{"id":119205,"date":"2026-06-29T22:25:44","date_gmt":"2026-06-29T16:55:44","guid":{"rendered":"https:\/\/www.guvi.in\/blog\/?p=119205"},"modified":"2026-06-29T22:25:46","modified_gmt":"2026-06-29T16:55:46","slug":"run-llms-with-ollama-and-python","status":"publish","type":"post","link":"https:\/\/www.guvi.in\/blog\/run-llms-with-ollama-and-python\/","title":{"rendered":"Run LLMs Locally with Ollama and Python"},"content":{"rendered":"\n<p>Cloud AI APIs are convenient \u2014 until you hit rate limits, get surprised by a bill, or realise you just sent sensitive customer data to a third-party server. <strong>Running LLMs locally with Ollama<\/strong> solves all three problems at once. This guide walks you through the complete setup: installing Ollama, pulling a model, and calling it from Python \u2014 whether you want a quick one-liner or a full streaming chat interface.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>TL;DR Summary<\/strong><\/h2>\n\n\n\n<ul>\n<li>\u00a0Running LLMs locally with Ollama lets you use powerful AI models on your own machine \u2014 no API keys, no cloud costs, no data leaving your device.<\/li>\n\n\n\n<li>Ollama supports models like Llama 3, Mistral, Gemma 2, and Phi-3 \u2014 all downloadable with a single command.<\/li>\n\n\n\n<li>You can call Ollama from Python using the official ollama library or directly via its REST API \u2014 both work with any framework.<\/li>\n\n\n\n<li>The full setup takes under 10 minutes on macOS, Linux, or Windows with WSL2.<\/li>\n\n\n\n<li>Local LLMs are ideal for privacy-sensitive workloads, offline use, and cutting per-token API costs to zero.<\/li>\n<\/ul>\n\n\n\n<div class=\"guvi-answer-card\" style=\"margin: 40px 0;\">\n\n  <div style=\"\n    position: relative;\n    background: linear-gradient(135deg, #f0fff4, #e6f7ee);\n    border: 1px solid #cfeedd;\n    padding: 26px 24px 22px 24px;\n    border-radius: 14px;\n    font-family: Arial, sans-serif;\n    box-shadow: 0 6px 16px rgba(0,0,0,0.05);\n  \">\n\n    <!-- Top accent -->\n    <div style=\"\n      position: absolute;\n      top: 0;\n      left: 0;\n      height: 6px;\n      width: 100%;\n      background: linear-gradient(to right, #099f4e, #6dd5a3);\n      border-radius: 14px 14px 0 0;\n    \"><\/div>\n\n    <!-- Title -->\n    <h3 style=\"\n      margin: 10px 0 12px 0;\n      color: #099f4e;\n      font-size: 20px;\n    \">\n      Run an LLM Locally with Ollama\n    <\/h3>\n\n    <!-- Content -->\n    <p style=\"\n      margin: 0;\n      color: #2f4f3f;\n      font-size: 16px;\n      line-height: 1.7;\n    \">\n      Running a large language model (LLM) locally with Ollama is straightforward. First, install Ollama from the official website, then download a model by running <code>ollama pull llama3<\/code> in your terminal. Once the model is installed, you can access it from Python using the Ollama library with methods such as <code>ollama.chat()<\/code>. After the initial model download, the LLM runs entirely on your local machine without requiring an internet connection or an API key. This makes Ollama an excellent choice for building AI applications that prioritize privacy, offline access, and low-latency inference.\n    <\/p>\n\n  <\/div>\n\n<\/div>\n\n\n\n<p>Explore HCL GUVI&#8217;s<a href=\"https:\/\/www.guvi.in\/mlp\/artificial-intelligence-and-machine-learning?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=run-llm-locally-ollama\"> <\/a><a href=\"https:\/\/www.guvi.in\/zen-class\/ai-ml-programme\/?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=Running+LLMs+Locally+with+Python+and+Ollama%3A+Full+Setup+Guide\" target=\"_blank\" rel=\"noreferrer noopener\">Artificial Intelligence &amp; Machine Learning Course<\/a> hands-on projects, mentorship, and placement support included.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Is Ollama and Why Use It?<\/strong><\/h2>\n\n\n\n<p>Ollama is an open-source tool that packages large language models into a simple CLI and REST server. Think of it as Docker for LLMs \u2014 you pull a model by name, and Ollama handles the quantisation, memory mapping, and inference runtime behind the scenes. No Python environment juggling, no manual GGUF file wrangling.<\/p>\n\n\n\n<p>The core reasons developers choose Ollama over cloud APIs:<\/p>\n\n\n\n<ul>\n<li><strong>Privacy:<\/strong> your prompts and data never leave your machine.<\/li>\n\n\n\n<li><strong>Cost:<\/strong> zero per-token charges after the one-time model download.<\/li>\n\n\n\n<li><strong>Latency:<\/strong> no network round-trip \u2014 especially fast on Apple Silicon or modern NVIDIA GPUs.<\/li>\n\n\n\n<li><strong>Offline use:<\/strong> works without any internet connection once the model is downloaded.<\/li>\n<\/ul>\n\n\n\n<p class=\"has-text-align-center\"><em><strong>Pro Tip: Ollama uses llama.cpp under the hood and automatically applies 4-bit quantisation, which means Llama 3 8B fits comfortably on a machine with 8 GB of RAM. You don&#8217;t need a GPU \u2014 modern CPUs run 7B-parameter models at usable speeds (roughly 10\u201320 tokens per second on an M2 MacBook Air).<\/strong><\/em><\/p>\n\n\n\n<p>Want to build real-world AI applications? Explore HCL GUVI&#8217;s<a href=\"https:\/\/www.guvi.in\/mlp\/artificial-intelligence-and-machine-learning?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=run-llm-locally-ollama\"> <\/a><a href=\"https:\/\/www.guvi.in\/zen-class\/ai-ml-programme\/?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=Running+LLMs+Locally+with+Python+and+Ollama%3A+Full+Setup+Guide\" target=\"_blank\" rel=\"noreferrer noopener\">Artificial Intelligence &amp; Machine Learning Course<\/a> hands-on projects, mentorship, and placement support included.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Installing Ollama: macOS, Linux, and Windows<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>macOS and Linux<\/strong><\/h3>\n\n\n\n<p>One command installs and starts the Ollama daemon:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>curl -fsSL https:\/\/ollama.com\/install.sh | sh&nbsp;<\/code><\/pre>\n\n\n\n<p>On macOS, you can also download the native app from ollama.com\/download \u2014 it runs as a menu-bar icon and starts the server automatically on login.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Windows<\/strong><\/h3>\n\n\n\n<p>Ollama has native Windows support (no WSL2 required as of version 0.1.30+). Download the .exe installer from ollama.com\/download and run it. The server starts in the background on port 11434.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Verify the Installation<\/strong><\/h3>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>ollama &#8211;version<br># Expected output: ollama version 0.x.x<br><br># Pull your first model (approx 4.7 GB)<br>ollama pull llama3<br><br># Run it interactively<br>ollama run llama3&nbsp;<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p class=\"has-text-align-center\"><em><strong>Warning: Model downloads can be large \u2014 Llama 3 8B is ~4.7 GB and Mistral 7B is ~4.1 GB. Pull models on a stable connection and make sure you have at least 8 GB free disk space per model. Ollama stores models in ~\/.ollama\/models on macOS\/Linux.<\/strong><\/em><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Calling Ollama from Python<\/strong><\/h2>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Option 1: The Official ollama Python Library<\/strong><\/h3>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>pip install ollama<br>import ollama<br>response = ollama.chat(<br>&nbsp; &nbsp; model=&#8217;llama3&#8242;,<br>&nbsp; &nbsp; messages=[<br>&nbsp; &nbsp; &nbsp; &nbsp; {&#8216;role&#8217;: &#8216;system&#8217;, &#8216;content&#8217;: &#8216;You are a helpful assistant.&#8217;},<br>&nbsp; &nbsp; &nbsp; &nbsp; {&#8216;role&#8217;: &#8216;user&#8217;, &nbsp; &#8216;content&#8217;: &#8216;Explain vector embeddings in two sentences.&#8217;}<br>&nbsp; &nbsp; ]<br>)<br><br><strong>print<\/strong>(response[&#8216;message&#8217;][&#8216;content&#8217;])&nbsp;<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>That&#8217;s the complete working example \u2014 no API key, no environment variables, no account. As long as the Ollama daemon is running and the model is pulled, this code works offline.