Skip to content

[FEAT]: Winstonai new plagiarized system #266

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

Open
Philrobots wants to merge 3 commits into
base: master
Choose a base branch
from
Open

[FEAT]: Winstonai new plagiarized system #266

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ce628ff
Feat(): Plagiat new system
Sep 11, 2024
76fdca9
Add excluded sources
Sep 20, 2024
f6d7f69
feat(): change winstonai plagiarism url
Jun 18, 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 change: 1 addition & 0 deletions edenai_apis/apis/winstonai/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1,2 @@
WINSTON_AI_API_URL = "https://api.gowinston.ai/functions/v1"
WINSTON_AI_PLAGIA_DETECTION_URL = "https://api.gowinston.ai/v2/plagiarism"
67 changes: 45 additions & 22 deletions edenai_apis/apis/winstonai/winstonai_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
import json
from typing import List, Dict
Copy link

@coderabbitai coderabbitai bot Jun 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue

Remove duplicate Dict import.

The Dict type is imported twice - once on line 2 and again on line 4, causing a redefinition.

Apply this diff to fix the duplicate import:

-from typing import List, Dict
 from http import HTTPStatus
-from typing import Dict, Sequence, Any, Optional
+from typing import List, Dict, Sequence, Any, Optional

Also applies to: 4-4

🤖 Prompt for AI Agents 
In edenai_apis/apis/winstonai/winstonai_api.py around lines 2 to 4, the Dict
type is imported twice, causing a duplicate import issue. Remove the redundant
Dict import from either line 2 or line 4 so that Dict is only imported once,
ensuring no redefinition occurs.

from http import HTTPStatus
from typing import Dict, Sequence, Any, Optional
from uuid import uuid4
import requests
from edenai_apis.apis.winstonai.config import WINSTON_AI_API_URL
from edenai_apis.apis.winstonai.config import WINSTON_AI_API_URL, WINSTON_AI_PLAGIA_DETECTION_URL
from edenai_apis.features import ProviderInterface, TextInterface, ImageInterface
from edenai_apis.features.image.ai_detection.ai_detection_dataclass import (
AiDetectionDataClass as ImageAiDetectionDataclass,
Expand Down Expand Up @@ -34,6 +34,7 @@ def __init__(self, api_keys: Optional[Dict[str, Any]] = None):
api_keys=api_keys or {},
)
self.api_url = WINSTON_AI_API_URL
self.plagia_url = WINSTON_AI_PLAGIA_DETECTION_URL
self.headers = {
"Content-Type": "application/json",
"Authorization": f'Bearer {self.api_settings["api_key"]}',
Expand Down Expand Up @@ -135,40 +136,62 @@ def text__plagia_detection(
{
"text": text,
"language": provider_params.get("language", "en"),
"version": provider_params.get("version", "2.0"),
"country": provider_params.get("country", "us"),
"excluded_sources": provider_params.get("excluded_sources", [])
}
)

response = requests.request(
"POST", f"{self.api_url}/plagiarism", headers=self.headers, data=payload
"POST", self.plagia_url, headers=self.headers, data=payload
)

if response.status_code != 200:
raise ProviderException(response.json(), code=response.status_code)

original_response = response.json()
results = original_response.get("results")
result = original_response.get("result")

if results is None:
if result is None:
raise ProviderException(response.json())

plagiarism_score: int = result.get("score")
sources = result.get("sources")
Copy link
Contributor

@Daggx Daggx Oct 2, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The sources variable should be retrieved from original_response and not result.
sources = original_response.get("sources")


candidates: Sequence[PlagiaDetectionCandidate] = []

for source in sources:
source_url = source.get("url")
source_score = source.get("score")
source_prediction = 'plagiarized' if source_score > 5 else 'not plagiarized'

# startIndex, endIndex, sequence
source_plagiarism_found: List[Dict[str, str]] = source.get("plagiarismFound")

plagiarized_text: str = ""

for plagiarism in source_plagiarism_found:
plagiarism_start_index = int(plagiarism.get("startIndex"))
plagiarism_end_index = int(plagiarism.get("endIndex"))

plagiarized_text += " ... " + text[plagiarism_start_index:plagiarism_end_index] + " ... "

Comment on lines +170 to +177
Copy link

@coderabbitai coderabbitai bot Jun 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🛠️ Refactor suggestion

Optimize plagiarized text construction and add validation.

