Add the usage instructions for generated_message_length_comparison.ipynb

generated_message_length_comparison.ipynb

@@ -1,10 +1,37 @@
 {
  "cells": [
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": [
+    "### How to run\n",
+    "\n",
+    "* Install libraries using the cell below (for grazie-api-gateway-client you will have to add a custom JB repository)\n",
+    "* Put the production prompt to file `data/prod_prompt.txt`\n",
+    "* Environment variables:\n",
+    "    - `GRAZIE_API_JWT_TOKEN` -- JWT token for grazie (check `api_wrappers/grazie_wrapper.py` to adjust the client initialization if necessary)\n",
+    "    - `HF_TOKEN` -- should _not_ be required; however, if it is, set it to a valid Hugging Face token"
+   ],
+   "id": "77d51d55b41735cf"
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "source": [
+    "!pip install grazie-api-gateway-client\n",
+    "!pip install tqdm\n",
+    "!pip install pandas\n",
+    "!pip install datasets"
+   ],
+   "id": "91fa273e8987f6f6",
+   "outputs": [],
+   "execution_count": null
+  },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-05-31T13:59:45.809229Z",
-     "start_time": "2024-05-31T13:59:45.738228Z"
+     "end_time": "2024-05-31T16:15:11.790663Z",
+     "start_time": "2024-05-31T16:15:11.777607Z"
     }
    },
    "cell_type": "code",
@@ -17,13 +44,13 @@
    ],
    "id": "ce11a4c781c152e",
    "outputs": [],
-   "execution_count": 9
+   "execution_count": 20
   },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-05-31T13:59:46.750857Z",
-     "start_time": "2024-05-31T13:59:46.726738Z"
+     "end_time": "2024-05-31T16:15:13.223782Z",
+     "start_time": "2024-05-31T16:15:13.207891Z"
     }
    },
    "cell_type": "code",
@@ -39,48 +66,21 @@
    ],
    "id": "84a769c8765a7b64",
    "outputs": [],
-   "execution_count": 10
+   "execution_count": 21
   },
   {
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-05-31T14:00:17.941407Z",
-     "start_time": "2024-05-31T13:59:48.952862Z"
-    }
-   },
+   "metadata": {},
    "cell_type": "code",
    "source": "generate_commit_message_prod(\"TEST\")",
    "id": "af2f20def94b0490",
-   "outputs": [
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[1;31mRequestFailedException\u001B[0m                    Traceback (most recent call last)",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\api_wrappers\\grazie_wrapper.py:35\u001B[0m, in \u001B[0;36mllm_request\u001B[1;34m(prompt)\u001B[0m\n\u001B[0;32m     34\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m---> 35\u001B[0m     output \u001B[38;5;241m=\u001B[39m \u001B[43mclient\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mchat\u001B[49m\u001B[43m(\u001B[49m\n\u001B[0;32m     36\u001B[0m \u001B[43m        \u001B[49m\u001B[43mchat\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mChatPrompt\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     37\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43madd_system\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mYou are a helpful assistant.\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m)\u001B[49m\n\u001B[0;32m     38\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43madd_user\u001B[49m\u001B[43m(\u001B[49m\u001B[43mprompt\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m     39\u001B[0m \u001B[43m        \u001B[49m\u001B[43mprofile\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mLLMProfile\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconfig\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mLLM_MODEL\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     40\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241m.\u001B[39mcontent\n\u001B[0;32m     41\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m:\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\grazie\\api\\client\\gateway.py:193\u001B[0m, in \u001B[0;36mGrazieApiGatewayClient.chat\u001B[1;34m(self, chat, profile, prompt_id, parameters, headers)\u001B[0m\n\u001B[0;32m    192\u001B[0m chunks: List[ChatResponseStream] \u001B[38;5;241m=\u001B[39m []\n\u001B[1;32m--> 193\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m stream_response \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mchat_stream(chat, profile\u001B[38;5;241m=\u001B[39mprofile, prompt_id\u001B[38;5;241m=\u001B[39mprompt_id, parameters\u001B[38;5;241m=\u001B[39mparameters, headers\u001B[38;5;241m=\u001B[39mheaders):\n\u001B[0;32m    194\u001B[0m     chunks\u001B[38;5;241m.