mirror of
https://github.com/microsoft/autogen.git
synced 2025-07-27 19:01:26 +00:00
318 lines
11 KiB
Plaintext
318 lines
11 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"<!--\n",
|
||
|
|
"tags: [\"logging\", \"debugging\"]\n",
|
||
|
|
"description: |\n",
|
||
|
|
" Provide capabilities of runtime logging for debugging and performance analysis.\n",
|
||
|
|
"-->\n",
|
||
|
|
"\n",
|
||
|
|
"# Runtime Logging with AutoGen \n",
|
||
|
|
"\n",
|
||
|
|
"AutoGen offers utilities to log data for debugging and performance analysis. This notebook demonstrates how to use them. \n",
|
||
|
|
"\n",
|
||
|
|
"In general, users can initiate logging by calling `autogen.runtime_logging.start()` and stop logging by calling `autogen.runtime_logging.stop()`"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 9,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Logging session ID: 6e08f3e0-392b-434e-8b69-4ab36c4fcf99\n",
|
||
|
|
"\u001b[33muser_proxy\u001b[0m (to assistant):\n",
|
||
|
|
"\n",
|
||
|
|
"What is the height of the Eiffel Tower? Only respond with the answer and terminate\n",
|
||
|
|
"\n",
|
||
|
|
"--------------------------------------------------------------------------------\n",
|
||
|
|
"\u001b[33massistant\u001b[0m (to user_proxy):\n",
|
||
|
|
"\n",
|
||
|
|
"The height of the Eiffel Tower is approximately 330 meters.\n",
|
||
|
|
"\n",
|
||
|
|
"TERMINATE\n",
|
||
|
|
"\n",
|
||
|
|
"--------------------------------------------------------------------------------\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import json\n",
|
||
|
|
"import autogen\n",
|
||
|
|
"from autogen import AssistantAgent, UserProxyAgent\n",
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"\n",
|
||
|
|
"# Setup API key. Add your own API key to config file or environment variable\n",
|
||
|
|
"llm_config = {\n",
|
||
|
|
" \"config_list\": autogen.config_list_from_json(\n",
|
||
|
|
" env_or_file=\"OAI_CONFIG_LIST\",\n",
|
||
|
|
" ),\n",
|
||
|
|
" \"temperature\": 0.9,\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"# Start logging\n",
|
||
|
|
"logging_session_id = autogen.runtime_logging.start(config={\"dbname\": \"logs.db\"})\n",
|
||
|
|
"print(\"Logging session ID: \" + str(logging_session_id))\n",
|
||
|
|
"\n",
|
||
|
|
"# Create an agent workflow and run it\n",
|
||
|
|
"assistant = AssistantAgent(name=\"assistant\", llm_config=llm_config)\n",
|
||
|
|
"user_proxy = UserProxyAgent(\n",
|
||
|
|
" name=\"user_proxy\",\n",
|
||
|
|
" code_execution_config=False,\n",
|
||
|
|
" human_input_mode=\"NEVER\",\n",
|
||
|
|
" is_termination_msg=lambda msg: \"TERMINATE\" in msg[\"content\"],\n",
|
||
|
|
")\n",
|
||
|
|
"\n",
|
||
|
|
"user_proxy.initiate_chat(\n",
|
||
|
|
" assistant, message=\"What is the height of the Eiffel Tower? Only respond with the answer and terminate\"\n",
|
||
|
|
")\n",
|
||
|
|
"autogen.runtime_logging.stop()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"## Getting Data from the SQLite Database \n",
|
||
|
|
"\n",
|
||
|
|
"`logs.db` should be generated, by default it's using SQLite database. You can view the data with GUI tool like `sqlitebrowser`, using SQLite command line shell or using python script:\n",
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 10,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"def get_log(dbname=\"logs.db\", table=\"chat_completions\"):\n",
|
||
|
|
" import sqlite3\n",
|
||
|
|
"\n",
|
||
|
|
" con = sqlite3.connect(dbname)\n",
|
||
|
|
" query = f\"SELECT * from {table}\"\n",
|
||
|
|
" cursor = con.execute(query)\n",
|
||
|
|
" rows = cursor.fetchall()\n",
|
||
|
|
" column_names = [description[0] for description in cursor.description]\n",
|
||
|