The current implementation has potential performance issues with string concatenation and lacks validation for array indices.

Apply this diff to improve the implementation:

-            plagiarized_text: str = ""
-
-            for plagiarism in source_plagiarism_found:
-                plagiarism_start_index = int(plagiarism.get("startIndex"))
-                plagiarism_end_index = int(plagiarism.get("endIndex"))
-
-                plagiarized_text += " ... " + text[plagiarism_start_index:plagiarism_end_index] + " ... "
+            plagiarized_segments = []
+            
+            for plagiarism in source_plagiarism_found:
+                start_idx = int(plagiarism.get("startIndex", 0))
+                end_idx = int(plagiarism.get("endIndex", 0))
+                
+                # Validate indices
+                if 0 <= start_idx < end_idx <= len(text):
+                    plagiarized_segments.append(text[start_idx:end_idx])
+            
+            plagiarized_text = " ... ".join(plagiarized_segments)
+            if plagiarized_segments:
+                plagiarized_text = f" ... {plagiarized_text} ... "
📝 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. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change
plagiarized_text: str = ""
for plagiarism in source_plagiarism_found:
plagiarism_start_index = int(plagiarism.get("startIndex"))
plagiarism_end_index = int(plagiarism.get("endIndex"))
plagiarized_text += " ... " + text[plagiarism_start_index:plagiarism_end_index] + " ... "
plagiarized_segments = []
for plagiarism in source_plagiarism_found:
start_idx = int(plagiarism.get("startIndex", 0))
end_idx = int(plagiarism.get("endIndex", 0))
# Validate indices
if 0 <= start_idx < end_idx <= len(text):
plagiarized_segments.append(text[start_idx:end_idx])
plagiarized_text = " ... ".join(plagiarized_segments)
if plagiarized_segments:
plagiarized_text = f" ... {plagiarized_text} ... "
🤖 Prompt for AI Agents 
In edenai_apis/apis/winstonai/winstonai_api.py around lines 170 to 177, the code
concatenates substrings to build plagiarized_text using repeated string
addition, which is inefficient. Also, it does not validate that the start and
end indices are within the bounds of the text. To fix this, replace the string
concatenation with collecting substrings in a list and join them once at the end
for better performance. Additionally, add checks to ensure
plagiarism_start_index and plagiarism_end_index are valid indices within the
text length before slicing to avoid errors.


plagia_detection_candidate = PlagiaDetectionCandidate(
url=source_url,
plagia_score=source_score,
Copy link
Contributor

@Daggx Daggx Oct 2, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The plagia_score should be a value between 0 and 1, we need to divide source_score/100

prediction=source_prediction,
plagiarized_text=plagiarized_text,
plagiarism_founds=source_plagiarism_found
)

candidates.append(plagia_detection_candidate)


plagia_detection_item = PlagiaDetectionItem(text=text, candidates=candidates)

standardized_response = PlagiaDetectionDataClass(
plagia_score=original_response["score"],
items=[
PlagiaDetectionItem(
text=result["title"],
candidates=[
PlagiaDetectionCandidate(
url=result["url"],
plagia_score=1,
prediction="plagiarized",
plagiarized_text=excerpt,
)
for excerpt in result["excerpts"]
],
)
for result in results
],
plagia_score=plagiarism_score,
items=[plagia_detection_item]
)

return ResponseType[PlagiaDetectionDataClass](
Expand Down
Loading