\u001B[39mappend(stream_response)\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\grazie\\api\\client\\gateway.py:254\u001B[0m, in \u001B[0;36mGrazieApiGatewayClient.chat_stream\u001B[1;34m(self, chat, profile, prompt_id, parameters, headers)\u001B[0m\n\u001B[0;32m    246\u001B[0m response \u001B[38;5;241m=\u001B[39m requests\u001B[38;5;241m.\u001B[39mpost(\n\u001B[0;32m    247\u001B[0m     url\u001B[38;5;241m=\u001B[39m\u001B[38;5;124mf\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;132;01m{\u001B[39;00m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_api_gateway_url\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m/\u001B[39m\u001B[38;5;132;01m{\u001B[39;00m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_auth_type\u001B[38;5;241m.\u001B[39mvalue\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m/v5/llm/chat/stream/v6\u001B[39m\u001B[38;5;124m\"\u001B[39m,\n\u001B[0;32m    248\u001B[0m     headers\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_generate_headers(headers),\n\u001B[1;32m   (...)\u001B[0m\n\u001B[0;32m    251\u001B[0m     stream\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m\n\u001B[0;32m    252\u001B[0m )\n\u001B[1;32m--> 254\u001B[0m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_raise_if_error\u001B[49m\u001B[43m(\u001B[49m\u001B[43mresponse\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    256\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m event \u001B[38;5;129;01min\u001B[39;00m _decode_llm_sse(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parse_sse_response(response\u001B[38;5;241m.\u001B[39miter_lines()), LLMChatEventV6):\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\grazie\\api\\client\\gateway.py:298\u001B[0m, in \u001B[0;36mGrazieApiGatewayClient._raise_if_error\u001B[1;34m(self, response)\u001B[0m\n\u001B[0;32m    297\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m response\u001B[38;5;241m.\u001B[39mstatus_code \u001B[38;5;241m!=\u001B[39m \u001B[38;5;241m200\u001B[39m:\n\u001B[1;32m--> 298\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m RequestFailedException(\u001B[38;5;124mf\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;132;01m{\u001B[39;00mresponse\u001B[38;5;241m.\u001B[39mstatus_code\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m Error: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mresponse\u001B[38;5;241m.\u001B[39mreason\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m. \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mresponse\u001B[38;5;241m.\u001B[39mtext\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m\"\u001B[39m)\n",
-      "\u001B[1;31mRequestFailedException\u001B[0m: 401 Error: Unauthorized. ",
-      "\nDuring handling of the above exception, another exception occurred:\n",
-      "\u001B[1;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
-      "Cell \u001B[1;32mIn[11], line 1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m \u001B[43mgenerate_commit_message_prod\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mTEST\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m)\u001B[49m\n",
-      "Cell \u001B[1;32mIn[10], line 8\u001B[0m, in \u001B[0;36mgenerate_commit_message_prod\u001B[1;34m(diff)\u001B[0m\n\u001B[0;32m      7\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mgenerate_commit_message_prod\u001B[39m(diff):\n\u001B[1;32m----> 8\u001B[0m \t\u001B[43mgenerate_for_prompt\u001B[49m\u001B[43m(\u001B[49m\u001B[43mprod_prompt\u001B[49m\u001B[43m(\u001B[49m\u001B[43mdiff\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\api_wrappers\\grazie_wrapper.py:57\u001B[0m, in \u001B[0;36mgenerate_for_prompt\u001B[1;34m(prompt)\u001B[0m\n\u001B[0;32m     54\u001B[0m     LLM_CACHE_USED[prompt] \u001B[38;5;241m=\u001B[39m \u001B[38;5;241m0\u001B[39m\n\u001B[0;32m     56\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m LLM_CACHE_USED[prompt] \u001B[38;5;241m>\u001B[39m\u001B[38;5;241m=\u001B[39m \u001B[38;5;28mlen\u001B[39m(LLM_CACHE[prompt]):\n\u001B[1;32m---> 57\u001B[0m     new_response \u001B[38;5;241m=\u001B[39m \u001B[43mllm_request\u001B[49m\u001B[43m(\u001B[49m\u001B[43mprompt\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     58\u001B[0m     LLM_CACHE[prompt]\u001B[38;5;241m.