Add Navrasa LLM download and explanation sections

Author: NirantK

docs/examples/Hindi_Tamil_RAG_with_Navrsasa7B.ipynb

@@ -161,6 +161,15 @@
         "We'll use the 7B model here, the 2B model isn't great and was suffering from reading comprehension challenges."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Downloading the Navrasa LLM\n",
+        "\n",
+        "We'll download the Navrasa LLM from TeluguLLM-Labs. This is a 7B model with PEFT."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -196,23 +205,21 @@
       ]
     },
     {
-      "cell_type": "code",
-      "execution_count": null,
+      "cell_type": "markdown",
       "metadata": {
-        "id": "4T-n_3TAj2VA"
+        "id": "LWVHPXIFzzgW"
       },
-      "outputs": [],
       "source": [
-        "questions, contexts = list(ds['question']), list(ds['context'])"
+        "## Embed the Context into Vectors"
       ]
     },
     {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "LWVHPXIFzzgW"
-      },
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
       "source": [
-        "## Embed the Context into Vectors"
+        "questions, contexts = list(ds['question']), list(ds['context'])"
       ]
     },
     {
@@ -310,6 +317,15 @@
         "search_client.upsert(collection_name=\"hindi_tamil_contexts\", points=context_points)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Selecting a Question\n",
+        "\n",
+        "I've randomly selected a question here, with a specific and we then find the answer to it. We have the correct answer for it too -- so we can compare the two when you run the code."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -345,6 +361,13 @@
         "len(search_context_text)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Running the Model with a Question & Context"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,