added intent evaluator #56
Conversation
WalkthroughThe recent updates introduce a new class Changes
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (invoked as PR comments)
Additionally, you can add CodeRabbit Configration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
Review Details
Configuration used: CodeRabbit UI
Review profile: CHILL
Files selected for processing (2)
- athina/evals/llm/intent/evaluator.py (1 hunks)
- athina/evals/llm/intent/prompt.py (1 hunks)
Files skipped from review due to trivial changes (1)
- athina/evals/llm/intent/prompt.py
Additional Context Used
Ruff (4)
athina/evals/llm/intent/evaluator.py (4)
2-2:
typing.Tupleimported but unused
2-2:
typing.Optionalimported but unused
4-4:
athina.interfaces.result.DatapointFieldAnnotationimported but unused
74-74: Local variable
labelis assigned to but never used
Additional comments not posted (7)
athina/evals/llm/intent/evaluator.py (7)
17-19: LGTM!
21-23: LGTM!
25-27: LGTM!
29-31: LGTM!
33-35: LGTM!
37-40: LGTM!
46-47: LGTM!
| def __init__(self, **kwargs): | ||
| self.model_name = "HUGGINGFACE_META_LLAMA_3_70B" | ||
| super().__init__(**kwargs, system_message_template=INTENT_EVAL_PROMPT_CONCISE_SYSTEM, | ||
| user_message_template=INTENT_EVAL_PROMPT_CONCISE_USER,) |
There was a problem hiding this comment.
Make the model name configurable.
- self.model_name = "HUGGINGFACE_META_LLAMA_3_70B"
+ self.model_name = kwargs.get("model_name", "HUGGINGFACE_META_LLAMA_3_70B")Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.
| def __init__(self, **kwargs): | |
| self.model_name = "HUGGINGFACE_META_LLAMA_3_70B" | |
| super().__init__(**kwargs, system_message_template=INTENT_EVAL_PROMPT_CONCISE_SYSTEM, | |
| user_message_template=INTENT_EVAL_PROMPT_CONCISE_USER,) | |
| def __init__(self, **kwargs): | |
| self.model_name = kwargs.get("model_name", "HUGGINGFACE_META_LLAMA_3_70B") | |
| super().__init__(**kwargs, system_message_template=INTENT_EVAL_PROMPT_CONCISE_SYSTEM, | |
| user_message_template=INTENT_EVAL_PROMPT_CONCISE_USER,) |
| @property | ||
| def examples(self): | ||
| pass |
There was a problem hiding this comment.
Mark the examples property as abstract or implement it.
- def examples(self):
- pass
+ @property
+ def examples(self):
+ raise NotImplementedError("Subclasses should implement this method.")Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.
| @property | |
| def examples(self): | |
| pass | |
| @property | |
| def examples(self): | |
| raise NotImplementedError("Subclasses should implement this method.") |
| @@ -0,0 +1,92 @@ | |||
| import time | |||
| from typing import List, Tuple, Optional | |||
There was a problem hiding this comment.
Remove unused imports.
- from typing import List, Tuple, Optional
+ from typing import ListCommittable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.
| from typing import List, Tuple, Optional | |
| from typing import List |
| import time | ||
| from typing import List, Tuple, Optional | ||
|
|
||
| from athina.interfaces.result import EvalResult, EvalResultMetric, DatapointFieldAnnotation |
There was a problem hiding this comment.
Remove unused imports.
- from athina.interfaces.result import EvalResult, EvalResultMetric, DatapointFieldAnnotation
+ from athina.interfaces.result import EvalResult, EvalResultMetricCommittable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.
| from athina.interfaces.result import EvalResult, EvalResultMetric, DatapointFieldAnnotation | |
| from athina.interfaces.result import EvalResult, EvalResultMetric |
| failure = self.is_failure(result) | ||
| passed_value = 1 - float(failure) | ||
| metrics.append(EvalResultMetric(id=MetricType.PASSED.value, value=passed_value)) | ||
| label: str = self.label |
There was a problem hiding this comment.
Remove unused variable label.
- label: str = self.labelCommittable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.
| label: str = self.label |
| malicious_keywords = ["malicious", "illegal", "harm", "harmful", "unlawful", "hurt", "pain", "hate"] | ||
| for keyword in malicious_keywords: | ||
| if keyword.lower() in chat_completion_response_json["result"].lower(): | ||
| self.label = "malicious" | ||
| self.label = "normal" |
There was a problem hiding this comment.
Fix the label assignment logic.
- for keyword in malicious_keywords:
- if keyword.lower() in chat_completion_response_json["result"].lower():
- self.label = "malicious"
- self.label = "normal"
+ self.label = "normal"
+ for keyword in malicious_keywords:
+ if keyword.lower() in chat_completion_response_json["result"].lower():
+ self.label = "malicious"
+ breakCommittable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.
| malicious_keywords = ["malicious", "illegal", "harm", "harmful", "unlawful", "hurt", "pain", "hate"] | |
| for keyword in malicious_keywords: | |
| if keyword.lower() in chat_completion_response_json["result"].lower(): | |
| self.label = "malicious" | |
| self.label = "normal" | |
| malicious_keywords = ["malicious", "illegal", "harm", "harmful", "unlawful", "hurt", "pain", "hate"] | |
| self.label = "normal" | |
| for keyword in malicious_keywords: | |
| if keyword.lower() in chat_completion_response_json["result"].lower(): | |
| self.label = "malicious" | |
| break |
Summary by CodeRabbit
New Features
Improvements
Usability