chore: import upstream snapshot with attribution

examples/codex/data/docs/getting_started_evals_pre_repair.ipynb

@@ -0,0 +1,111 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Getting started with Evals, sampled fixture\n",
+    "\n",
+    "This fixture mirrors the Cookbook Evals walkthrough but uses tiny local records instead of running a long benchmark.\n"
+   ],
+   "id": "cell-000"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "MODEL = \"gpt-3.5-turbo\"  # stale model kept intentionally for review\n",
+    "\n",
+    "schema = \"Table cars_data, columns = [Id, MPG, Cylinders, Horsepower, Year]\"\n",
+    "examples = [\n",
+    "    {\"question\": \"Which cars have more than 100 horsepower?\", \"ideal\": \"SELECT Id FROM cars_data WHERE Horsepower > 100\"},\n",
+    "    {\"question\": \"How many cars are from 1970?\", \"ideal\": \"SELECT count(*) FROM cars_data WHERE Year = 1970\"},\n",
+    "]\n"
+   ],
+   "id": "cell-001"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_eval_rows(records):\n",
+    "    return [\n",
+    "        {\n",
+    "            \"input\": [\n",
+    "                {\"role\": \"system\", \"content\": f\"Answer with SQLite SQL. {schema}\"},\n",
+    "                {\"role\": \"user\", \"content\": record[\"question\"]},\n",
+    "            ],\n",
+    "            \"ideal\": record[\"ideal\"],\n",
+    "        }\n",
+    "        for record in records\n",
+    "    ]\n",
+    "\n",
+    "eval_rows = make_eval_rows(examples)\n",
+    "eval_rows[0]\n"
+   ],
+   "id": "cell-002"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Legacy CLI command kept as a repair target; this cell only records it.\n",
+    "EVAL_COMMAND = \"oaieval gpt-3.5-turbo spider-sql --max_samples 25\"\n",
+    "print(EVAL_COMMAND)\n"
+   ],
+   "id": "cell-003"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Manual log-name placeholder kept as a repair target.\n",
+    "log_name = \"240327024443FACXGMKA_gpt-3.5-turbo_spider-sql.jsonl\"  # EDIT THIS\n",
+    "local_events = [\n",
+    "    {\"type\": \"final_report\", \"data\": {\"accuracy\": 0.5}},\n",
+    "    {\"type\": \"sampling\", \"data\": {\"prompt\": eval_rows[0][\"input\"], \"sampled\": \"SELECT Id FROM cars_data WHERE Horsepower > 100\"}},\n",
+    "]\n",
+    "final_report = next(event[\"data\"] for event in local_events if event[\"type\"] == \"final_report\")\n",
+    "final_report\n"
+   ],
+   "id": "cell-004"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "pygments_lexer": "ipython3"
+  },
+  "codex_case_study": {
+   "source_repo": "https://github.com/openai/openai-cookbook",
+   "source_path": "examples/evaluation/Getting_Started_with_OpenAI_Evals.ipynb",
+   "source_commit": "96b1d67^",
+   "purpose": "Runtime-sampled pre-repair fixture derived from a Cookbook documentation reliability run.",
+   "sampling_note": "Compact Evals-style maintenance sample with stale model, deprecated CLI, and result-log issues.",
+   "repair_story": {
+    "target_iteration": 2,
+    "repair_depth": "Two-pass cleanup: first modernize the obvious stale Evals flow, then use validation feedback to remove result-log brittleness.",
+    "issue_layers": [
+     "stale model",
+     "deprecated oaieval command",
+     "manual log-name/runtime result dependency"
+    ]
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/codex/data/docs/knowledge_retrieval_pre_repair.ipynb