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Option 2: Streaming Responses<\/strong><\/h3>\n\n\n\n<p>For longer outputs, streaming lets you display tokens as they are generated instead of waiting for the full response:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>import ollama<br><br>stream = ollama.chat(<br>&nbsp; &nbsp; model=&#8217;llama3&#8242;,<br>&nbsp; &nbsp; messages=[{&#8216;role&#8217;: &#8216;user&#8217;, &#8216;content&#8217;: &#8216;Write a Python function to reverse a string.&#8217;}],<br>&nbsp; &nbsp; stream=<strong>True<\/strong><br>)<br><br><strong>for<\/strong> chunk in stream:<br>&nbsp; &nbsp; <strong>print<\/strong>(chunk[&#8216;message&#8217;][&#8216;content&#8217;], end=&#8221;, flush=<strong>True<\/strong>)<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Option 3: The REST API Directly<\/strong><\/h3>\n\n\n\n<p>Ollama exposes a local REST server, so you can call it with requests or any HTTP client \u2014 useful if you&#8217;re integrating into a framework that already manages HTTP:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>import requests, json<br><br>payload = {<br>&nbsp; &nbsp; &#8216;model&#8217;: &#8216;llama3&#8217;,<br>&nbsp; &nbsp; &#8216;prompt&#8217;: &#8216;What is retrieval-augmented generation?&#8217;,<br>&nbsp; &nbsp; &#8216;stream&#8217;: <strong>False<\/strong><br>}<br><br>r = requests.post(&#8216;http:\/\/localhost:11434\/api\/generate&#8217;, json=payload)<br><strong>print<\/strong>(r.json()[&#8216;response&#8217;])&nbsp;<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<div style=\"background-color: #099f4e; border: 3px solid #110053; border-radius: 12px; padding: 18px 22px; color: #FFFFFF; font-size: 18px; font-family: Montserrat, Helvetica, sans-serif; line-height: 1.6; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15); max-width: 750px;\">\n\n  <strong style=\"font-size: 22px; color: #FFFFFF;\">\ud83d\udca1 Did You Know?<\/strong>\n  <br \/><br \/>\n\n  <strong style=\"color: #FFFFFF;\">Ollama<\/strong> provides an <strong style=\"color: #FFFFFF;\">OpenAI-compatible REST API<\/strong> at the <code style=\"color: #FFFFFF;\">\/v1\/chat\/completions<\/code> endpoint. This allows developers to use Ollama as a local replacement in applications built with the <strong style=\"color: #FFFFFF;\">OpenAI Python library<\/strong> by simply updating the <strong style=\"color: #FFFFFF;\">base_url<\/strong> to <code style=\"color: #FFFFFF;\">http:\/\/localhost:11434\/v1<\/code> and setting the <strong style=\"color: #FFFFFF;\">api_key<\/strong> to <code style=\"color: #FFFFFF;\">ollama<\/code>. As a result, many existing AI applications can run with locally hosted models with minimal code changes.\n\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Which Model Should You Pull?<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td><strong>Model<\/strong><\/td><td><strong>Size<\/strong><\/td><td><strong>RAM Needed<\/strong><\/td><td><strong>Best For<\/strong><\/td><\/tr><tr><td>llama3<\/td><td>8B&nbsp; (~4.7 GB)<\/td><td>8 GB<\/td><td>General chat, coding, summarisation<\/td><\/tr><tr><td>mistral<\/td><td>7B&nbsp; (~4.1 GB)<\/td><td>8 GB<\/td><td>Fast inference, instruction following<\/td><\/tr><tr><td>gemma2<\/td><td>9B&nbsp; (~5.5 GB)<\/td><td>10 GB<\/td><td>Google-tuned reasoning tasks<\/td><\/tr><tr><td>phi3<\/td><td>3.8B (~2.3 GB)<\/td><td>6 GB<\/td><td>Low-RAM devices, quick prototyping<\/td><\/tr><tr><td>codellama<\/td><td>7B&nbsp; (~3.8 GB)<\/td><td>8 GB<\/td><td>Code generation and completion<\/td><\/tr><tr><td>llava<\/td><td>7B&nbsp; (~4.5 GB)<\/td><td>8 GB<\/td><td>Multimodal \u2014 image + text prompts<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Quick rule: if you have 8 GB of RAM, start with <strong>llama3<\/strong> for general use or <strong>codellama<\/strong> for coding tasks. If RAM is tight, <strong>phi3<\/strong> delivers surprisingly strong results at a fraction of the size.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Using Ollama with LangChain and LlamaIndex<\/strong><\/h2>\n\n\n\n<p>Ollama integrates directly with the two most popular Python LLM frameworks, so you can build RAG pipelines, agents, and chat applications without changing your architecture.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>LangChain<\/strong><\/h3>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>pip install langchain-ollama<br><br>from langchain_ollama import OllamaLLM<br><br>llm = OllamaLLM(model=&#8217;llama3&#8242;)<br><strong>print<\/strong>(llm.invoke(&#8216;Summarise the CAP theorem in one paragraph.&#8217;))<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>LlamaIndex<\/strong><\/h3>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>pip install llama-index-llms-ollama<br><br>from llama_index.llms.ollama import Ollama<br><br>llm = Ollama(model=&#8217;mistral&#8217;, request_timeout=120.0)<br>response = llm.complete(&#8216;What is the difference between RAG and fine-tuning?&#8217;)<br><strong>print<\/strong>(response)<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p><strong><em>Pro Tip:<\/em><\/strong><em> When building RAG pipelines locally, pair Ollama with nomic-embed-text for embeddings \u2014 it&#8217;s a lightweight embedding model also available via ollama pull nomic-embed-text. This keeps the entire pipeline on your machine, including the vector search step.<\/em><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Key Takeaways<\/strong><\/h2>\n\n\n\n<ul>\n<li>Ollama is the fastest way to run LLMs locally \u2014 one install command, one pull command, and your model is ready.<\/li>\n\n\n\n<li>The official Ollama Python library makes integration a five-line script. The REST API works for any language or framework.<\/li>\n\n\n\n<li>Llama 3 8B and Mistral 7B run on 8 GB RAM machines \u2014 no GPU required, though one significantly improves speed.<\/li>\n\n\n\n<li>Ollama&#8217;s OpenAI-compatible endpoint lets you swap cloud APIs for local inference with minimal code changes.<\/li>\n\n\n\n<li>For production RAG pipelines, combine Ollama with LangChain or LlamaIndex and a local embedding model like nomic-embed-text.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Common Mistakes to Avoid<\/strong><\/h2>\n\n\n\n<ul>\n<li><strong>Common Mistake 1 \u2014 Pulling a model too large for your RAM:<\/strong> If the model size exceeds your available RAM, Ollama will use swap memory and inference will be extremely slow (sometimes 1 token per second or worse). Always check the RAM requirement before pulling.<\/li>\n\n\n\n<li><strong>Common Mistake 2 \u2014 Forgetting to start the Ollama daemon:<\/strong> The Python library and REST API both require the Ollama server to be running. If you get a connection refused error, run ollama serve in a separate terminal window.<\/li>\n\n\n\n<li><strong>Common Mistake 3 \u2014 Using stream=False for long outputs:<\/strong> Generating a 500-word response with streaming disabled holds the connection open for the full generation time. Use stream=True for anything beyond short answers to keep your application responsive.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Wrapping Up<\/strong><\/h2>\n\n\n\n<p>Running LLMs locally with Ollama removes the three biggest friction points of cloud AI: cost, privacy risk, and rate limits. The setup takes less than 10 minutes, the Python integration is four lines of code, and the model quality of Llama 3 and Mistral is genuinely competitive with GPT-3.5 for most tasks. Pull a model, run the example, and see for yourself \u2014 local inference is more accessible than it has ever been.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>FAQs<\/strong><\/h2>\n\n\n<div id=\"rank-math-faq\" class=\"rank-math-block\">\n<div class=\"rank-math-list \">\n<div id=\"faq-question-1782447980832\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">1.\u00a0 \u00a0 <strong>Do I need a GPU to run LLMs locally with Ollama? <\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>No. Ollama runs on CPU-only machines using llama.cpp with 4-bit quantisation. A GPU significantly improves inference speed \u2014 on an M2 MacBook, Llama 3 8B runs at roughly 60 tokens per second vs 10 tokens per second on CPU \u2014 but it is not required for development or low-volume use.