\u001B[39mappend(new_response)\n\u001B[0;32m     60\u001B[0m     \u001B[38;5;28;01mwith\u001B[39;00m \u001B[38;5;28mopen\u001B[39m(LLM_CACHE_FILE, \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mwb\u001B[39m\u001B[38;5;124m\"\u001B[39m) \u001B[38;5;28;01mas\u001B[39;00m file:\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\api_wrappers\\grazie_wrapper.py:42\u001B[0m, in \u001B[0;36mllm_request\u001B[1;34m(prompt)\u001B[0m\n\u001B[0;32m     35\u001B[0m         output \u001B[38;5;241m=\u001B[39m client\u001B[38;5;241m.\u001B[39mchat(\n\u001B[0;32m     36\u001B[0m             chat\u001B[38;5;241m=\u001B[39mChatPrompt()\n\u001B[0;32m     37\u001B[0m             \u001B[38;5;241m.\u001B[39madd_system(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mYou are a helpful assistant.\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[0;32m     38\u001B[0m             \u001B[38;5;241m.\u001B[39madd_user(prompt),\n\u001B[0;32m     39\u001B[0m             profile\u001B[38;5;241m=\u001B[39mLLMProfile(config\u001B[38;5;241m.\u001B[39mLLM_MODEL)\n\u001B[0;32m     40\u001B[0m         )\u001B[38;5;241m.\u001B[39mcontent\n\u001B[0;32m     41\u001B[0m     \u001B[38;5;28;01mexcept\u001B[39;00m:\n\u001B[1;32m---> 42\u001B[0m         \u001B[43mtime\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43msleep\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconfig\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mGRAZIE_TIMEOUT_SEC\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     44\u001B[0m \u001B[38;5;28;01massert\u001B[39;00m output \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[0;32m     46\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m output\n",
-      "\u001B[1;31mKeyboardInterrupt\u001B[0m: "
-     ]
-    }
-   ],
-   "execution_count": 11
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-05-31T14:00:33.963374Z",
-     "start_time": "2024-05-31T14:00:21.253920Z"
+     "end_time": "2024-05-31T16:15:24.167706Z",
+     "start_time": "2024-05-31T16:15:16.619781Z"
     }
    },
    "cell_type": "code",
@@ -90,43 +90,6 @@
    ],
    "id": "a49cabf576c9d692",
    "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Downloading readme:   0%|          | 0.00/2.41k [00:00<?, ?B/s]"
-      ],
-      "application/vnd.jupyter.widget-view+json": {
-       "version_major": 2,
-       "version_minor": 0,
-       "model_id": "5dc984c015fc4493aedbfb5a70f7b026"
-      }
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Downloading data: 100%|██████████| 163k/163k [00:00<00:00, 474kB/s]\n",
-      "Downloading data: 100%|██████████| 167k/167k [00:00<00:00, 493kB/s]\n",
-      "Downloading data: 100%|██████████| 163k/163k [00:00<00:00, 684kB/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "Generating test split: 0 examples [00:00, ? examples/s]"
-      ],
-      "application/vnd.jupyter.widget-view+json": {
-       "version_major": 2,
-       "version_minor": 0,
-       "model_id": "5f55866359b345d09a67f87888b8ad73"
-      }
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
     {
      "data": {
       "text/plain": [
@@ -198,67 +161,26 @@
        "</div>"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
-   "execution_count": 12
+   "execution_count": 22
   },
   {
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-05-30T13:20:38.052443Z",
-     "start_time": "2024-05-30T13:20:26.913353Z"
-    }
-   },
+   "metadata": {},
    "cell_type": "code",
    "source": "DATA[\"prediction_prod\"] = DATA.progress_apply(lambda row: generate_commit_message_prod(str(row[\"diff\"])), axis=1)",
    "id": "9ded493e087f991d",
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "  1%|          | 1/163 [00:10<29:35, 10.96s/it]\n"
-     ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001B[1;31m---------------------------------------------------------------------------\u001B[0m",