@@ -0,0 +1,116 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Function calling for knowledge retrieval, sampled fixture\n",
+    "\n",
+    "This fixture is derived from the Cookbook arXiv retrieval example. It uses two local paper records so execution stays fast while the repair loop still sees legacy tool-calling patterns.\n"
+   ],
+   "id": "cell-000"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "GPT_MODEL = \"gpt-4-turbo-preview\"  # stale model kept intentionally for the repair loop\n",
+    "\n",
+    "papers = [\n",
+    "    {\"title\": \"PPO for sequence generation\", \"article_url\": \"https://example.com/ppo\", \"summary\": \"PPO stabilizes policy updates with clipped objectives.\"},\n",
+    "    {\"title\": \"Retrieval augmented generation\", \"article_url\": \"https://example.com/rag\", \"summary\": \"RAG combines retrieval with generation to ground answers.\"},\n",
+    "]\n"
+   ],
+   "id": "cell-001"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_articles(query, top_k=2):\n",
+    "    query_terms = set(query.lower().split())\n",
+    "    ranked = sorted(\n",
+    "        papers,\n",
+    "        key=lambda paper: len(query_terms & set((paper[\"title\"] + \" \" + paper[\"summary\"]).lower().split())),\n",
+    "        reverse=True,\n",
+    "    )\n",
+    "    return ranked[:top_k]\n",
+    "\n",
+    "get_articles(\"ppo reinforcement learning\")\n"
+   ],
+   "id": "cell-002"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def read_article_and_summarize(query):\n",
+    "    article = get_articles(query, top_k=1)[0]\n",
+    "    return f'{article[\"title\"]}: {article[\"summary\"]}'\n",
+    "\n",
+    "read_article_and_summarize(\"ppo sequence generation\")\n"
+   ],
+   "id": "cell-003"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Legacy function-calling schema kept as a repair target.\n",
+    "arxiv_functions = [\n",
+    "    {\n",
+    "        \"name\": \"get_articles\",\n",
+    "        \"description\": \"Use this function to get academic papers from a local article index.\",\n",
+    "        \"parameters\": {\n",
+    "            \"type\": \"object\",\n",
+    "            \"properties\": {\"query\": {\"type\": \"string\"}},\n",
+    "            \"required\": [\"query\"],\n",
+    "        },\n",
+    "    }\n",
+    "]\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"How does PPO work?\"}]\n",
+    "print(arxiv_functions[0][\"name\"], messages[0][\"content\"])\n"
+   ],
+   "id": "cell-004"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "pygments_lexer": "ipython3"
+  },
+  "codex_case_study": {
+   "source_repo": "https://github.com/openai/openai-cookbook",
+   "source_path": "examples/How_to_call_functions_for_knowledge_retrieval.ipynb",
+   "source_commit": "96b1d67^",
+   "purpose": "Runtime-sampled pre-repair fixture derived from a Cookbook documentation reliability run.",
+   "sampling_note": "Compact knowledge-retrieval maintenance sample with stale model and legacy tool-calling issues.",
+   "repair_story": {
+    "target_iteration": 3,
+    "repair_depth": "Three-pass cleanup: modernize model/API shape, then tighten runnable local setup, then restore the full retrieval teaching flow.",
+    "issue_layers": [
+     "stale chat model",
+     "legacy function-calling schema",
+     "setup/runnability gap",
+     "end-to-end retrieval flow integrity"
+    ]
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/codex/data/docs/qdrant_embeddings_search_pre_repair.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Qdrant embedding search, sampled fixture\n",
+    "\n",
+    "This fixture is derived from the Cookbook Qdrant search example. It keeps the same teaching arc with a tiny local article set so validation can execute quickly.\n"
+   ],
+   "id": "cell-000"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from math import sqrt\n",
+    "\n",
+    "EMBEDDING_MODEL = \"text-embedding-ada-002\"  # legacy model kept intentionally for the repair loop\n",
+    "\n",
+    "articles = [\n",
+    "    {\"id\": 1, \"title\": \"Modern art in Europe\", \"url\": \"https://example.com/art\", \"content\": \"Cubism and surrealism reshaped European museums.\"},\n",
+    "    {\"id\": 2, \"title\": \"Scottish battle history\", \"url\": \"https://example.com/scotland\", \"content\": \"Bannockburn and Stirling Bridge shaped Scottish history.\"},\n",
+    "    {\"id\": 3, \"title\": \"Space telescope discoveries\", \"url\": \"https://example.com/space\", \"content\": \"Modern telescopes reveal planets, galaxies, and stars.\"},\n",
+    "]\n"
+   ],
+   "id": "cell-001"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def embed(text: str) -> list[float]:\n",
+    "    buckets = [0.0, 0.0, 0.0, 0.0]\n",
+    "    for index, char in enumerate(text.lower()):\n",
+    "        buckets[index % len(buckets)] += ord(char) / 1000\n",
+    "    length = sqrt(sum(value * value for value in buckets)) or 1\n",
+    "    return [round(value / length, 4) for value in buckets]\n",
+    "\n",
+    "for article in articles:\n",
+    "    article[\"title_vector\"] = embed(article[\"title\"])\n",
+    "    article[\"content_vector\"] = embed(article[\"content\"])\n"
+   ],
+   "id": "cell-002"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class LocalQdrant:\n",
+    "    def __init__(self, rows):\n",
+    "        self.rows = rows\n",
+    "\n",
+    "    def search(self, collection_name, query_vector, limit=3, query_filter=None):\n",
+    "        vector_name, query = query_vector\n",
+    "        scored = []\n",
+    "        for row in self.rows:\n",
+    "            vector = row[f\"{vector_name}_vector\"]\n",
+    "            score = sum(a * b for a, b in zip(query, vector))\n",
+    "            scored.append((score, row))\n",
+    "        return sorted(scored, reverse=True)[:limit]\n",
+    "\n",
+    "    def query_points(self, collection_name, query, using=\"title\", limit=3):\n",
+    "        return self.search(collection_name, (using, query), limit=limit)\n",
+    "\n",
+    "qdrant = LocalQdrant(articles)\n"
+   ],
+   "id": "cell-003"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def query_qdrant(query, collection_name, vector_name=\"title\", top_k=3):\n",
+    "    embedded_query = embed(query)\n",
+    "    return qdrant.search(\n",
+    "        collection_name=collection_name,\n",
+    "        query_vector=(vector_name, embedded_query),\n",
+    "        limit=top_k,\n",
+    "        query_filter=None,\n",
+    "    )\n",
+    "\n",
+    "for score, article in query_qdrant(\"modern art in Europe\", \"Articles\", \"title\"):\n",
+    "    print(f'{article[\"title\"]}: {score:.3f}')\n"
+   ],
+   "id": "cell-004"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "pygments_lexer": "ipython3"
+  },
+  "codex_case_study": {
+   "source_repo": "https://github.com/openai/openai-cookbook",
+   "source_path": "examples/vector_databases/qdrant/Using_Qdrant_for_embeddings_search.ipynb",
+   "source_commit": "96b1d67^",
+   "purpose": "Runtime-sampled pre-repair fixture derived from a Cookbook documentation reliability run.",
+   "sampling_note": "Compact Qdrant-style maintenance sample with stale embedding-model and query API issues.",
+   "repair_story": {
+    "target_iteration": 1,
+    "repair_depth": "One-pass cleanup: modernize the local Qdrant query path and clarify the sampled fixture framing.",
+    "issue_layers": [
+     "stale embedding model",
+     "deprecated qdrant.search call",
+     "fixture framing/setup clarity"
+    ]
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}