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1782447985517\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">2.\u00a0 \u00a0 <strong>Which is better for local LLMs \u2014 Ollama or LM Studio? <\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Ollama is better for developers who want a CLI, Python library, and REST API they can script and automate. LM Studio provides a graphical interface and is better for non-technical users who want a point-and-click experience. Both use llama.cpp under the hood and support the same GGUF model format.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1782448012371\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">3.\u00a0 \u00a0 <strong>Can I run Ollama on a server without a GPU? <\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Yes. Ollama runs on any Linux machine, including cloud VMs without GPUs. A CPU-only VM with 16 GB RAM and 2\u20134 vCPUs can serve a 7B-parameter model for low-traffic internal applications. For higher throughput, add a GPU instance.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1782448019488\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">4.\u00a0 \u00a0 <strong>Is Ollama production-ready? <\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Ollama is stable for internal tools, development environments, and low-traffic applications. For high-traffic production APIs, consider vLLM or TGI (Text Generation Inference) instead \u2014 they offer better batching, token streaming, and horizontal scaling. Ollama itself recommends this distinction in its documentation.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1782448028005\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">5.\u00a0 \u00a0 <strong>How do I update a model in Ollama?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Run ollama pull &lt;model-name> again. Ollama checks for a newer version and downloads only the changed layers, similar to how Docker handles image updates. Your existing pulled models are not affected.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1782448036280\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \">6.\u00a0 \u00a0 <strong>Can I use my own fine-tuned model with Ollama? <\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Yes. Ollama supports importing custom models via a Modelfile\u00a0 a simple configuration file that points to a GGUF weights file and sets system prompts, parameters, and templates. This lets you package and serve your own fine-tuned models with the same ollama run interface as official models.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Cloud AI APIs are convenient \u2014 until you hit rate limits, get surprised by a bill, or realise you just sent sensitive customer data to a third-party server. Running LLMs locally with Ollama solves all three problems at once. This guide walks you through the complete setup: installing Ollama, pulling a model, and calling it [&hellip;]<\/p>\n","protected":false},"author":63,"featured_media":119663,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[717],"tags":[],"views":"17","authorinfo":{"name":"Vishalini Devarajan","url":"https:\/\/www.guvi.in\/blog\/author\/vishalini\/"},"thumbnailURL":"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/06\/run-llms-with-ollama-and-python-300x150.webp","_links":{"self":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/119205"}],"collection":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/users\/63"}],"replies":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/comments?post=119205"}],"version-history":[{"count":2,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/119205\/revisions"}],"predecessor-version":[{"id":119661,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/119205\/revisions\/119661"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media\/119663"}],"wp:attachment":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media?parent=119205"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/categories?post=119205"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/tags?post=119205"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}