Update gptv terminology to gpt-4v (#1093)

examples/How_to_combine_GPT4v_with_RAG_Outfit_Assistant.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# How to combine GPTV with RAG - Create a Clothing Matchmaker App\n",
+    "# How to combine GPT-4V with RAG - Create a Clothing Matchmaker App\n",
     "\n",
     "Welcome to the Clothing Matchmaker App Jupyter Notebook! This project demonstrates the power of the GPT-4-vision model in analyzing images of clothing items and extracting key features such as color, style, and type. The core of our app relies on this advanced image analysis model developed by OpenAI, which enables us to accurately identify the characteristics of the input clothing item.\n",
     "\n",
@@ -616,7 +616,7 @@
    "source": [
     "### Guardrails\n",
     "\n",
-    "In the context of using Large Language Models (LLMs) like GPTv, \"guardrails\" refer to mechanisms or checks put in place to ensure that the model's output remains within desired parameters or boundaries. These guardrails are crucial for maintaining the quality and relevance of the model's responses, especially when dealing with complex or nuanced tasks.\n",
+    "In the context of using Large Language Models (LLMs) like GPT-4v, \"guardrails\" refer to mechanisms or checks put in place to ensure that the model's output remains within desired parameters or boundaries. These guardrails are crucial for maintaining the quality and relevance of the model's responses, especially when dealing with complex or nuanced tasks.\n",
     "\n",
     "Guardrails are useful for several reasons:\n",
     "\n",
@@ -625,7 +625,7 @@
     "3. **Safety**: They prevent the model from generating harmful, offensive, or inappropriate content.\n",
     "4. **Contextual Relevance**: They ensure that the model's output is contextually relevant to the specific task or domain it is being used for.\n",
     "\n",
-    "In our case, we are using GPTv to analyze fashion images and suggest items that would complement an original outfit. To implement guardrails, we can **refine results**: After obtaining initial suggestions from GPTv, we can send the original image and the suggested items back to the model. We can then ask GPTv to evaluate whether each suggested item would indeed be a good fit for the original outfit.\n",
+    "In our case, we are using GPT-4v to analyze fashion images and suggest items that would complement an original outfit. To implement guardrails, we can **refine results**: After obtaining initial suggestions from GPT-4v, we can send the original image and the suggested items back to the model. We can then ask GPT-4v to evaluate whether each suggested item would indeed be a good fit for the original outfit.\n",
     "\n",
     "This gives the model the ability to self-correct and adjust its own output based on feedback or additional information. By implementing these guardrails and enabling self-correction, we can enhance the reliability and usefulness of the model's output in the context of fashion analysis and recommendation.\n",
     "\n",

registry.yaml

@@ -1196,8 +1196,8 @@
   tags:
     - guardrails
 
-- title: How to combine GPTv with RAG to create a clothing matchmaker app
-  path: examples/How_to_combine_GPTv_with_RAG_Outfit_Assistant.ipynb
+- title: How to combine GPT4 with vision with RAG to create a clothing matchmaker app
+  path: examples/How_to_combine_GPT4v_with_RAG_Outfit_Assistant.ipynb
   date: 2024-02-16
   authors:
     - teomusatoiu