outputs corrected

docs/tutorials/github_rag_llamaindex_argilla.ipynb

@@ -28,18 +28,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[31mERROR: Invalid requirement: 'argilla-llama-index>=1.0.0 llama-index-readers-github==0.1.9'\u001b[0m\u001b[31m\n",
-      "\u001b[0mNote: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "%pip install \"argilla-llama-index>=1.0.0\" \"llama-index-readers-github==0.1.9\""
    ]
@@ -63,7 +54,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -110,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -139,7 +130,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -157,7 +148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -204,9 +195,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The FeedbackDataset in Argilla is designed to be a versatile and adaptable dataset that supports a wide range of NLP tasks, including those focused on large language models. It offers the ability to handle multiple tasks on the same record within a coherent user interface, supports multiple annotators per record, customizable tasks, and synchronization with a database. While it currently may lack some features present in older datasets, new features are continuously being added to the FeedbackDataset over time to enhance its capabilities.\n"
+     ]
+    }
+   ],
    "source": [
     "index = VectorStoreIndex.from_documents(documents)\n",
     "\n",
@@ -241,9 +240,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Question: What types of dataset can I choose from in Argilla?\n",
+      "Answer: You can choose between older datasets tailored to singular NLP tasks and the FeedbackDataset, which is designed to support a wider range of NLP tasks, including those centered on large language models.\n",
+      "----------------------------\n",
+      "Question: How can I create and update an Argilla dataset?\n",
+      "Answer: To create and update an Argilla dataset, you can add new fields and questions to the dataset using the Python SDK. For local `FeedbackDataset` instances, you can extend the fields and questions lists with new entries or remove existing ones as needed. Additionally, you can add metadata properties to the dataset, change metadata properties' titles, and delete metadata properties. For vector settings, you can update them for both local and remote `FeedbackDataset` instances. It's important to note that configuration updates are limited for remote datasets to avoid inconsistencies between the dataset and defined records and annotations.\n",
+      "----------------------------\n",
+      "Question: Can I upload Markdown files into an Argilla dataset?\n",
+      "Answer: You can render images in the Argilla UI using Markdown files by setting `use_markdown` to `True`. Additionally, you can pass a URL in the metadata field `_image_url` to render images in the Argilla UI for tasks like Text Classification and Token Classification.\n",
+      "----------------------------\n",
+      "Question: Could you explain how to annotate datasets in Argilla?\n",
+      "Answer: To annotate datasets in Argilla, users can utilize the Argilla UI which offers a user-friendly interface for annotating records. Depending on the task type, such as text classification, multi-label text classification, token classification, or Text2Text, different annotation methods are available. For text classification tasks, users can select the label(s) that best describe the record, validate predictions, and remove validated labels if needed. In multi-label text classification, users can select multiple labels, validate predictions with percentages above 50%, and clear or discard annotations as required. \n",
+      "\n",
+      "In token classification tasks, users can highlight words in the text and assign labels, validate predictions, remove specific labels, clear all annotations, and discard records. For Text2Text datasets, users can edit annotations in a text box, validate predictions, clear or discard changes, and discard records if necessary. After annotating a record, users can validate the changes made, revert to the previous state, or discard the record from the dataset. The Argilla UI also provides filters to help users search and filter records efficiently.\n",
+      "----------------------------\n"
+     ]
+    }
+   ],
    "source": [
     "questions = [\n",
     "    \"What types of dataset can I choose from in Argilla?\",\n",