@elgap/edukaai 0.1.0

package/.output/server/chunks/build/sample-datasets-CVLWMQUA.mjs

@@ -0,0 +1,45 @@
+import { ref, mergeProps, unref, useSSRContext } from 'vue';
+import { ssrRenderAttrs, ssrRenderList, ssrInterpolate } from 'vue/server-renderer';
+
+const _sfc_main = {
+  __name: "sample-datasets",
+  __ssrInlineRender: true,
+  setup(__props) {
+    const showPreview = ref(false);
+    const previewData = ref(null);
+    return (_ctx, _push, _parent, _attrs) => {
+      _push(`<div${ssrRenderAttrs(mergeProps({ class: "max-w-4xl mx-auto" }, _attrs))}><div class="mb-6"><h1 class="text-2xl font-bold mb-2">Sample Datasets &amp; Public Data</h1><p class="text-gray-600"> Explore high-quality example datasets and learn about public datasets you can use for training. </p></div><div class="card mb-6"><h2 class="text-lg font-semibold mb-4">📦 Sample Datasets (Ready to Import)</h2><p class="text-sm text-gray-600 mb-4"> Download these sample datasets to see what high-quality training data looks like. You can import them directly into edukaAI. </p><div class="space-y-4"><div class="p-4 bg-blue-50 rounded-lg border border-blue-200"><div class="flex justify-between items-start mb-2"><div><h3 class="font-semibold text-blue-900">Coding Examples Dataset</h3><p class="text-sm text-blue-700">5 programming examples with detailed explanations</p></div><span class="px-2 py-1 bg-blue-100 text-blue-800 text-xs rounded">JSON</span></div><p class="text-sm text-gray-600 mb-3"> Includes: Python string manipulation, JavaScript variable declarations, React data fetching, SQL injection prevention, async/await patterns. </p><div class="flex gap-2"><a href="/sample-data/coding-examples.json" download class="inline-flex items-center gap-1 px-3 py-1.5 bg-blue-600 text-white text-sm rounded hover:bg-blue-700 transition-colors"><svg class="w-4 h-4" fill="none" stroke="currentColor" viewBox="0 0 24 24"><path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"></path></svg> Download JSON </a><button class="inline-flex items-center gap-1 px-3 py-1.5 bg-white border border-blue-300 text-blue-700 text-sm rounded hover:bg-blue-50 transition-colors"> 👁 Preview </button></div></div><div class="p-4 bg-green-50 rounded-lg border border-green-200"><div class="flex justify-between items-start mb-2"><div><h3 class="font-semibold text-green-900">General Knowledge Dataset</h3><p class="text-sm text-green-700">4 diverse examples: explanations, writing, analysis</p></div><span class="px-2 py-1 bg-green-100 text-green-800 text-xs rounded">JSON</span></div><p class="text-sm text-gray-600 mb-3"> Includes: Explaining photosynthesis to a child, professional email writing, remote work analysis, ML vs traditional programming explanation. </p><div class="flex gap-2"><a href="/sample-data/general-knowledge-examples.json" download class="inline-flex items-center gap-1 px-3 py-1.5 bg-green-600 text-white text-sm rounded hover:bg-green-700 transition-colors"><svg class="w-4 h-4" fill="none" stroke="currentColor" viewBox="0 0 24 24"><path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4"></path></svg> Download JSON </a><button class="inline-flex items-center gap-1 px-3 py-1.5 bg-white border border-green-300 text-green-700 text-sm rounded hover:bg-green-50 transition-colors"> 👁 Preview </button></div></div></div></div><div class="card mb-6"><h2 class="text-lg font-semibold mb-4">🌐 Public Datasets for Training</h2><p class="text-sm text-gray-600 mb-4"> These are well-known, publicly available datasets used by researchers and companies to train LLMs. You can download them and examine the format. </p><div class="space-y-4"><div class="p-4 border rounded-lg hover:shadow-md transition-shadow"><div class="flex justify-between items-start mb-2"><h3 class="font-semibold">Stanford Alpaca</h3><span class="px-2 py-1 bg-gray-100 text-gray-600 text-xs rounded">52K examples</span></div><p class="text-sm text-gray-600 mb-2"> One of the