Small fixes for reading the input files correctly and to the OpenAIFi… (openai#1801)

robtinn · MW-OAI · web-flow · commit 80251ba3616e · 2025-05-07T06:50:27.000-07:00
Co-authored-by: MW-OAI &lt;mitchwelzen@openai.com&gt;
diff --git a/examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb b/examples/fine-tuned_qa/ft_retrieval_augmented_generation_qdrant.ipynb
@@ -11,6 +11,8 @@
     "\n",
     "We will also be integrating Qdrant and Few-Shot Learning to boost the model's performance and reduce hallucinations. This could serve as a practical guide for ML practitioners, data scientists, and AI Engineers interested in leveraging the power of OpenAI models for specific use-cases. 🤩\n",
     "\n",
+    "Note: This notebook uses the gpt-3.5-turbo model. Fine-tuning on the SQuAD dataset with this setup yields only minimal gains for more advanced models such as gpt-4o or gpt-4.1. As such, this notebook is primarily intended as a guide for fine-tuning workflows and retrieval-augmented generation (RAG) practices\n",
+    "\n",
     "## Why should you read this blog?\n",
     "\n",
     "You want to learn how to \n",
@@ -559,7 +561,7 @@
     "\n",
     "    def create_openai_file(self):\n",
     "        self.file_object = client.files.create(\n",
-    "            file=open(self.training_file_path, \"r\"),\n",
+    "            file=open(self.training_file_path, \"rb\"),\n",
     "            purpose=\"fine-tune\",\n",
     "        )\n",
     "\n",
@@ -571,19 +573,22 @@
     "\n",
     "    def create_fine_tuning_job(self):\n",
     "        self.fine_tuning_job = client.fine_tuning.jobs.create(\n",
-    "            training_file=self.file_object[\"id\"],\n",
+    "            training_file=self.file_object.id,\n",
     "            model=self.model_name,\n",
     "            suffix=self.suffix,\n",
     "        )\n",
     "\n",
     "    def wait_for_fine_tuning(self, sleep_time=45):\n",
-    "        while self.fine_tuning_job.status != 'succeeded':\n",
+    "        while True:\n",
+    "            # Retrieve the latest fine-tuning job status\n",
+    "            self.fine_tuning_job = client.fine_tuning.jobs.retrieve(self.fine_tuning_job.id)\n",
+    "            print(\"Job Status:\", self.fine_tuning_job.status)\n",
+    "            if self.fine_tuning_job.status in {'succeeded', 'failed', 'cancelled'}:\n",
+    "                break\n",
     "            time.sleep(sleep_time)\n",
-    "            self.fine_tuning_job.refresh()\n",
-    "            print(\"Job Status: \", self.fine_tuning_job.status)\n",
     "\n",
     "    def retrieve_fine_tuned_model(self):\n",
-    "        self.model_id = client.fine_tuning.jobs.retrieve(self.fine_tuning_job[\"id\"]).fine_tuned_model\n",
+    "        self.model_id = client.fine_tuning.jobs.retrieve(self.fine_tuning_job.id).fine_tuned_model\n",
     "        return self.model_id\n",
     "\n",
     "    def fine_tune_model(self):\n",