-      "\u001B[1;31mRequestFailedException\u001B[0m                    Traceback (most recent call last)",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\api_wrappers\\grazie_wrapper.py:35\u001B[0m, in \u001B[0;36mllm_request\u001B[1;34m(prompt)\u001B[0m\n\u001B[0;32m     34\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m---> 35\u001B[0m     output \u001B[38;5;241m=\u001B[39m output \u001B[38;5;241m=\u001B[39m \u001B[43mclient\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mchat\u001B[49m\u001B[43m(\u001B[49m\n\u001B[0;32m     36\u001B[0m \u001B[43m        \u001B[49m\u001B[43mchat\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mChatPrompt\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     37\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43madd_system\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mYou are a helpful assistant.\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m)\u001B[49m\n\u001B[0;32m     38\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43madd_user\u001B[49m\u001B[43m(\u001B[49m\u001B[43mprompt\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m     39\u001B[0m \u001B[43m        \u001B[49m\u001B[43mprofile\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mLLMProfile\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconfig\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mLLM_MODEL\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     40\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241m.\u001B[39mcontent\n\u001B[0;32m     41\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m:\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\grazie\\api\\client\\gateway.py:193\u001B[0m, in \u001B[0;36mGrazieApiGatewayClient.chat\u001B[1;34m(self, chat, profile, prompt_id, parameters, headers)\u001B[0m\n\u001B[0;32m    192\u001B[0m chunks: List[ChatResponseStream] \u001B[38;5;241m=\u001B[39m []\n\u001B[1;32m--> 193\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m stream_response \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mchat_stream(chat, profile\u001B[38;5;241m=\u001B[39mprofile, prompt_id\u001B[38;5;241m=\u001B[39mprompt_id, parameters\u001B[38;5;241m=\u001B[39mparameters, headers\u001B[38;5;241m=\u001B[39mheaders):\n\u001B[0;32m    194\u001B[0m     chunks\u001B[38;5;241m.\u001B[39mappend(stream_response)\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\grazie\\api\\client\\gateway.py:254\u001B[0m, in \u001B[0;36mGrazieApiGatewayClient.chat_stream\u001B[1;34m(self, chat, profile, prompt_id, parameters, headers)\u001B[0m\n\u001B[0;32m    246\u001B[0m response \u001B[38;5;241m=\u001B[39m requests\u001B[38;5;241m.\u001B[39mpost(\n\u001B[0;32m    247\u001B[0m     url\u001B[38;5;241m=\u001B[39m\u001B[38;5;124mf\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;132;01m{\u001B[39;00m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_api_gateway_url\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m/\u001B[39m\u001B[38;5;132;01m{\u001B[39;00m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_auth_type\u001B[38;5;241m.\u001B[39mvalue\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m/v5/llm/chat/stream/v6\u001B[39m\u001B[38;5;124m\"\u001B[39m,\n\u001B[0;32m    248\u001B[0m     headers\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_generate_headers(headers),\n\u001B[1;32m   (...)\u001B[0m\n\u001B[0;32m    251\u001B[0m     stream\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mTrue\u001B[39;00m\n\u001B[0;32m    252\u001B[0m )\n\u001B[1;32m--> 254\u001B[0m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_raise_if_error\u001B[49m\u001B[43m(\u001B[49m\u001B[43mresponse\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m    256\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m event \u001B[38;5;129;01min\u001B[39;00m _decode_llm_sse(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parse_sse_response(response\u001B[38;5;241m.\u001B[39miter_lines()), LLMChatEventV6):\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\grazie\\api\\client\\gateway.py:298\u001B[0m, in \u001B[0;36mGrazieApiGatewayClient._raise_if_error\u001B[1;34m(self, response)\u001B[0m\n\u001B[0;32m    297\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m response\u001B[38;5;241m.\u001B[39mstatus_code \u001B[38;5;241m!=\u001B[39m \u001B[38;5;241m200\u001B[39m:\n\u001B[1;32m--> 298\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m RequestFailedException(\u001B[38;5;124mf\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;132;01m{\u001B[39;00mresponse\u001B[38;5;241m.\u001B[39mstatus_code\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m Error: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mresponse\u001B[38;5;241m.\u001B[39mreason\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m. \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mresponse\u001B[38;5;241m.\u001B[39mtext\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m\"\u001B[39m)\n",