|
" data = [dict(zip(column_names, row)) for row in rows]\n",
|
||
|
|
" con.close()\n",
|
||
|
|
" return data"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 11,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/html": [
|
||
|
|
"<div>\n",
|
||
|
|
"<style scoped>\n",
|
||
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
||
|
|
" vertical-align: middle;\n",
|
||
|
|
" }\n",
|
||
|
|
"\n",
|
||
|
|
" .dataframe tbody tr th {\n",
|
||
|
|
" vertical-align: top;\n",
|
||
|
|
" }\n",
|
||
|
|
"\n",
|
||
|
|
" .dataframe thead th {\n",
|
||
|
|
" text-align: right;\n",
|
||
|
|
" }\n",
|
||
|
|
"</style>\n",
|
||
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
||
|
|
" <thead>\n",
|
||
|
|
" <tr style=\"text-align: right;\">\n",
|
||
|
|
" <th></th>\n",
|
||
|
|
" <th>id</th>\n",
|
||
|
|
" <th>invocation_id</th>\n",
|
||
|
|
" <th>client_id</th>\n",
|
||
|
|
" <th>wrapper_id</th>\n",
|
||
|
|
" <th>session_id</th>\n",
|
||
|
|
" <th>request</th>\n",
|
||
|
|
" <th>response</th>\n",
|
||
|
|
" <th>is_cached</th>\n",
|
||
|
|
" <th>cost</th>\n",
|
||
|
|
" <th>start_time</th>\n",
|
||
|
|
" <th>end_time</th>\n",
|
||
|
|
" <th>total_tokens</th>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" </thead>\n",
|
||
|
|
" <tbody>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>0</th>\n",
|
||
|
|
" <td>1</td>\n",
|
||
|
|
" <td>e8bb00d7-6da5-4407-a949-e19b55d53da8</td>\n",
|
||
|
|
" <td>139819167322784</td>\n",
|
||
|
|
" <td>139823225568704</td>\n",
|
||
|
|
" <td>8821a150-8c78-4d05-a858-8a64f1d18648</td>\n",
|
||
|
|
" <td>You are a helpful AI assistant.\\nSolve tasks u...</td>\n",
|
||
|
|
" <td>The height of the Eiffel Tower is approximatel...</td>\n",
|
||
|
|
" <td>1</td>\n",
|
||
|
|
" <td>0.01572</td>\n",
|
||
|
|
" <td>2024-02-13 15:06:22.082896</td>\n",
|
||
|
|
" <td>2024-02-13 15:06:22.083169</td>\n",
|
||
|
|
" <td>507</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>1</th>\n",
|
||
|
|
" <td>2</td>\n",
|
||
|
|
" <td>c8522790-0067-484b-bb37-d39ae80db98b</td>\n",
|
||
|
|
" <td>139823225568656</td>\n",
|
||
|
|
" <td>139823225563040</td>\n",
|
||
|
|
" <td>fb0ef547-a2ac-428b-8c20-a5e63263b8e1</td>\n",
|
||
|
|
" <td>You are a helpful AI assistant.\\nSolve tasks u...</td>\n",
|
||
|
|
" <td>The height of the Eiffel Tower is approximatel...</td>\n",
|
||
|
|
" <td>1</td>\n",
|
||
|
|
" <td>0.01572</td>\n",
|
||
|
|
" <td>2024-02-13 15:06:23.498758</td>\n",
|
||
|
|
" <td>2024-02-13 15:06:23.499045</td>\n",
|
||
|
|
" <td>507</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>2</th>\n",
|
||
|
|
" <td>3</td>\n",
|
||
|
|
" <td>91c3f6c0-c6f7-4306-89cd-f304c9556de4</td>\n",
|
||
|
|
" <td>139823225449024</td>\n",
|
||
|
|
" <td>139819166072448</td>\n",
|
||
|
|
" <td>6e08f3e0-392b-434e-8b69-4ab36c4fcf99</td>\n",
|
||
|
|
" <td>You are a helpful AI assistant.\\nSolve tasks u...</td>\n",
|
||
|
|
" <td>The height of the Eiffel Tower is approximatel...</td>\n",
|
||
|
|
" <td>1</td>\n",
|
||
|
|
" <td>0.01572</td>\n",
|
||
|
|
" <td>2024-02-13 15:06:24.688990</td>\n",
|
||
|
|
" <td>2024-02-13 15:06:24.689238</td>\n",
|
||
|
|
" <td>507</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" </tbody>\n",
|
||
|
|
"</table>\n",
|
||
|
|
"</div>"
|
||
|
|
],
|
||
|
|
"text/plain": [
|
||
|
|
" id invocation_id client_id wrapper_id \\\n",
|
||
|
|
"0 1 e8bb00d7-6da5-4407-a949-e19b55d53da8 139819167322784 139823225568704 \n",
|
||
|
|
"1 2 c8522790-0067-484b-bb37-d39ae80db98b 139823225568656 139823225563040 \n",
|
||
|
|
"2 3 91c3f6c0-c6f7-4306-89cd-f304c9556de4 139823225449024 139819166072448 \n",
|
||
|
|
"\n",
|
||
|
|
" session_id \\\n",
|
||
|
|
"0 8821a150-8c78-4d05-a858-8a64f1d18648 \n",
|
||
|
|
"1 fb0ef547-a2ac-428b-8c20-a5e63263b8e1 \n",
|
||
|
|
"2 6e08f3e0-392b-434e-8b69-4ab36c4fcf99 \n",
|
||
|
|
"\n",
|
||
|
|
" request \\\n",
|
||
|
|
"0 You are a helpful AI assistant.\\nSolve tasks u... \n",
|
||
|
|
"1 You are a helpful AI assistant.\\nSolve tasks u... \n",
|
||
|
|
"2 You are a helpful AI assistant.\\nSolve tasks u... \n",
|
||
|
|
"\n",
|
||
|
|
" response is_cached cost \\\n",
|
||
|
|
"0 The height of the Eiffel Tower is approximatel... 1 0.01572 \n",
|
||
|
|
"1 The height of the Eiffel Tower is approximatel... 1 0.01572 \n",
|
||
|
|
"2 The height of the Eiffel Tower is approximatel... 1 0.01572 \n",
|
||
|
|
"\n",
|
||
|
|
" start_time end_time total_tokens \n",
|
||
|
|
"0 2024-02-13 15:06:22.082896 2024-02-13 15:06:22.083169 507 \n",
|
||
|
|
"1 2024-02-13 15:06:23.498758 2024-02-13 15:06:23.499045 507 \n",
|
||
|
|
"2 2024-02-13 15:06:24.688990 2024-02-13 15:06:24.689238 507 "
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 11,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"def str_to_dict(s):\n",
|
||
|
|
" return json.loads(s)\n",
|
||
|
|
"\n",
|
||
|
|
"\n",
|
||
|
|
"log_data = get_log()\n",
|
||
|
|
"log_data_df = pd.DataFrame(log_data)\n",
|
||
|
|
"\n",
|
||
|
|
"log_data_df[\"total_tokens\"] = log_data_df.apply(\n",
|
||
|
|
" lambda row: str_to_dict(row[\"response\"])[\"usage\"][\"total_tokens\"], axis=1\n",
|
||
|
|
")\n",
|
||
|
|
"\n",
|
||
|
|
"log_data_df[\"request\"] = log_data_df.apply(lambda row: str_to_dict(row[\"request\"])[\"messages\"][0][\"content\"], axis=1)\n",
|
||
|
|
"\n",
|
||
|
|
"log_data_df[\"response\"] = log_data_df.apply(\n",
|
||
|
|
" lambda row: str_to_dict(row[\"response\"])[\"choices\"][0][\"message\"][\"content\"], axis=1\n",
|
||
|
|
")\n",
|
||
|
|
"\n",
|
||
|
|
"log_data_df"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"## Computing Cost \n",
|
||
|
|
"\n",
|
||
|
|
"One use case of logging data is to compute the cost of a session."
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 12,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Total tokens for all sessions: 1521, total cost: 0.0472\n",
|
||
|
|
"Total tokens for session 6e08f3e0-392b-434e-8b69-4ab36c4fcf99: 507, cost: 0.0157\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# Sum totoal tokens for all sessions\n",
|
||
|
|
"total_tokens = log_data_df[\"total_tokens\"].sum()\n",
|
||
|
|
"\n",
|
||
|
|
"# Sum total cost for all sessions\n",
|
||
|
|
"total_cost = log_data_df[\"cost\"].sum()\n",
|
||
|
|
"\n",
|
||
|
|
"# Total tokens for specific session\n",
|
||
|
|
"session_tokens = log_data_df[log_data_df[\"session_id\"] == logging_session_id][\"total_tokens\"].sum()\n",
|
||
|
|
"session_cost = log_data_df[log_data_df[\"session_id\"] == logging_session_id][\"cost\"].sum()\n",
|
||
|
|
"\n",
|
||
|
|
"print(\"Total tokens for all sessions: \" + str(total_tokens) + \", total cost: \" + str(round(total_cost, 4)))\n",
|
||
|
|
"print(\n",
|
||
|
|
" \"Total tokens for session \"\n",
|
||
|
|
" + str(logging_session_id)\n",
|
||
|
|
" + \": \"\n",
|
||
|
|
" + str(session_tokens)\n",
|
||
|
|
" + \", cost: \"\n",
|
||
|
|
" + str(round(session_cost, 4))\n",
|
||
|
|
")"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "autog",
|
||
|
|
"language": "python",
|
||
|
|
"name": "python3"
|
||
|
|
},
|
||
|
|
"language_info": {
|
||
|
|
"codemirror_mode": {
|
||
|
|
"name": "ipython",
|
||
|
|
"version": 3
|
||
|
|
},
|
||
|
|
"file_extension": ".py",
|
||
|
|
"mimetype": "text/x-python",
|
||
|
|
"name": "python",
|
||
|
|
"nbconvert_exporter": "python",
|
||
|
|
"pygments_lexer": "ipython3",
|
||
|
|
"version": "3.10.13"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 2
|
||
|
|
}
|