Skip to content

Instantly share code, notes, and snippets.

@louis030195
Created December 29, 2023 00:54
Show Gist options
  • Save louis030195/3a937de928c553a0c6d9be3d92766c55 to your computer and use it in GitHub Desktop.
Save louis030195/3a937de928c553a0c6d9be3d92766c55 to your computer and use it in GitHub Desktop.
[
{
"test_case": "Getting weather information",
"models": [
"mistralai/mistral-7b-instruct",
"mistralai/mixtral-8x7b-instruct",
"openai/gpt-3.5-turbo-1106",
"anthropic/claude-2.1"
],
"steps": [
{
"endpoint": "http://localhost:3000/assistants",
"method": "POST",
"request": {
"instructions": "You are a weather bot. Use the provided functions to answer questions.",
"name": "Weather Bot",
"tools": [
{
"type": "function",
"function": {
"name": "getCurrentWeather",
"description": "Get the weather in location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state e.g. San Francisco, CA"
},
"unit": {
"type": "string"
}
},
"required": [
"location"
]
}
}
}
],
"model": "model_id"
},
"expected_response": {
"id": "<ASSISTANT_ID>",
"name": "Weather Bot",
"model": "<MODEL_ID>",
"instructions": "You are a weather bot. Use the provided functions to answer questions.",
"tools": [
{
"type": "function",
"function": {
"name": "getCurrentWeather",
"description": "Get the weather in location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state e.g. San Francisco, CA"
},
"unit": {
"type": "string"
}
},
"required": [
"location"
]
}
}
}
]
},
"save_response_to_variable": [
{
"name": "id",
"type": "assistant_id"
}
]
},
{
"endpoint": "http://localhost:3000/threads",
"method": "POST",
"request": {},
"expected_response": {
"id": "<THREAD_ID>"
},
"save_response_to_variable": [
{
"name": "id",
"type": "thread_id"
}
]
},
{
"endpoint": "http://localhost:3000/threads/thread_id/messages",
"method": "POST",
"request": {
"role": "user",
"content": "What's the weather in San Francisco?"
},
"expected_response": {
"id": "<MESSAGE_ID>",
"thread_id": "<THREAD_ID>",
"role": "user",
"content": [
{
"type": "text",
"text": {
"value": "What's the weather in San Francisco?",
"annotations": []
}
}
]
},
"save_response_to_variable": [
{
"name": "id",
"type": "message_id"
}
]
},
{
"endpoint": "http://localhost:3000/threads/thread_id/runs",
"method": "POST",
"request": {
"assistant_id": "assistant_id",
"instructions": "Please get the weather."
},
"expected_response": {
"id": "<RUN_ID>",
"thread_id": "<THREAD_ID>",
"assistant_id": "<ASSISTANT_ID>",
"status": "running",
"instructions": "Please get the weather."
},
"save_response_to_variable": [
{
"name": "id",
"type": "run_id"
}
]
},
{
"endpoint": "http://localhost:3000/threads/thread_id/runs",
"method": "GET",
"request": {},
"expected_response": {
"id": "<RUN_ID>",
"thread_id": "<THREAD_ID>",
"assistant_id": "<ASSISTANT_ID>",
"status": "requires_action",
"required_action": {
"type": "submit_tool_outputs",
"submit_tool_outputs": {
"tool_calls": [
{
"id": "<TOOL_CALL_ID>",
"type": "function",
"function": {
"name": "getCurrentWeather",
"arguments": {
"location": "San Francisco"
}
}
}
]
}
},
"last_error": null,
"expires_at": 0,
"started_at": null,
"cancelled_at": null,
"failed_at": null,
"completed_at": null,
"model": "<MODEL_ID>",
"instructions": "Please get the weather.",
"tools": [],
"file_ids": [],
"metadata": {}
},
"save_response_to_variable": [
{
"name": "id",
"type": "run_id"
},
{
"name": "tool_call_id ! TODO > this is wrong",
"type": "tool_call_id"
}
]
},
{
"endpoint": "http://localhost:3000/threads/thread_id/runs/run_id/submit_tool_outputs",
"method": "POST",
"request": {
"tool_outputs": [
{
"tool_call_id": "<TOOL_CALL_ID>",
"output": {
"weather": "It's sunny in San Francisco."
}
}
]
},
"expected_response": {
"id": "<RUN_ID>",
"thread_id": "<THREAD_ID>",
"assistant_id": "<ASSISTANT_ID>",
"status": "running",
"instructions": "Please get the weather.",
"model": "<MODEL_ID>"
},
"save_response_to_variable": [
{
"name": "id",
"type": "run_id"
}
]
}
]
}
]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment