u093f\u0932\u094d\u0915\u0941\u0932 \u092d\u0940 \u0938\u0939\u0940 \u0928\u0939\u0940\u0902 \u0939\u094b\u0924\u093e \u0939\u0948\u0964 \u0939\u093e\u0932\u093e\u0902\u0915\u093f \u091c\u092c \u092a\u0940\u0930\u093f\u092f\u0921 \u090f\u0915 \u0939\u092b\u094d\u0924\u0947 \u092f\u093e \u0909\u0938\u0938\u0947 \u0905\u0927\u093f\u0915 \u0938\u092e\u092f \u0924\u0915 \u0928\u0939\u0940\u0902 \u0906\u0924\u0947 \u0939\u0948\u0902, \u0924\u094b \u0907\u0938\u0915\u0947 \u092c\u093e\u0926 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u0930\u093e\u0928\u0947 \u0915\u0940 \u0938\u0932\u093e\u0939 \u0926\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948\u0964<br \/>\u0938\u094d\u0924\u0928\u094b\u0902 \u092e\u0947\u0902 \u092c\u0926\u0932\u093e\u0935 \u0906\u0928\u093e: \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u092e\u0947\u0902 \u0938\u094d\u0924\u0928 \u092e\u0947\u0902 \u0938\u0942\u091c\u0928, \u0915\u094b\u092e\u0932\u0924\u093e \u092f\u093e \u0907\u0938\u0915\u0947 \u0930\u0902\u0917 \u092e\u0947\u0902 \u092c\u0926\u0932\u093e\u0935 \u0906 \u091c\u093e\u0924\u093e \u0939\u0948\u0964 \u092e\u0941\u0916\u094d\u092f \u0930\u0942\u092a \u0938\u0947 \u0928\u093f\u092a\u094d\u092a\u0932 (\u090f\u0930\u093f\u0913\u0932\u093e) \u0915\u0947 \u0906\u0915\u093e\u0930 \u0914\u0930 \u0930\u0902\u0917 \u092e\u0947\u0902 \u092c\u0926\u0932\u093e\u0935 \u0926\u0947\u0916\u0928\u0947 \u0915\u094b \u092e\u093f\u0932\u0924\u093e \u0939\u0948\u0964 \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u0915\u094b \u0926\u0947\u0916\u0924\u0947 \u0939\u0941\u090f \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u094b \u0915\u0948\u0938\u0947 \u0915\u0902\u092b\u0930\u094d\u092e \u0915\u0930\u0947\u0902?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u092a\u0939\u0932\u0947 \u092e\u0939\u0940\u0928\u0947 \u092e\u0947\u0902 \u0915\u0948\u0938\u0947 \u0927\u094d\u092f\u093e\u0928 \u0930\u0916\u0947\u0902?\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0940 \u091c\u093e\u0902\u091a \u0915\u0948\u0938\u0947 \u0915\u0930\u0947\u0902?\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0938\u0940 \u0915\u094b \u0915\u0948\u0938\u0947 \u092c\u0948\u0920\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u0915\u094d\u092f\u093e \u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0938\u0940 \u0915\u094b \u0938\u0947\u0915\u094d\u0938 \u0915\u0930\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0938\u0940 \u0915\u094b \u0915\u094c\u0928 \u0938\u093e \u092b\u0932 \u0916\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0924\u0928\u093e \u092a\u093e\u0928\u0940 \u092a\u0940\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u092e\u093e\u0902 \u092c\u0928\u0928\u0947 \u0915\u093e \u0938\u0941\u0916 \u0907\u0938 \u0938\u0902\u0938\u093e\u0930 \u0915\u093e \u0938\u092c\u0938\u0947 \u092c\u0921\u093c\u093e \u0938\u0941\u0916 \u0939\u0948\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u090f\u0915 \u092e\u0939\u093f\u0932\u093e \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0905\u0928\u0947\u0915 \u0936\u093e\u0930\u0940\u0930\u093f\u0915 \u090f\u0935\u0902 \u092e\u093e\u0928\u0938\u093f\u0915 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u0906\u092a \u0907\u0928\u094d\u0939\u0940 \u092c\u0926\u0932\u093e\u0935\u094b\u0902 \u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u0947 \u0928\u093e\u092e \u0938\u0947 \u091c\u093e\u0928\u0924\u0947 \u0939\u0948\u0902, \u2013 <b>WRONG<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0915\u0908 \u0939\u093e\u0930\u094d\u092e\u094b\u0928\u0932 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u092e\u0947\u0902 \u091c\u0940 \u092e\u091a\u0932\u0928\u093e, \u0909\u0932\u094d\u091f\u0940 \u0906\u0928\u093e, \u092c\u093e\u0930-\u092c\u093e\u0930 \u092a\u0947\u0936\u093e\u092c \u0906\u0928\u093e, \u0914\u0930 \u0925\u0915\u093e\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0936\u093e\u092e\u093f\u0932 \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u092e \u0907\u0938 \u092c\u094d\u0932\u0949\u0917 \u092e\u0947\u0902 \u092c\u093e\u0924 \u092d\u0940 \u0915\u0930\u0928\u0947 \u0935\u093e\u0932\u0947 \u0939\u0948\u0902\u0964 \u2013 <b>CORRECT<\/b><\/td>\n<\/tr>\n<tr>\n<td>6<\/td>\n<td>\u0917\u0930\u094d\u092d\u0927\u093e\u0930\u0923 \u0915\u0947 \u092a\u0939\u0932\u0947 \u0938\u0902\u0915\u0947\u0924 \u0915\u094d\u092f\u093e \u0939\u094b\u0924\u0947 \u0939\u0948\u0902?<\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0938\u0902\u0915\u0947\u0924: \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u0915\u0940 \u092a\u0942\u0930\u0940 \u091c\u093e\u0928\u0915\u093e\u0930\u0940! Home Quick Enquiry Patient LoginCall Us: 08062136530 Emergency No: 07340054470 Open main menuServicesPatients &amp; VisitorsInternational Patients About Us Book an Appointment Call BackWhatsApp \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0942\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u091c\u093e\u0928\u0947\u0964Obstetrics and Gynaecology |by Dr. C. P. Dadhich| Published on 06\/02\/2025Table of Contents\u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u092c \u0915\u0930\u0935\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u2013 <b>WRONG<\/b><\/td>\n<td>\u0915\u094b \u0926\u0947\u0916\u0924\u0947 \u0939\u0941\u090f \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u094b \u0915\u0948\u0938\u0947 \u0915\u0902\u092b\u0930\u094d\u092e \u0915\u0930\u0947\u0902?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u092a\u0939\u0932\u0947 \u092e\u0939\u0940\u0928\u0947 \u092e\u0947\u0902 \u0915\u0948\u0938\u0947 \u0927\u094d\u092f\u093e\u0928 \u0930\u0916\u0947\u0902?\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0940 \u091c\u093e\u0902\u091a \u0915\u0948\u0938\u0947 \u0915\u0930\u0947\u0902?\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0938\u0940 \u0915\u094b \u0915\u0948\u0938\u0947 \u092c\u0948\u0920\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u0915\u094d\u092f\u093e \u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0938\u0940 \u0915\u094b \u0938\u0947\u0915\u094d\u0938 \u0915\u0930\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0938\u0940 \u0915\u094b \u0915\u094c\u0928 \u0938\u093e \u092b\u0932 \u0916\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0915\u093f\u0924\u0928\u093e \u092a\u093e\u0928\u0940 \u092a\u0940\u0928\u093e \u091a\u093e\u0939\u093f\u090f?\u092e\u093e\u0902 \u092c\u0928\u0928\u0947 \u0915\u093e \u0938\u0941\u0916 \u0907\u0938 \u0938\u0902\u0938\u093e\u0930 \u0915\u093e \u0938\u092c\u0938\u0947 \u092c\u0921\u093c\u093e \u0938\u0941\u0916 \u0939\u0948\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u090f\u0915 \u092e\u0939\u093f\u0932\u093e \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0905\u0928\u0947\u0915 \u0936\u093e\u0930\u0940\u0930\u093f\u0915 \u090f\u0935\u0902 \u092e\u093e\u0928\u0938\u093f\u0915 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u0906\u092a \u0907\u0928\u094d\u0939\u0940 \u092c\u0926\u0932\u093e\u0935\u094b\u0902 \u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u0947 \u0928\u093e\u092e \u0938\u0947 \u091c\u093e\u0928\u0924\u0947 \u0939\u0948\u0902, \u2013 <b>WRONG<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0915\u0908 \u0939\u093e\u0930\u094d\u092e\u094b\u0928\u0932 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u092e\u0947\u0902 \u091c\u0940 \u092e\u091a\u0932\u0928\u093e, \u0909\u0932\u094d\u091f\u0940 \u0906\u0928\u093e, \u092c\u093e\u0930-\u092c\u093e\u0930 \u092a\u0947\u0936\u093e\u092c \u0906\u0928\u093e, \u0914\u0930 \u0925\u0915\u093e\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0936\u093e\u092e\u093f\u0932 \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u092e \u0907\u0938 \u092c\u094d\u0932\u0949\u0917 \u092e\u0947\u0902 \u092c\u093e\u0924 \u092d\u0940 \u0915\u0930\u0928\u0947 \u0935\u093e\u0932\u0947 \u0939\u0948\u0902\u0964 \u2013<b>CORRECT<\/b><\/td>\n<\/tr>\n<tr>\n<td>7<\/td>\n<td><b>\u0917\u0930\u094d\u092d\u093e\u0935\u0938\u094d\u0925\u093e \u0915\u0940 \u092a\u0941\u0937\u094d\u091f\u093f \u0915\u0947 \u0932\u093f\u090f \u0915\u094c\u0928 \u0938\u0947 \u0939\u093e\u0930\u094d\u092e\u094b\u0928 \u0915\u093e \u092a\u0924\u093e \u0932\u0917\u093e\u0928\u093e \u0939\u094b\u0924\u093e \u0939\u0948?<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f\u00a0\u0915\u0947 \u0932\u093f\u090f \u0938\u092c\u0938\u0947 \u0905\u091a\u094d\u091b\u093e \u0938\u092e\u092f \u0915\u092e \u0938\u0947 \u0915\u092e \u090f\u0915 \u092c\u093e\u0930 \u092a\u0940\u0930\u093f\u092f\u0921 \u0915\u093e \u092e\u093f\u0938 \u0939\u094b \u091c\u093e\u0928\u0947 \u0915\u0947 7 \u0926\u093f\u0928 \u092c\u093e\u0926 \u0939\u0948\u0964 \u0906\u092a \u0918\u0930 \u092a\u0930 \u0939\u0940 \u0939\u094b\u092e \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u093f\u091f \u0938\u0947 hCG \u0915\u0947 \u0938\u094d\u0924\u0930 \u0915\u093e \u092a\u0924\u093e \u0932\u0917\u093e \u0938\u0915\u0924\u0947 \u0939\u0948\u0902\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u0907\u0938 \u0939\u093e\u0930\u094d\u092e\u094b\u0928 \u0915\u0947 \u0938\u094d\u0924\u0930 \u092e\u0947\u0902 \u0905\u091a\u094d\u091b\u0940 \u0916\u093e\u0938\u0940 \u0935\u0943\u0926\u094d\u0927\u093f \u0926\u0947\u0916\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948\u0964 \u092f\u0939\u093e\u0902 \u0906\u092a\u0915\u094b \u090f\u0915 \u092c\u093e\u0924 \u0915\u093e \u0927\u094d\u092f\u093e\u0928 \u0930\u0916\u0928\u093e \u0939\u094b\u0917\u093e \u0915\u093f \u092c\u0939\u0941\u0924 \u091c\u0932\u094d\u0926\u0940 \u091f\u0947\u0938\u094d\u091f \u0915\u0930\u0928\u0947 \u0938\u0947 \u092d\u0940 \u0917\u0932\u0924 \u092a\u0930\u093f\u0923\u093e\u092e \u0906 \u0938\u0915\u0924\u0947 \u0939\u0948\u0902, \u0907\u0938\u0932\u093f\u090f \u092f\u0926\u093f \u0906\u092a\u0915\u0947 \u092a\u0940\u0930\u093f\u092f\u0921 \u0926\u0947\u0930 \u0938\u0947 \u0906 \u0930\u0939\u0947 \u0939\u0948\u0902 \u0914\u0930 \u091f\u0947\u0938\u094d\u091f \u0928\u0947\u0917\u0947\u091f\u093f\u0935 \u0906\u0924\u093e \u0939\u0948, \u0924\u094b \u0906\u092a\u0915\u094b \u0938\u0932\u093e\u0939 \u0926\u0940 \u091c\u093e\u0924\u0940 \u0939\u0948 \u0915\u093f \u0915\u092e \u0938\u0947 \u0915\u092e 3 \u0926\u093f\u0928 \u0914\u0930 \u0930\u0941\u0915\u0947\u0902 \u0914\u0930 \u092b\u093f\u0930 \u0938\u0947 \u091f\u0947\u0938\u094d\u091f \u0915\u0930\u0947\u0902\u0964 \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u0907\u0938\u0947 \u0915\u0930\u0928\u0947 \u0915\u093e \u092d\u0940 \u090f\u0915 \u0938\u0939\u0940 \u0924\u0930\u0940\u0915\u093e \u0939\u094b\u0924\u093e \u0939\u0948, \u091c\u094b \u0906\u092a \u091f\u0947\u0938\u094d\u091f \u0915\u093f\u091f \u0915\u0947 \u0928\u093f\u0930\u094d\u0926\u0947\u0936\u0928 \u0935\u093e\u0932\u0940 \u092a\u0930\u094d\u091a\u0940 \u092a\u0930 \u092d\u0940 \u0926\u0947\u0916 \u0938\u0915\u0924\u0947 \u0939\u0948\u0902\u0964 \u0938\u091f\u0940\u0915 \u092a\u0930\u093f\u0923\u093e\u092e\u094b\u0902 \u0915\u0947 \u0932\u093f\u090f \u0906\u092a\u0915\u094b \u0938\u0941\u092c\u0939 \u0915\u0947 \u0938\u092c\u0938\u0947 \u092a\u0939\u0932\u0947 \u092a\u0947\u0936\u093e\u092c \u0915\u093e \u0907\u0938\u094d\u0924\u0947\u092e\u093e\u0932 \u0915\u0930\u0928\u093e \u0939\u094b\u0924\u093e \u0939\u0948, \u0915\u094d\u092f\u094b\u0902\u0915\u093f \u0907\u0938\u0940 \u0926\u094c\u0930\u093e\u0928 hCG \u0939\u093e\u0930\u094d\u092e\u094b\u0928 \u0915\u0947 \u0938\u0939\u0940 \u0938\u094d\u0924\u0930 \u0915\u094b \u092e\u093e\u092a\u093e \u091c\u093e \u0938\u0915\u0924\u093e \u0939\u0948\u0964 \u0907\u0938\u0915\u0947 \u0905\u0924\u093f\u0930\u093f\u0915\u094d\u0924 \u092f\u0926\u093f \u0906\u092a\u0915\u094b \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u0915\u093e \u0905\u0928\u0941\u092d\u0935 \u0939\u094b\u0924\u093e \u0939\u0948, \u0914\u0930 \u091f\u0947\u0938\u094d\u091f \u0915\u093e \u092a\u0930\u093f\u0923\u093e\u092e \u092d\u0940 \u0928\u0947\u0917\u0947\u091f\u093f\u0935 \u0906 \u0930\u0939\u093e \u0939\u0948, \u0924\u094b \u0924\u0941\u0930\u0902\u0924 \u0921\u0949\u0915\u094d\u091f\u0930 \u0915\u0947 \u092a\u093e\u0938 \u091c\u093e\u0915\u0930 \u092c\u094d\u0932\u0921 \u091f\u0947\u0938\u094d\u091f \u0915\u0930\u093e\u090f\u0902\u0964 \u0915\u093f\u0938\u0940 \u092d\u0940 \u092a\u094d\u0930\u0915\u093e\u0930 \u0915\u0947 \u0915\u0928\u094d\u092b\u094d\u092f\u0942\u091c\u0928 \u0915\u0940 \u0938\u094d\u0925\u093f\u0924\u093f \u092e\u0947\u0902 \u0921\u0949\u0915\u094d\u091f\u0930\u0940 \u0938\u0932\u093e\u0939 \u092c\u0939\u0941\u0924 \u091c\u094d\u092f\u093e\u0926\u093e \u0905\u0928\u093f\u0935\u093e\u0930\u094d\u092f \u0939\u0948\u0964 \u2013 <b>CORRECT<\/b><\/td>\n<td>\u00a0 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923 \u0915\u094d\u092f\u093e \u0939\u0948?<br \/>\u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u092e\u0939\u093f\u0932\u093e\u0913\u0902 \u0915\u0947 \u0936\u0930\u0940\u0930 \u092e\u0947\u0902 \u0915\u0908 \u0939\u093e\u0930\u094d\u092e\u094b\u0928\u0932 \u092c\u0926\u0932\u093e\u0935 \u0906\u0924\u0947 \u0939\u0948\u0902\u0964 \u092a\u094d\u0930\u0947\u0917\u0928\u0947\u0902\u0938\u0940 \u0915\u0947 \u0936\u0941\u0930\u0941\u0906\u0924\u0940 \u0932\u0915\u094d\u0937\u0923\u094b\u0902 \u092e\u0947\u0902 \u091c\u0940 \u092e\u091a\u0932\u0928\u093e, \u0909\u0932\u094d\u091f\u0940 \u0906\u0928\u093e, \u092c\u093e\u0930-\u092c\u093e\u0930 \u092a\u0947\u0936\u093e\u092c \u0906\u0928\u093e, \u0914\u0930 \u0925\u0915\u093e\u0928 \u091c\u0948\u0938\u0947 \u0932\u0915\u094d\u0937\u0923 \u0936\u093e\u092e\u093f\u0932 \u0939\u0948, \u091c\u093f\u0938\u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0939\u092e \u0907\u0938 \u092c\u094d\u0932\u0949\u0917 \u092e\u0947\u0902 \u092c\u093e\u0924 \u092d\u0940 \u0915\u0930\u0928\u0947 \u0935\u093e\u0932\u0947 \u0939\u0948\u0902\u0964 \u2013 <b>WRONG<\/b><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<h3 class=\"wp-block-heading\" id=\"h-explanation\">Explanation<\/h3>\n<p>As seen from the above Hindi outputs, with Gemini Embeddings, we get 5 correct outputs from the 7 queries, while Jina AI embeddings and Multilingual-e5-large, we get 3 correct responses only.<\/p>\n<p>This shows that Gemini Embeddings, as reflective on the MTEB benchmark, can perform well and better than other embeddings models for multilingual languages as well like Hindi.<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-conclusions\">Conclusions<\/h2>\n<p>In conclusion, Gemini Embeddings represent a significant advancement in multilingual NLP, particularly for Indic languages like Hindi. With its robust multilingual capabilities, support for large input sizes, and superior performance on benchmarks like MTEB, Gemini excels in tasks such as retrieval, classification, and semantic search. As demonstrated through hands-on comparisons, Gemini outperforms other models, offering enhanced accuracy and efficiency, making it a valuable tool for advancing NLP in diverse languages.