Skip to content

Replace example test data #101

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
leonidb merged 5 commits into from
Jul 25, 2025
Merged

Replace example test data #101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
384073d
Replace example test data
ErikLagerSB Jul 24, 2025
2fdd46d
Replace example test data in notebooks
ErikLagerSB Jul 24, 2025
e63146d
Fix notebooks and used sample conversatios.
ErikLagerSB Jul 25, 2025
7dcda11
Fix notebooks
ErikLagerSB Jul 25, 2025
26830a0
Removed trailing redundant cell
ErikLagerSB Jul 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1,251 changes: 841 additions & 410 deletions agentune_simulate/examples/data/sample_conversations.csv
View file
Open in desktop

Large diffs are not rendered by default.

89 changes: 41 additions & 48 deletions agentune_simulate/examples/getting_started.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,8 +25,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:19:33.714851Z",
"start_time": "2025-07-23T07:19:30.010353Z"
"end_time": "2025-07-25T08:06:06.794006Z",
"start_time": "2025-07-25T08:06:03.385595Z"
}
},
"cell_type": "code",
Expand Down Expand Up @@ -54,8 +54,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:19:36.118443Z",
"start_time": "2025-07-23T07:19:34.063665Z"
"end_time": "2025-07-25T08:06:08.457844Z",
"start_time": "2025-07-25T08:06:07.389495Z"
}
},
"cell_type": "code",
Expand Down Expand Up @@ -87,8 +87,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:19:36.129148Z",
"start_time": "2025-07-23T07:19:36.126869Z"
"end_time": "2025-07-25T08:06:09.098346Z",
"start_time": "2025-07-25T08:06:09.095374Z"
}
},
"cell_type": "code",
Expand Down Expand Up @@ -118,8 +118,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:19:37.318293Z",
"start_time": "2025-07-23T07:19:37.220430Z"
"end_time": "2025-07-25T08:06:09.680771Z",
"start_time": "2025-07-25T08:06:09.529678Z"
}
},
"cell_type": "code",
Expand All @@ -135,11 +135,11 @@
"output_type": "stream",
"text": [
"Loading conversations from data/sample_conversations.csv...\n",
"✓ Loaded 100 conversations\n",
"✓ Sample conversation has 6 messages\n",
"✓ Loaded 47 conversations\n",
"✓ Sample conversation has 16 messages\n",
"✓ Extracted 2 unique outcomes\n",
" - resolved: Issue was successfully resolved\n",
" - unresolved: Issue was not resolved\n"
" - unresolved: Issue was not resolved\n",
" - resolved: Issue was successfully resolved\n"
]
}
],
Expand All @@ -154,8 +154,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:19:41.743896Z",
"start_time": "2025-07-23T07:19:38.432667Z"
"end_time": "2025-07-25T08:06:15.868901Z",
"start_time": "2025-07-25T08:06:10.106998Z"
}
},
"cell_type": "code",
Expand All @@ -176,7 +176,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"✓ Created vector store with 409 documents\n"
"✓ Created vector store with 840 documents\n"
]
}
],
Expand All @@ -191,8 +191,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:20:30.227359Z",
"start_time": "2025-07-23T07:19:41.753690Z"
"end_time": "2025-07-25T08:08:13.858232Z",
"start_time": "2025-07-25T08:06:15.875031Z"
}
},
"cell_type": "code",
Expand All @@ -202,7 +202,7 @@
" default_chat_model=chat_model,\n",
" outcomes=outcomes,\n",
" vector_store=vector_store,\n",
" max_messages=10\n",
" max_messages=25\n",
").build()\n",
"\n",
"# Run simulation with first 5 conversations as starting points\n",
Expand All @@ -217,16 +217,17 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-07-23 10:19:41,755 - Starting intent extraction on 5 conversations\n",
"2025-07-23 10:19:46,194 - Finished extracting original intents; generated 5 scenarios\n",
