Fine tuning QA example using legacy code and needs update

[bojanbabic]

Instead of using search functionality, it should be using embeddings search.

This the diff in order to make this notebook work with the current version of the APIs.

diff --git a/examples/fine-tuned_qa/olympics-3-train-qa.ipynb b/examples/fine-tuned_qa/olympics-3-train-qa.ipynb
index c046e3c..15654d9 100644
--- a/examples/fine-tuned_qa/olympics-3-train-qa.ipynb
+++ b/examples/fine-tuned_qa/olympics-3-train-qa.ipynb
@@ -1,12 +1,5 @@
 {
  "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "<span style=\"color:orange; font-weight:bold\">Note: To answer questions based on text documents, we recommend the procedure in <a href=\"https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb\">Question Answering using Embeddings</a>. Some of the code below may rely on <a href=\"https://github.com/openai/openai-cookbook/tree/main/transition_guides_for_deprecated_API_endpoints\">deprecated API endpoints</a>.</span>"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -157,6 +150,19 @@
     "df.head()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_embedding(text, model=\"text-embedding-ada-002\"):\n",
+    "    text = text.replace(\"\\n\", \" \")\n",
+    "    return openai.Embedding.create(input = [text], model=model)['data'][0]['embedding']\n",
+    "\n",
+    "df['questions_embedding'] = df.questions.apply(lambda x: get_embedding(x, model='text-embedding-ada-002'))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -238,28 +244,22 @@
    "outputs": [],
    "source": [
     "import random\n",
+    "from openai.embeddings_utils import cosine_similarity\n",
     "\n",
-    "def get_random_similar_contexts(question, context, file_id=olympics_search_fileid, search_model='ada', max_rerank=10):\n",
-    "    \"\"\"\n",
-    "    Find similar contexts to the given context using the search file\n",
+    "def get_random_similar_contexts(df, question, context, max_rerank=10, search_model='text-embedding-ada-002'):\n",
     "    \"\"\"\n",
-    "    try:\n",
-    "        results = openai.Engine(search_model).search(\n",
-    "            search_model=search_model, \n",
-    "            query=question, \n",
-    "            max_rerank=max_rerank,\n",
-    "            file=file_id\n",
-    "        )\n",
-    "        candidates = []\n",
-    "        for result in results['data'][:3]:\n",
-    "            if result['text'] == context:\n",
-    "                continue\n",
-    "            candidates.append(result['text'])\n",
-    "        random_candidate = random.choice(candidates)\n",
-    "        return random_candidate\n",
-    "    except Exception as e:\n",
-    "        print(e)\n",
-    "        return \"\"\n",
+    "    Find similar contexts to the given context using question embeddings search\n",
+    "    \"\"\"    \n",
+    "    embedding = get_embedding(question, search_model)\n",
+    "    df['tmp_question_similarities'] = df.questions_embedding.apply(lambda x: cosine_similarity(x, embedding))\n",
+    "    res = df.sort_values('tmp_question_similarities', ascending=False).head(max_rerank)\n",