<\/p>\n<h4 class=\"wp-block-heading\" id=\"h-key-takeaways\">Key Takeaways<\/h4>\n<ul class=\"wp-block-list\">\n<li><strong>Importance of Word Embeddings for Indic Languages<\/strong>: High-quality embeddings enhance NLP tasks like translation, QA, and retrieval, addressing linguistic challenges and resource gaps. <\/li>\n<li><strong>Gemini Embedding Model<\/strong>: Google\u2019s Gemini Embeddings leverage its AI framework for multilingual text processing, covering 100+ languages, including low-resource ones. <\/li>\n<li><strong>Key Features<\/strong>: Supports 8,000 tokens and 3,072-dimensional embeddings, handling long documents and complex queries efficiently. <\/li>\n<li><strong>Impressive Performance<\/strong>: Tops the MTEB Multilingual leaderboard with a 68.32 mean task score, proving its superiority in multilingual NLP.<\/li>\n<\/ul>\n<p><strong>The media shown in this article is not owned by Analytics Vidhya and is used at the Author\u2019s discretion.<\/strong><a href=\"https:\/\/www.analyticsvidhya.com\/blog\/author\/adarsh2039075\/\"\/><\/p>\n<h2 class=\"wp-block-heading\" id=\"h-frequently-asked-questions\">Frequently Asked Questions<\/h2>\n<div class=\"schema-faq wp-block-yoast-faq-block\">\n<div class=\"schema-faq-section\" id=\"faq-question-1742197212791\"><strong class=\"schema-faq-question\">Q1. What is the Gemini Embedding model?<\/strong> <\/p>\n<p class=\"schema-faq-answer\">Ans. The Gemini Embedding model, built on Google\u2019s Gemini AI, offers top-tier multilingual text embedding for 100+ languages, including Hindi.<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1742197233728\"><strong class=\"schema-faq-question\">Q2. What makes Gemini Embedding unique compared to other models?<\/strong> <\/p>\n<p class=\"schema-faq-answer\">Ans. Gemini Embedding excels in multilingual support, handles 8,000 tokens, and outputs 3,072 dimensions, ensuring efficiency in classification, retrieval, and semantic search.<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1742197261056\"><strong class=\"schema-faq-question\">Q3. How does Gemini Embedding perform in multilingual tasks?<\/strong> <\/p>\n<p class=\"schema-faq-answer\">Ans. Gemini Embedding performs well in both high-resource languages like English and low-resource ones like Assamese and Macedonian. It ranks top on the MTEB Multilingual leaderboard, showcasing its strong multilingual capabilities.<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1742197287486\"><strong class=\"schema-faq-question\">Q4. What is the architecture of the Gemini Embedding model?<\/strong> <\/p>\n<p class=\"schema-faq-answer\">Ans. The model, initialized from the Gemini LLM, uses a transformer architecture with bidirectional attention to generate high-quality text embeddings that capture context and meaning.<\/p>\n<\/p><\/div>\n<div class=\"schema-faq-section\" id=\"faq-question-1742197304176\"><strong class=\"schema-faq-question\">Q5. How was the Gemini Embedding model trained?<\/strong> <\/p>\n<p class=\"schema-faq-answer\">Ans. Gemini Embedding was trained using noise-contrastive estimation (NCE) loss with in-batch negatives. It underwent two training stages: pre-finetuning on a large dataset and fine-tuning on task-specific datasets for better NLP performance.<\/p>\n<\/p><\/div>\n<\/p><\/div>\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\/mimi6\/\" 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_ZkJo4gb.webp\" width=\"48\" height=\"48\" alt=\"Nibedita Dutta\" loading=\"lazy\" class=\"rounded-circle\"\/><\/p>\n<p>                                <\/a>\n                                <\/div>\n<\/p><\/div>\n<p>Nibedita completed her master\u2019s in Chemical Engineering from IIT Kharagpur in 2014 and is currently working as a Senior Data Scientist. In her current capacity, she works on building intelligent ML-based solutions to improve business processes.               <\/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>Word embeddings for Indic languages like Hindi are crucial for advancing Natural Language Processing (NLP) tasks such as machine translation, question answering, and information retrieval. These embeddings capture semantic properties of words, enabling more accurate and context-aware NLP applications. Given the vast number of Hindi speakers and the growing digital content in Indic languages, high-quality [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":139379,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[12033],"tags":[5815,13598,59412,20726,59414,59413],"dealstore":[],"offerexpiration":[],"class_list":["post-139378","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-analytics","tag-blogathon","tag-comparison","tag-embedding","tag-gemini","tag-jina","tag-multilinguale5large"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Comparison of Gemini Embedding with Multilingual-e5-large &amp; Jina - 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=139378\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Comparison of Gemini Embedding with Multilingual-e5-large &amp; Jina - Som2ny Network\" \/>\n<meta property=\"og:description\" content=\"Word embeddings for Indic languages like Hindi are crucial for advancing Natural Language Processing (NLP) tasks such as machine translation, question answering, and information retrieval. These embeddings capture semantic properties of words, enabling more accurate and context-aware NLP applications. Given the vast number of Hindi speakers and the growing digital content in Indic languages, high-quality [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/fivemor.com\/?p=139378\" \/>\n<meta property=\"og:site_name\" content=\"Som2ny Network\" \/>\n<meta property=\"article:published_time\" content=\"2025-03-17T10:22:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.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=\"10 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/fivemor.com\/?p=139378#article\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/?p=139378\"},\"author\":{\"name\":\"admin\",\"@id\":\"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371\"},\"headline\":\"Comparison of Gemini Embedding with Multilingual-e5-large &#038; Jina\",\"datePublished\":\"2025-03-17T10:22:58+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=139378\"},\"wordCount\":1733,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/fivemor.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=139378#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp\",\"keywords\":[\"Blogathon\",\"Comparison\",\"Embedding\",\"Gemini\",\"Jina\",\"Multilinguale5large\"],\"articleSection\":[\"Analytics\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/fivemor.com\/?p=139378#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/fivemor.com\/?p=139378\",\"url\":\"https:\/\/fivemor.com\/?p=139378\",\"name\":\"Comparison of Gemini Embedding with Multilingual-e5-large & Jina - Som2ny Network\",\"isPartOf\":{\"@id\":\"https:\/\/fivemor.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/fivemor.com\/?p=139378#primaryimage\"},\"image\":{\"@id\":\"https:\/\/fivemor.com\/?p=139378#primaryimage\"},\"thumbnailUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp\",\"datePublished\":\"2025-03-17T10:22:58+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/fivemor.com\/?p=139378#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/fivemor.com\/?p=139378\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/fivemor.com\/?p=139378#primaryimage\",\"url\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp\",\"contentUrl\":\"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp\",\"width\":872,\"height\":473},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/fivemor.com\/?p=139378#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/fivemor.com\/?bp_activities=1\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Comparison of Gemini Embedding with Multilingual-e5-large &#038; Jina\"}]},{\"@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":"Comparison of Gemini Embedding with Multilingual-e5-large & Jina - 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=139378","og_locale":"en_US","og_type":"article","og_title":"Comparison of Gemini Embedding with Multilingual-e5-large & Jina - Som2ny Network","og_description":"Word embeddings for Indic languages like Hindi are crucial for advancing Natural Language Processing (NLP) tasks such as machine translation, question answering, and information retrieval. These embeddings capture semantic properties of words, enabling more accurate and context-aware NLP applications. Given the vast number of Hindi speakers and the growing digital content in Indic languages, high-quality [&hellip;]","og_url":"https:\/\/fivemor.com\/?p=139378","og_site_name":"Som2ny Network","article_published_time":"2025-03-17T10:22:58+00:00","og_image":[{"width":872,"height":473,"url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp","type":"image\/webp"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Est. reading time":"10 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/fivemor.com\/?p=139378#article","isPartOf":{"@id":"https:\/\/fivemor.com\/?p=139378"},"author":{"name":"admin","@id":"https:\/\/fivemor.com\/#\/schema\/person\/b85e3c3dc0e1daea076524dc8810c371"},"headline":"Comparison of Gemini Embedding with Multilingual-e5-large &#038; Jina","datePublished":"2025-03-17T10:22:58+00:00","mainEntityOfPage":{"@id":"https:\/\/fivemor.com\/?p=139378"},"wordCount":1733,"commentCount":0,"publisher":{"@id":"https:\/\/fivemor.com\/#organization"},"image":{"@id":"https:\/\/fivemor.com\/?p=139378#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp","keywords":["Blogathon","Comparison","Embedding","Gemini","Jina","Multilinguale5large"],"articleSection":["Analytics"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/fivemor.com\/?p=139378#respond"]}]},{"@type":"WebPage","@id":"https:\/\/fivemor.com\/?p=139378","url":"https:\/\/fivemor.com\/?p=139378","name":"Comparison of Gemini Embedding with Multilingual-e5-large & Jina - Som2ny Network","isPartOf":{"@id":"https:\/\/fivemor.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/fivemor.com\/?p=139378#primaryimage"},"image":{"@id":"https:\/\/fivemor.com\/?p=139378#primaryimage"},"thumbnailUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp","datePublished":"2025-03-17T10:22:58+00:00","breadcrumb":{"@id":"https:\/\/fivemor.com\/?p=139378#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/fivemor.com\/?p=139378"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/fivemor.com\/?p=139378#primaryimage","url":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp","contentUrl":"https:\/\/fivemor.com\/wp-content\/uploads\/2025\/03\/Google-Gemini-into-Tableau-Dashboards.webp.webp","width":872,"height":473},{"@type":"BreadcrumbList","@id":"https:\/\/fivemor.com\/?p=139378#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/fivemor.com\/?bp_activities=1"},{"@type":"ListItem","position":2,"name":"Comparison of Gemini Embedding with Multilingual-e5-large &#038; Jina"}]},{"@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\/139378","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=139378"}],"version-history":[{"count":0,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/posts\/139378\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=\/wp\/v2\/media\/139379"}],"wp:attachment":[{"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=139378"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=139378"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=139378"},{"taxonomy":"dealstore","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fdealstore&post=139378"},{"taxonomy":"offerexpiration","embeddable":true,"href":"https:\/\/fivemor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fofferexpiration&post=139378"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}