"2025-07-23 10:19:46,195 - Starting conversation simulations (self.max_concurrent_conversations=20)\n",
"2025-07-23 10:19:51,197 - Progress: 0/5 scenarios completed\n",
"2025-07-23 10:20:01,199 - Progress: 1/5 scenarios completed\n",
"2025-07-23 10:20:16,202 - Progress: 2/5 scenarios completed\n",
"2025-07-23 10:20:21,204 - Progress: 5/5 scenarios completed\n",
"2025-07-23 10:20:21,206 - Finished simulating conversations; simulated 5 conversations, with 0 failures\n",
"2025-07-23 10:20:21,208 - Starting analysis of simulation results\n",
"2025-07-23 10:20:30,225 - Finished analyzing results\n"
"2025-07-25 11:06:15,876 - Starting intent extraction on 5 conversations\n",
"2025-07-25 11:06:18,934 - Finished extracting original intents; generated 5 scenarios\n",
"2025-07-25 11:06:18,934 - Starting conversation simulations (self.max_concurrent_conversations=20)\n",
"2025-07-25 11:06:23,935 - Progress: 0/5 scenarios completed\n",
"2025-07-25 11:06:48,942 - Progress: 1/5 scenarios completed\n",
"2025-07-25 11:07:23,950 - Progress: 3/5 scenarios completed\n",
"2025-07-25 11:07:38,955 - Progress: 4/5 scenarios completed\n",
"2025-07-25 11:08:03,962 - Progress: 5/5 scenarios completed\n",
"2025-07-25 11:08:03,964 - Finished simulating conversations; simulated 5 conversations, with 0 failures\n",
"2025-07-25 11:08:03,965 - Starting analysis of simulation results\n",
"2025-07-25 11:08:13,856 - Finished analyzing results\n"
]
},
{
Expand All @@ -248,8 +249,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-07-23T07:20:30.241663Z",
"start_time": "2025-07-23T07:20:30.238988Z"
"end_time": "2025-07-25T08:08:13.871712Z",
"start_time": "2025-07-25T08:08:13.869520Z"
}
},
"cell_type": "code",
Expand All @@ -268,21 +269,21 @@
"Simulated conversations: 5\n",
"\n",
"Average messages per conversation:\n",
" Original: 4.4\n",
" Simulated: 5.0\n",
" Original: 16.8\n",
" Simulated: 13.0\n",
"\n",
"Outcome distribution comparison:\n",
"Outcome Original Simulated \n",
"--------------------------------------------------\n",
"resolved 4 (80.0%) 4 (80.0%)\n",
"unresolved 1 (20.0%) 1 (20.0%)\n",
"resolved 1 (20.0%) 2 (40.0%)\n",
"unresolved 4 (80.0%) 3 (60.0%)\n",
"\n",
"Sample conversation (6 messages):\n",
" 1. customer: Last night, I waited in line for 2 hours in the business office, but because I only had a copy of my...\n",
" 2. agent: We're very sorry for the inconvenience and frustration you've experienced. I am from the Guangdong C...\n",
" 3. customer: I've already been through enough hassle with this process. Why can't you resolve the issue directly ...\n",
" 4. agent: I apologize for the inconvenience and understand your frustration. I will escalate your issue intern...\n",
" ... and 2 more messages\n",
"Sample conversation (13 messages):\n",
" 1. agent: Thank you for calling PC Support, how can I help you today?\n",
" 2. customer: My laptop screen is flickering and sometimes goes completely black. I need assistance to get this fi...\n",
" 3. agent: I'm sorry to hear about your screen issues. Let's start by checking the basics. Can you tell me if t...\n",
" 4. customer: The screen flickers both when the laptop is still and when I move it. I haven't made any recent chan...\n",
" ... and 9 more messages\n",
"========================================\n"
]
}
Expand Down Expand Up @@ -312,14 +313,6 @@
" - [Streamlit web interface](https://github.com/SparkBeyond/agentune/blob/main/agentune_simulate/streamlit/README.md)"
],
"id": "6adea4e078c54658"
},
{
"metadata": {},
"cell_type": "code",
"outputs": [],
"execution_count": null,
"source": "",
"id": "76af0307231433b8"
}
],
"metadata": {
Expand Down
Loading