mirror of
https://github.com/katanemo/plano.git
synced 2026-06-17 15:25:17 +02:00
add long example
This commit is contained in:
parent
44b16b4903
commit
e218f875d7
1 changed files with 54 additions and 0 deletions
|
|
@ -104,4 +104,58 @@ mod test {
|
|||
println!("{:?}", messages_for_halluncination);
|
||||
assert_eq!(messages_for_halluncination.len(), 3);
|
||||
}
|
||||
#[test]
|
||||
fn test_hallucination_message_long() {
|
||||
let test_str = r#"
|
||||
[
|
||||
{
|
||||
"role": "system",
|
||||
"model" : "gpt-3.5-turbo",
|
||||
"content": "You are a helpful assistant.\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"headcount\", \"description\": \"Get headcount data for a region by staffing type\", \"parameters\": {\"properties\": {\"staffing_type\": {\"type\": \"str\", \"description\": \"The staffing type like contract, fte or agency\"}, \"region\": {\"type\": \"str\", \"description\": \"the geographical region for which you want headcount data.\"}}, \"required\": [\"staffing_type\", \"region\"]}}}\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>"
|
||||
},
|
||||
{ "role": "user", "content": "Hello" },
|
||||
{
|
||||
"role": "assistant",
|
||||
"model": "gpt-3.5-turbo",
|
||||
"content": "Hi there!"
|
||||
},
|
||||
{ "role": "user", "content": "tell me about headcount data" },
|
||||
{
|
||||
"role": "assistant",
|
||||
"model": "Arch-Function-1.5B",
|
||||
"content": "The \"headcount\" tool provides information about the number of employees in a specific region based on the type of staffing used. It requires two parameters: \"staffing_type\" and \"region\". The \"staffing_type\" parameter specifies the type of staffing, such as contract, full-time equivalent (fte), or agency. The \"region\" parameter specifies the geographical region for which you want headcount data."
|
||||
},
|
||||
{ "role": "user", "content": "europe" },
|
||||
{
|
||||
"role": "system",
|
||||
"model": "Arch-Function-1.5B",
|
||||
"content": "It seems like you are asking for headcount data for Europe. Could you please specify the staffing type?"
|
||||
},
|
||||
{ "role": "user", "content": "fte" },
|
||||
{
|
||||
"role": "assistant",
|
||||
"model": "gpt-3.5-turbo",
|
||||
"content": "The headcount is 50000"
|
||||
},
|
||||
{ "role": "user", "content": "tell me about the weather" },
|
||||
{
|
||||
"role": "assistant",
|
||||
"model": "Arch-Function-1.5B",
|
||||
"content" : "The weather forcast tools requires 2 parameters: city and days. Please specify"
|
||||
},
|
||||
{ "role": "user", "content": "Seattle" },
|
||||
{
|
||||
"role": "system",
|
||||
"model": "Arch-Function-1.5B",
|
||||
"content": "It seems like you are asking for weather data for Seattle. Could you please specify the days?"
|
||||
},
|
||||
{ "role": "user", "content": "7 days" }
|
||||
]
|
||||
"#;
|
||||
|
||||
let messages: Vec<Message> = serde_json::from_str(test_str).unwrap();
|
||||
let messages_for_halluncination = extract_messages_for_hallucination(&messages);
|
||||
println!("{:?}", messages_for_halluncination);
|
||||
assert_eq!(messages_for_halluncination.len(), 3);
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue