Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -32,18 +32,9 @@ def chunk_text(text, chunk_size=1000):
|
|
| 32 |
|
| 33 |
# Function to classify text as law-related or not using zero-shot classification
|
| 34 |
def classify_text(text):
|
| 35 |
-
# Load the zero-shot classification pipeline
|
| 36 |
classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
|
| 37 |
-
|
| 38 |
-
# Define the candidate labels
|
| 39 |
candidate_labels = ["law-related", "not law-related"]
|
| 40 |
-
|
| 41 |
-
# Run the classifier with the candidate labels
|
| 42 |
result = classifier(text[:512], candidate_labels=candidate_labels)
|
| 43 |
-
|
| 44 |
-
st.write(f"Classification result: {result}")
|
| 45 |
-
|
| 46 |
-
# Check if the highest-scoring label is "law-related"
|
| 47 |
return result['labels'][0] == "law-related"
|
| 48 |
|
| 49 |
# Main area - Display content and perform tasks
|
|
@@ -56,11 +47,12 @@ if uploaded_file is not None:
|
|
| 56 |
|
| 57 |
uploaded_file.seek(0) # Reset file pointer to the beginning
|
| 58 |
text = uploaded_file.read().decode(encoding)
|
| 59 |
-
st.write("File content loaded successfully!") # Debugging: Confirm file loading
|
| 60 |
|
| 61 |
-
# Classify the text
|
| 62 |
if classify_text(text):
|
| 63 |
-
st.write("This document is classified as law-related.")
|
|
|
|
|
|
|
| 64 |
chunks = chunk_text(text, chunk_size=1000)
|
| 65 |
|
| 66 |
if task == "Summarization":
|
|
|
|
| 32 |
|
| 33 |
# Function to classify text as law-related or not using zero-shot classification
|
| 34 |
def classify_text(text):
|
|
|
|
| 35 |
classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
|
|
|
|
|
|
|
| 36 |
candidate_labels = ["law-related", "not law-related"]
|
|
|
|
|
|
|
| 37 |
result = classifier(text[:512], candidate_labels=candidate_labels)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
return result['labels'][0] == "law-related"
|
| 39 |
|
| 40 |
# Main area - Display content and perform tasks
|
|
|
|
| 47 |
|
| 48 |
uploaded_file.seek(0) # Reset file pointer to the beginning
|
| 49 |
text = uploaded_file.read().decode(encoding)
|
|
|
|
| 50 |
|
| 51 |
+
# Classify the text before proceeding with summarization or NER
|
| 52 |
if classify_text(text):
|
| 53 |
+
st.write("This document is classified as law-related.")
|
| 54 |
+
|
| 55 |
+
# Chunk the text if it is too long
|
| 56 |
chunks = chunk_text(text, chunk_size=1000)
|
| 57 |
|
| 58 |
if task == "Summarization":
|