first open-source instruction-following datasets. Contains 52,000 instruction-output pairs generated using GPT-3.5. This dataset sparked the open-source LLM revolution. </p><div class="flex items-center gap-2 text-sm"><span class="text-gray-500">License: CC BY-NC 4.0 (Research only)</span></div><a href="https://github.com/tatsu-lab/stanford_alpaca" target="_blank" class="mt-2 inline-flex items-center gap-1 text-blue-600 hover:underline text-sm"> View on GitHub → </a></div><div class="p-4 border rounded-lg hover:shadow-md transition-shadow"><div class="flex justify-between items-start mb-2"><h3 class="font-semibold">Databricks Dolly</h3><span class="px-2 py-1 bg-gray-100 text-gray-600 text-xs rounded">15K examples</span></div><p class="text-sm text-gray-600 mb-2"> First commercially viable instruction dataset (CC BY-SA 3.0 license). Contains human-generated instructions covering brainstorming, classification, closed QA, generation, information extraction, and open QA. </p><div class="flex items-center gap-2 text-sm"><span class="text-green-600">✅ Commercial use allowed</span></div><a href="https://github.com/databrickslabs/dolly" target="_blank" class="mt-2 inline-flex items-center gap-1 text-blue-600 hover:underline text-sm"> View on GitHub → </a></div><div class="p-4 border rounded-lg hover:shadow-md transition-shadow"><div class="flex justify-between items-start mb-2"><h3 class="font-semibold">ShareGPT Dataset</h3><span class="px-2 py-1 bg-gray-100 text-gray-600 text-xs rounded">90K+ conversations</span></div><p class="text-sm text-gray-600 mb-2"> Real user conversations with ChatGPT, shared publicly. Shows natural user interactions and assistant responses. Great for understanding real-world conversation patterns. </p><div class="flex items-center gap-2 text-sm"><span class="text-gray-500">License: CC0 (Public Domain)</span></div><a href="https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered" target="_blank" class="mt-2 inline-flex items-center gap-1 text-blue-600 hover:underline text-sm"> View on HuggingFace → </a></div><div class="p-4 border rounded-lg hover:shadow-md transition-shadow"><div class="flex justify-between items-start mb-2"><h3 class="font-semibold">OpenOrca</h3><span class="px-2 py-1 bg-gray-100 text-gray-600 text-xs rounded">~4M examples</span></div><p class="text-sm text-gray-600 mb-2"> Massive dataset of reasoning traces (chain-of-thought) collected from GPT-4. Excellent for teaching models to show their work and reason step-by-step. One of the highest-quality large-scale datasets. </p><div class="flex items-center gap-2 text-sm"><span class="text-gray-500">License: MIT</span></div><a href="https://huggingface.co/datasets/Open-Orca/OpenOrca" target="_blank" class="mt-2 inline-flex items-center gap-1 text-blue-600 hover:underline text-sm"> View on HuggingFace → </a></div><div class="p-4 border rounded-lg hover:shadow-md transition-shadow"><div class="flex justify-between items-start mb-2"><h3 class="font-semibold">CodeAlpaca</h3><span class="px-2 py-1 bg-gray-100 text-gray-600 text-xs rounded">20K examples</span></div><p class="text-sm text-gray-600 mb-2"> Programming-focused instruction dataset. Contains code generation, explanation, and debugging examples across multiple programming languages. Perfect for training coding assistants. </p><div class="flex items-center gap-2 text-sm"><span class="text-gray-500">License: CC BY-NC 4.0 (Research only)</span></div><a href="https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k" target="_blank" class="mt-2 inline-flex items-center gap-1 text-blue-600 hover:underline text-sm"> View on HuggingFace → </a></div></div></div><div class="card"><h2 class="text-lg font-semibold mb-4">📥 How to Use These Datasets</h2><div class="space-y-4 text-sm"><div class="flex items-start gap-3"><div class="w-8 h-8 bg-blue-100 rounded-full flex items-center justify-center font-bold text-blue-600 flex-shrink-0">1</div><div><h4 class="font-medium">Download Sample Data</h4><p class="text-gray-600">Click &quot;Download JSON&quot; to get sample datasets in Alpaca format.