Spaces:
Running
Running
abhishekdeshmukh
commited on
Commit
·
ed81b57
1
Parent(s):
b2c7041
First commit
Browse files- .idea/.gitignore +8 -0
- .idea/inspectionProfiles/profiles_settings.xml +6 -0
- .idea/misc.xml +7 -0
- .idea/modules.xml +8 -0
- .idea/textdetectextension.iml +8 -0
- .idea/vcs.xml +6 -0
- README.md +27 -13
- app.py +62 -0
- requirements.txt +5 -0
.idea/.gitignore
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Default ignored files
|
2 |
+
/shelf/
|
3 |
+
/workspace.xml
|
4 |
+
# Editor-based HTTP Client requests
|
5 |
+
/httpRequests/
|
6 |
+
# Datasource local storage ignored files
|
7 |
+
/dataSources/
|
8 |
+
/dataSources.local.xml
|
.idea/inspectionProfiles/profiles_settings.xml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<component name="InspectionProjectProfileManager">
|
2 |
+
<settings>
|
3 |
+
<option name="USE_PROJECT_PROFILE" value="false" />
|
4 |
+
<version value="1.0" />
|
5 |
+
</settings>
|
6 |
+
</component>
|
.idea/misc.xml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<project version="4">
|
3 |
+
<component name="Black">
|
4 |
+
<option name="sdkName" value="Python 3.8" />
|
5 |
+
</component>
|
6 |
+
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8" project-jdk-type="Python SDK" />
|
7 |
+
</project>
|
.idea/modules.xml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<project version="4">
|
3 |
+
<component name="ProjectModuleManager">
|
4 |
+
<modules>
|
5 |
+
<module fileurl="file://$PROJECT_DIR$/.idea/textdetectextension.iml" filepath="$PROJECT_DIR$/.idea/textdetectextension.iml" />
|
6 |
+
</modules>
|
7 |
+
</component>
|
8 |
+
</project>
|
.idea/textdetectextension.iml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<module type="PYTHON_MODULE" version="4">
|
3 |
+
<component name="NewModuleRootManager">
|
4 |
+
<content url="file://$MODULE_DIR$" />
|
5 |
+
<orderEntry type="jdk" jdkName="Python 3.8" jdkType="Python SDK" />
|
6 |
+
<orderEntry type="sourceFolder" forTests="false" />
|
7 |
+
</component>
|
8 |
+
</module>
|
.idea/vcs.xml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<project version="4">
|
3 |
+
<component name="VcsDirectoryMappings">
|
4 |
+
<mapping directory="" vcs="Git" />
|
5 |
+
</component>
|
6 |
+
</project>
|
README.md
CHANGED
@@ -1,13 +1,27 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# AI Text Detection API
|
2 |
+
|
3 |
+
This API provides endpoints for detecting AI-generated text using the RoBERTa-based model from fakespot-ai.
|
4 |
+
|
5 |
+
## API Endpoints
|
6 |
+
|
7 |
+
- GET `/`: Health check endpoint
|
8 |
+
- POST `/predict`: Predict if text is AI-generated or human-written
|
9 |
+
|
10 |
+
### Sample Usage
|
11 |
+
|
12 |
+
POST `/predict`
|
13 |
+
```json
|
14 |
+
{
|
15 |
+
"text": "Your text to analyze"
|
16 |
+
}
|
17 |
+
```
|
18 |
+
|
19 |
+
Response:
|
20 |
+
```json
|
21 |
+
{
|
22 |
+
"text": "Your text to analyze",
|
23 |
+
"human_probability": 85.5,
|
24 |
+
"ai_probability": 14.5,
|
25 |
+
"prediction": "Human-written"
|
26 |
+
}
|
27 |
+
```
|
app.py
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from fastapi import FastAPI, HTTPException
|
2 |
+
from fastapi.middleware.cors import CORSMiddleware
|
3 |
+
from pydantic import BaseModel
|
4 |
+
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
5 |
+
import torch
|
6 |
+
|
7 |
+
app = FastAPI()
|
8 |
+
|
9 |
+
# Add CORS middleware
|
10 |
+
app.add_middleware(
|
11 |
+
CORSMiddleware,
|
12 |
+
allow_origins=["*"], # For development - you should restrict this in production
|
13 |
+
allow_credentials=True,
|
14 |
+
allow_methods=["*"],
|
15 |
+
allow_headers=["*"],
|
16 |
+
)
|
17 |
+
|
18 |
+
# Load model and tokenizer
|
19 |
+
model_name = "fakespot-ai/roberta-base-ai-text-detection-v1"
|
20 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
21 |
+
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
22 |
+
|
23 |
+
|
24 |
+
class TextRequest(BaseModel):
|
25 |
+
text: str
|
26 |
+
|
27 |
+
|
28 |
+
@app.post("/predict")
|
29 |
+
async def predict(request: TextRequest):
|
30 |
+
try:
|
31 |
+
# Tokenize the input text
|
32 |
+
inputs = tokenizer(request.text, return_tensors="pt", truncation=True, max_length=512)
|
33 |
+
|
34 |
+
# Make prediction
|
35 |
+
with torch.no_grad():
|
36 |
+
outputs = model(**inputs)
|
37 |
+
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
|
38 |
+
|
39 |
+
# Get the probability scores
|
40 |
+
human_prob = predictions[0][0].item()
|
41 |
+
ai_prob = predictions[0][1].item()
|
42 |
+
|
43 |
+
return {
|
44 |
+
"text": request.text,
|
45 |
+
"human_probability": round(human_prob * 100, 2),
|
46 |
+
"ai_probability": round(ai_prob * 100, 2),
|
47 |
+
"prediction": "AI-generated" if ai_prob > human_prob else "Human-written"
|
48 |
+
}
|
49 |
+
|
50 |
+
except Exception as e:
|
51 |
+
raise HTTPException(status_code=500, detail=str(e))
|
52 |
+
|
53 |
+
|
54 |
+
@app.get("/")
|
55 |
+
async def root():
|
56 |
+
return {"message": "AI Text Detection API is running"}
|
57 |
+
|
58 |
+
|
59 |
+
if __name__ == "__main__":
|
60 |
+
import uvicorn
|
61 |
+
|
62 |
+
uvicorn.run(app, host="0.0.0.0", port=7860)
|
requirements.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
transformers
|
2 |
+
torch
|
3 |
+
fastapi
|
4 |
+
uvicorn
|
5 |
+
python-multipart
|