-      "\u001B[1;31mRequestFailedException\u001B[0m: 401 Error: Unauthorized. ",
-      "\nDuring handling of the above exception, another exception occurred:\n",
-      "\u001B[1;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
-      "Cell \u001B[1;32mIn[17], line 1\u001B[0m\n\u001B[1;32m----> 1\u001B[0m DATA[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mprediction_prod\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[43mDATA\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mprogress_apply\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43;01mlambda\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[43mrow\u001B[49m\u001B[43m:\u001B[49m\u001B[43m \u001B[49m\u001B[43mgenerate_commit_message_prod\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43mrow\u001B[49m\u001B[43m[\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mdiff\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m]\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43maxis\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;241;43m1\u001B[39;49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\tqdm\\std.py:917\u001B[0m, in \u001B[0;36mtqdm.pandas.<locals>.inner_generator.<locals>.inner\u001B[1;34m(df, func, *args, **kwargs)\u001B[0m\n\u001B[0;32m    914\u001B[0m \u001B[38;5;66;03m# Apply the provided function (in **kwargs)\u001B[39;00m\n\u001B[0;32m    915\u001B[0m \u001B[38;5;66;03m# on the df using our wrapper (which provides bar updating)\u001B[39;00m\n\u001B[0;32m    916\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m--> 917\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mgetattr\u001B[39m(df, df_function)(wrapper, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n\u001B[0;32m    918\u001B[0m \u001B[38;5;28;01mfinally\u001B[39;00m:\n\u001B[0;32m    919\u001B[0m     t\u001B[38;5;241m.\u001B[39mclose()\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\pandas\\core\\frame.py:10361\u001B[0m, in \u001B[0;36mDataFrame.apply\u001B[1;34m(self, func, axis, raw, result_type, args, by_row, engine, engine_kwargs, **kwargs)\u001B[0m\n\u001B[0;32m  10347\u001B[0m \u001B[38;5;28;01mfrom\u001B[39;00m \u001B[38;5;21;01mpandas\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mcore\u001B[39;00m\u001B[38;5;21;01m.\u001B[39;00m\u001B[38;5;21;01mapply\u001B[39;00m \u001B[38;5;28;01mimport\u001B[39;00m frame_apply\n\u001B[0;32m  10349\u001B[0m op \u001B[38;5;241m=\u001B[39m frame_apply(\n\u001B[0;32m  10350\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[0;32m  10351\u001B[0m     func\u001B[38;5;241m=\u001B[39mfunc,\n\u001B[1;32m   (...)\u001B[0m\n\u001B[0;32m  10359\u001B[0m     kwargs\u001B[38;5;241m=\u001B[39mkwargs,\n\u001B[0;32m  10360\u001B[0m )\n\u001B[1;32m> 10361\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mop\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mapply\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241m.\u001B[39m__finalize__(\u001B[38;5;28mself\u001B[39m, method\u001B[38;5;241m=\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mapply\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\pandas\\core\\apply.py:916\u001B[0m, in \u001B[0;36mFrameApply.apply\u001B[1;34m(self)\u001B[0m\n\u001B[0;32m    913\u001B[0m \u001B[38;5;28;01melif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mraw:\n\u001B[0;32m    914\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mapply_raw(engine\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mengine, engine_kwargs\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mengine_kwargs)\n\u001B[1;32m--> 