</p></div></div><div class="flex items-start gap-3"><div class="w-8 h-8 bg-blue-100 rounded-full flex items-center justify-center font-bold text-blue-600 flex-shrink-0">2</div><div><h4 class="font-medium">Examine the Format</h4><p class="text-gray-600">Open the JSON file to see the structure: instruction, input, output, category, difficulty.</p></div></div><div class="flex items-start gap-3"><div class="w-8 h-8 bg-blue-100 rounded-full flex items-center justify-center font-bold text-blue-600 flex-shrink-0">3</div><div><h4 class="font-medium">Import or Create Similar</h4><p class="text-gray-600"> Use these as templates! Notice the quality: complete explanations, code examples, proper formatting. Create your own examples following this pattern. </p></div></div></div><div class="mt-6 p-4 bg-yellow-50 rounded-lg"><h4 class="font-medium text-yellow-800 mb-2">💡 Pro Tip: Learn from Examples</h4><p class="text-sm text-yellow-700 mb-2"> Before creating your own dataset, study these samples. Notice how good examples include: </p><ul class="list-disc list-inside ml-4 space-y-1 text-sm text-yellow-700"><li>Clear, specific instructions</li><li>Complete, thorough responses</li><li>Code blocks with syntax highlighting</li><li>Multiple approaches or solutions</li><li>Explanations of WHY, not just HOW</li></ul></div></div>`);
+      if (unref(showPreview)) {
+        _push(`<div class="fixed inset-0 bg-black/50 z-50 flex items-center justify-center p-4"><div class="bg-white rounded-xl max-w-3xl w-full max-h-[80vh] overflow-auto"><div class="p-6"><div class="flex justify-between items-center mb-4"><h3 class="text-lg font-semibold">Dataset Preview</h3><button class="text-gray-500 hover:text-gray-700"><svg class="w-6 h-6" fill="none" stroke="currentColor" viewBox="0 0 24 24"><path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M6 18L18 6M6 6l12 12"></path></svg></button></div>`);
+        if (unref(previewData)) {
+          _push(`<div class="space-y-4"><!--[-->`);
+          ssrRenderList(unref(previewData).examples.slice(0, 3), (example, idx) => {
+            _push(`<div class="p-4 bg-gray-50 rounded-lg"><div class="mb-2"><span class="text-xs font-semibold text-blue-600 uppercase">Example ${ssrInterpolate(idx + 1)}</span><span class="ml-2 text-xs text-gray-500">${ssrInterpolate(example.category)} | ${ssrInterpolate(example.difficulty)}</span></div><p class="font-medium mb-2">${ssrInterpolate(example.instruction)}</p><div class="text-sm text-gray-600 bg-white p-3 rounded border">${ssrInterpolate(example.output.substring(0, 200))}... </div></div>`);
+          });
+          _push(`<!--]-->`);
+          if (unref(previewData).examples.length > 3) {
+            _push(`<p class="text-center text-sm text-gray-500"> + ${ssrInterpolate(unref(previewData).examples.length - 3)} more examples </p>`);
+          } else {
+            _push(`<!---->`);
+          }
+          _push(`</div>`);
+        } else {
+          _push(`<!---->`);
+        }
+        _push(`</div></div></div>`);
+      } else {
+        _push(`<!---->`);
+      }
+      _push(`</div>`);
+    };
+  }
+};
+const _sfc_setup = _sfc_main.setup;
+_sfc_main.setup = (props, ctx) => {
+  const ssrContext = useSSRContext();
+  (ssrContext.modules || (ssrContext.modules = /* @__PURE__ */ new Set())).add("pages/sample-datasets.vue");
+  return _sfc_setup ? _sfc_setup(props, ctx) : void 0;
+};
+
+export { _sfc_main as default };
+//# sourceMappingURL=sample-datasets-CVLWMQUA.mjs.map

package/.output/server/chunks/build/sample-datasets-CVLWMQUA.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"sample-datasets-CVLWMQUA.mjs","sources":["../../../../node_modules/.cache/nuxt/.nuxt/dist/server/_nuxt/sample-datasets-CVLWMQUA.js"],"names":[],"mappings":"","x_google_ignoreList":[0]}