Merge branch 'main' into add-evaluation-cookbook

Author: jannikmaierhoefer

authors.yaml

@@ -271,4 +271,9 @@ erikakettleson-openai:
 jannik-maierhofer:
   name: "Jannik Maierhöfer"
   website: "https://www.linkedin.com/in/maierhoefer/"
-  avatar: "https://avatars.githubusercontent.com/u/48529566"
+  avatar: "https://avatars.githubusercontent.com/u/48529566?v=4"
+
+josiah-openai:
+  name: "Josiah Grace"
+  website: "https://www.linkedin.com/in/josiahbgrace"
+  avatar: "https://avatars.githubusercontent.com/u/181146311?v=4"

examples/evaluation/Getting_Started_with_OpenAI_Evals.ipynb

@@ -21,6 +21,9 @@
     }
    },
    "source": [
+    "**Note: OpenAI now has a hosted evals product with an API! We recommend you use this instead.\n",
+    "See [Evals](https://platform.openai.com/docs/guides/evals)**\n",
+    "\n",
     "The [OpenAI Evals](https://github.com/openai/evals/tree/main) framework consists of\n",
     "1. A framework to evaluate an LLM (large language model) or a system built on top of an LLM.\n",
     "2. An open-source registry of challenging evals\n",
@@ -419,7 +422,7 @@
      "text": [
       "[2024-03-26 19:44:39,836] [registry.py:257] Loading registry from /Users/shyamal/.virtualenvs/openai/lib/python3.11/site-packages/evals/registry/evals\n",
       "[2024-03-26 19:44:43,623] [registry.py:257] Loading registry from /Users/shyamal/.evals/evals\n",
-      "[2024-03-26 19:44:43,635] [oaieval.py:189] \u001B[1;35mRun started: 240327024443FACXGMKA\u001B[0m\n",
+      "[2024-03-26 19:44:43,635] [oaieval.py:189] \u001b[1;35mRun started: 240327024443FACXGMKA\u001b[0m\n",
       "[2024-03-26 19:44:43,663] [registry.py:257] Loading registry from /Users/shyamal/.virtualenvs/openai/lib/python3.11/site-packages/evals/registry/modelgraded\n",
       "[2024-03-26 19:44:43,851] [registry.py:257] Loading registry from /Users/shyamal/.evals/modelgraded\n",
       "[2024-03-26 19:44:43,853] [data.py:90] Fetching /Users/shyamal/.virtualenvs/openai/lib/python3.11/site-packages/evals/registry/data/sql/spider_sql.jsonl\n",