916\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mapply_standard\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\pandas\\core\\apply.py:1063\u001B[0m, in \u001B[0;36mFrameApply.apply_standard\u001B[1;34m(self)\u001B[0m\n\u001B[0;32m   1061\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mapply_standard\u001B[39m(\u001B[38;5;28mself\u001B[39m):\n\u001B[0;32m   1062\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mengine \u001B[38;5;241m==\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mpython\u001B[39m\u001B[38;5;124m\"\u001B[39m:\n\u001B[1;32m-> 1063\u001B[0m         results, res_index \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mapply_series_generator\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m   1064\u001B[0m     \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m   1065\u001B[0m         results, res_index \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mapply_series_numba()\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\pandas\\core\\apply.py:1081\u001B[0m, in \u001B[0;36mFrameApply.apply_series_generator\u001B[1;34m(self)\u001B[0m\n\u001B[0;32m   1078\u001B[0m \u001B[38;5;28;01mwith\u001B[39;00m option_context(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mmode.chained_assignment\u001B[39m\u001B[38;5;124m\"\u001B[39m, \u001B[38;5;28;01mNone\u001B[39;00m):\n\u001B[0;32m   1079\u001B[0m     \u001B[38;5;28;01mfor\u001B[39;00m i, v \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28menumerate\u001B[39m(series_gen):\n\u001B[0;32m   1080\u001B[0m         \u001B[38;5;66;03m# ignore SettingWithCopy here in case the user mutates\u001B[39;00m\n\u001B[1;32m-> 1081\u001B[0m         results[i] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc(v, \u001B[38;5;241m*\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mkwargs)\n\u001B[0;32m   1082\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(results[i], ABCSeries):\n\u001B[0;32m   1083\u001B[0m             \u001B[38;5;66;03m# If we have a view on v, we need to make a copy because\u001B[39;00m\n\u001B[0;32m   1084\u001B[0m             \u001B[38;5;66;03m#  series_generator will swap out the underlying data\u001B[39;00m\n\u001B[0;32m   1085\u001B[0m             results[i] \u001B[38;5;241m=\u001B[39m results[i]\u001B[38;5;241m.\u001B[39mcopy(deep\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mFalse\u001B[39;00m)\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\.venv\\lib\\site-packages\\tqdm\\std.py:912\u001B[0m, in \u001B[0;36mtqdm.pandas.<locals>.inner_generator.<locals>.inner.<locals>.wrapper\u001B[1;34m(*args, **kwargs)\u001B[0m\n\u001B[0;32m    906\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mwrapper\u001B[39m(\u001B[38;5;241m*\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs):\n\u001B[0;32m    907\u001B[0m     \u001B[38;5;66;03m# update tbar correctly\u001B[39;00m\n\u001B[0;32m    908\u001B[0m     \u001B[38;5;66;03m# it seems `pandas apply` calls `func` twice\u001B[39;00m\n\u001B[0;32m    909\u001B[0m     \u001B[38;5;66;03m# on the first column/row to decide whether it can\u001B[39;00m\n\u001B[0;32m    910\u001B[0m     \u001B[38;5;66;03m# take a fast or slow code path; so stop when t.total==t.n\u001B[39;00m\n\u001B[0;32m    911\u001B[0m     t\u001B[38;5;241m.\u001B[39mupdate(n\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m1\u001B[39m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m t\u001B[38;5;241m.\u001B[39mtotal \u001B[38;5;129;01mor\u001B[39;00m t\u001B[38;5;241m.\u001B[39mn \u001B[38;5;241m<\u001B[39m t\u001B[38;5;241m.\u001B[39mtotal \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;241m0\u001B[39m)\n\u001B[1;32m--> 912\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m func(\u001B[38;5;241m*\u001B[39margs, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n",
-      "Cell \u001B[1;32mIn[17], line 1\u001B[0m, in \u001B[0;36m<lambda>\u001B[1;34m(row)\u001B[0m\n\u001B[1;32m----> 1\u001B[0m DATA[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mprediction_prod\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m DATA\u001B[38;5;241m.\u001B[39mprogress_apply(\u001B[38;5;28;01mlambda\u001B[39;00m row: \u001B[43mgenerate_commit_message_prod\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43mrow\u001B[49m\u001B[43m[\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mdiff\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m]\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m, axis\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m1\u001B[39m)\n",
