add ndcg@k to evaluate metrics
This commit is contained in:
parent
3a661c5977
commit
04bd107ada
2 changed files with 88 additions and 34 deletions
|
@ -1,5 +1,5 @@
|
|||
{
|
||||
"repo": "https://github.com/AntonOsika/gpt-engineer.git",
|
||||
"repo": "https://github.com/AntonOsika/gpt_engineer.git",
|
||||
"commit": "7735a6445bae3611c62f521e6464c67c957f87c2",
|
||||
"assertions": [
|
||||
{
|
||||
|
@ -12,48 +12,48 @@
|
|||
{
|
||||
"query": "What version of the openai package is active?",
|
||||
"matches": [
|
||||
"pyprojet.toml:14"
|
||||
"pyproject.toml:14"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "Ask user for clarification",
|
||||
"matches": [
|
||||
"gpt-engineer/steps.py:69"
|
||||
"gpt_engineer/steps.py:69"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "generate tests for python code",
|
||||
"matches": [
|
||||
"gpt-engineer/steps.py:153"
|
||||
"gpt_engineer/steps.py:153"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "get item from database based on key",
|
||||
"matches": [
|
||||
"gpt-engineer/db.py:42",
|
||||
"gpt-engineer/db.py:68"
|
||||
"gpt_engineer/db.py:42",
|
||||
"gpt_engineer/db.py:68"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "prompt user to select files",
|
||||
"matches": [
|
||||
"gpt-engineer/file_selector.py:171",
|
||||
"gpt-engineer/file_selector.py:306",
|
||||
"gpt-engineer/file_selector.py:289",
|
||||
"gpt-engineer/file_selector.py:234"
|
||||
"gpt_engineer/file_selector.py:171",
|
||||
"gpt_engineer/file_selector.py:306",
|
||||
"gpt_engineer/file_selector.py:289",
|
||||
"gpt_engineer/file_selector.py:234"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "send to rudderstack",
|
||||
"matches": [
|
||||
"gpt-engineer/collect.py:11",
|
||||
"gpt-engineer/collect.py:38"
|
||||
"gpt_engineer/collect.py:11",
|
||||
"gpt_engineer/collect.py:38"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "parse code blocks from chat messages",
|
||||
"matches": [
|
||||
"gpt-engineer/chat_to_files.py:10",
|
||||
"gpt_engineer/chat_to_files.py:10",
|
||||
"docs/intro/chat_parsing.md:1"
|
||||
]
|
||||
},
|
||||
|
@ -66,35 +66,35 @@
|
|||
{
|
||||
"query": "ask the user if the code ran successfully?",
|
||||
"matches": [
|
||||
"gpt-engineer/learning.py:54"
|
||||
"gpt_engineer/learning.py:54"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "how is consent granted by the user?",
|
||||
"matches": [
|
||||
"gpt-engineer/learning.py:107",
|
||||
"gpt-engineer/learning.py:130",
|
||||
"gpt-engineer/learning.py:152"
|
||||
"gpt_engineer/learning.py:107",
|
||||
"gpt_engineer/learning.py:130",
|
||||
"gpt_engineer/learning.py:152"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "what are all the different steps the agent can take?",
|
||||
"matches": [
|
||||
"docs/intro/steps_module.md:1",
|
||||
"gpt-engineer/steps.py:391"
|
||||
"gpt_engineer/steps.py:391"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "ask the user for clarification?",
|
||||
"matches": [
|
||||
"gpt-engineer/steps.py:69"
|
||||
"gpt_engineer/steps.py:69"
|
||||
]
|
||||
},
|
||||
{
|
||||
"query": "what models are available?",
|
||||
"matches": [
|
||||
"gpt-engineer/ai.py:315",
|
||||
"gpt-engineer/ai.py:341",
|
||||
"gpt_engineer/ai.py:315",
|
||||
"gpt_engineer/ai.py:341",
|
||||
"docs/open-models.md:1"
|
||||
]
|
||||
},
|
||||
|
@ -107,7 +107,7 @@
|
|||
{
|
||||
"query": "does the agent know how to fix code?",
|
||||
"matches": [
|
||||
"gpt-engineer/steps.py:367"
|
||||
"gpt_engineer/steps.py:367"
|
||||
]
|
||||
}
|
||||
]
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue