Merge branch 'main' into km/model-selection-cookbook-updates

Author: erikakettleson-openai

.gitignore

@@ -140,6 +140,7 @@ examples/fine-tuned_qa/local_cache/*
 
 # PyCharm files
 .idea/
+.cursorignore
 
 # VS Code files
 .vscode/

authors.yaml

@@ -3,6 +3,11 @@
 # You can optionally customize how your information shows up cookbook.openai.com over here.
 # If your information is not present here, it will be pulled from your GitHub profile.
 
+minh-hoque:
+  name: "Minhajul Hoque"
+  website: "https://www.linkedin.com/in/minhajul-hoque-83242b163/"
+  avatar: "https://avatars.githubusercontent.com/u/84698472?v=4"
+
 shikhar-cyber:
   name: "Shikhar Kwatra"
   website: "https://www.linkedin.com/in/shikharkwatra/"
@@ -126,13 +131,13 @@ aaronwilkowitz-openai:
 charuj:
   name: "Charu Jaiswal"
   website: "https://www.linkedin.com/in/charu-j-8a866471"
-  avatar: "https://avatars.githubusercontent.com/u/18404643?v=4" 
+  avatar: "https://avatars.githubusercontent.com/u/18404643?v=4"
 
 rupert-openai:
   name: "Rupert Truman"
   website: "https://www.linkedin.com/in/rupert-truman/"
   avatar: "https://avatars.githubusercontent.com/u/171234447"
-  
+
 keelan-openai:
   name: "Keelan Schule"
   website: "https://www.linkedin.com/in/keelanschule/"
@@ -171,8 +176,8 @@ evanweiss-openai:
 girishd:
   name: "Girish Dusane"
   website: "https://www.linkedin.com/in/girishdusane/"
-  avatar: "https://avatars.githubusercontent.com/u/272708"   
-  
+  avatar: "https://avatars.githubusercontent.com/u/272708"
+
 lxing-oai:
   name: "Luke Xing"
   website: "https://www.linkedin.com/in/lukexing/"
@@ -227,7 +232,7 @@ erickgort:
   name: "Erick Gort"
   website: "https://www.linkedin.com/in/erick-gort-32ab1678/"
   avatar: "https://avatars.githubusercontent.com/u/189261906?v=4"
-  
+
 kylecote-tray:
   name: "Kyle Cote"
   website: "https://github.com/kylecote-tray"
@@ -297,7 +302,7 @@ rzhao-openai:
   name: "Randy Zhao"
   website: "https://www.linkedin.com/in/randy-zhao-27433616b"
   avatar: "https://avatars.githubusercontent.com/u/208724779?v=4"
-  
+
 brandonbaker-openai:
   name: "Brandon Baker"
   website: "https://www.linkedin.com/in/brandonbaker18"

examples/Speech_transcription_methods.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",