-      "Cell \u001B[1;32mIn[3], line 8\u001B[0m, in \u001B[0;36mgenerate_commit_message_prod\u001B[1;34m(diff)\u001B[0m\n\u001B[0;32m      7\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mgenerate_commit_message_prod\u001B[39m(diff):\n\u001B[1;32m----> 8\u001B[0m \t\u001B[43mgenerate_for_prompt\u001B[49m\u001B[43m(\u001B[49m\u001B[43mprod_prompt\u001B[49m\u001B[43m(\u001B[49m\u001B[43mdiff\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\api_wrappers\\grazie_wrapper.py:57\u001B[0m, in \u001B[0;36mgenerate_for_prompt\u001B[1;34m(prompt)\u001B[0m\n\u001B[0;32m     54\u001B[0m     LLM_CACHE_USED[prompt] \u001B[38;5;241m=\u001B[39m \u001B[38;5;241m0\u001B[39m\n\u001B[0;32m     56\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m LLM_CACHE_USED[prompt] \u001B[38;5;241m>\u001B[39m\u001B[38;5;241m=\u001B[39m \u001B[38;5;28mlen\u001B[39m(LLM_CACHE[prompt]):\n\u001B[1;32m---> 57\u001B[0m     new_response \u001B[38;5;241m=\u001B[39m \u001B[43mllm_request\u001B[49m\u001B[43m(\u001B[49m\u001B[43mprompt\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     58\u001B[0m     LLM_CACHE[prompt]\u001B[38;5;241m.\u001B[39mappend(new_response)\n\u001B[0;32m     60\u001B[0m     \u001B[38;5;28;01mwith\u001B[39;00m \u001B[38;5;28mopen\u001B[39m(LLM_CACHE_FILE, \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mwb\u001B[39m\u001B[38;5;124m\"\u001B[39m) \u001B[38;5;28;01mas\u001B[39;00m file:\n",
-      "File \u001B[1;32mD:\\petrtsv\\work\\jetbrains\\commit-rewriting-processing\\api_wrappers\\grazie_wrapper.py:42\u001B[0m, in \u001B[0;36mllm_request\u001B[1;34m(prompt)\u001B[0m\n\u001B[0;32m     35\u001B[0m         output \u001B[38;5;241m=\u001B[39m output \u001B[38;5;241m=\u001B[39m client\u001B[38;5;241m.\u001B[39mchat(\n\u001B[0;32m     36\u001B[0m             chat\u001B[38;5;241m=\u001B[39mChatPrompt()\n\u001B[0;32m     37\u001B[0m             \u001B[38;5;241m.\u001B[39madd_system(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mYou are a helpful assistant.\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[0;32m     38\u001B[0m             \u001B[38;5;241m.\u001B[39madd_user(prompt),\n\u001B[0;32m     39\u001B[0m             profile\u001B[38;5;241m=\u001B[39mLLMProfile(config\u001B[38;5;241m.\u001B[39mLLM_MODEL)\n\u001B[0;32m     40\u001B[0m         )\u001B[38;5;241m.\u001B[39mcontent\n\u001B[0;32m     41\u001B[0m     \u001B[38;5;28;01mexcept\u001B[39;00m:\n\u001B[1;32m---> 42\u001B[0m         \u001B[43mtime\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43msleep\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconfig\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mGRAZIE_TIMEOUT_SEC\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m     44\u001B[0m \u001B[38;5;28;01massert\u001B[39;00m output \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[0;32m     46\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m output\n",
-      "\u001B[1;31mKeyboardInterrupt\u001B[0m: "
-     ]
-    }
-   ],
-   "execution_count": 17
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-05-31T14:00:33.979797Z",
-     "start_time": "2024-05-31T14:00:33.965373Z"
+     "end_time": "2024-05-31T16:15:24.183660Z",
+     "start_time": "2024-05-31T16:15:24.170584Z"
     }
    },
    "cell_type": "code",
@@ -276,26 +198,26 @@
      ]
     }
    ],
-   "execution_count": 13
+   "execution_count": 23
   },
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": [
     "prod_avg_length = DATA[\"prediction_prod\"].str.len().mean()\n",
     "print(f\"Prod average length: {prod_avg_length}\")"
    ],
-   "id": "ec8b4412410794a4"
+   "id": "ec8b4412410794a4",
+   "outputs": [],
+   "execution_count": null
   },
   {
    "metadata": {},
    "cell_type": "code",
-   "outputs": [],
-   "execution_count": null,
    "source": "print(f\"Length ratio (current / prod): {current_avg_length / prod_avg_length})\")",
-   "id": "10f087784896eca3"
+   "id": "10f087784896eca3",
+   "outputs": [],
+   "execution_count": null
   }
  ],
  "metadata": {