Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -6,24 +6,22 @@ import re
|
|
| 6 |
model = SentenceTransformer('all-MiniLM-L6-v2')
|
| 7 |
|
| 8 |
def extract_lists(text):
|
| 9 |
-
#
|
| 10 |
-
|
| 11 |
-
matches = re.findall(pattern, text)
|
| 12 |
-
|
| 13 |
-
# Process each match into a list of keywords
|
| 14 |
lists = []
|
| 15 |
-
for
|
| 16 |
-
#
|
| 17 |
-
|
| 18 |
-
if
|
| 19 |
-
|
| 20 |
-
|
|
|
|
|
|
|
| 21 |
return lists
|
| 22 |
|
| 23 |
def compare_embeddings(query, lists_text):
|
| 24 |
# Extract lists from the input text
|
| 25 |
keyword_lists = extract_lists(lists_text)
|
| 26 |
-
|
| 27 |
if not keyword_lists:
|
| 28 |
return "No valid lists found in the input. Please check the format."
|
| 29 |
|
|
@@ -40,7 +38,6 @@ def compare_embeddings(query, lists_text):
|
|
| 40 |
|
| 41 |
# Calculate average similarity for the list
|
| 42 |
avg_similarity = similarities.mean().item()
|
| 43 |
-
|
| 44 |
results.append((i, avg_similarity, keywords))
|
| 45 |
|
| 46 |
# Sort results by similarity score (descending)
|
|
@@ -50,7 +47,7 @@ def compare_embeddings(query, lists_text):
|
|
| 50 |
output = ""
|
| 51 |
for i, score, keywords in results:
|
| 52 |
output += f"List {i}: Similarity score {score:.4f}\n"
|
| 53 |
-
output += f"
|
| 54 |
|
| 55 |
return output
|
| 56 |
|
|
@@ -61,13 +58,13 @@ iface = gr.Interface(
|
|
| 61 |
gr.Textbox(label="Query"),
|
| 62 |
gr.Textbox(
|
| 63 |
label="Lists of keywords",
|
| 64 |
-
placeholder="Enter
|
| 65 |
lines=5
|
| 66 |
),
|
| 67 |
],
|
| 68 |
outputs=gr.Textbox(label="Results"),
|
| 69 |
title="Keyword Lists Comparison App",
|
| 70 |
-
description="Compare a query with multiple lists of keywords and find the most relevant lists. Enter each list
|
| 71 |
)
|
| 72 |
|
| 73 |
# Launch the app
|
|
|
|
| 6 |
model = SentenceTransformer('all-MiniLM-L6-v2')
|
| 7 |
|
| 8 |
def extract_lists(text):
|
| 9 |
+
# Split the input text by newlines and process each line
|
| 10 |
+
lines = text.split('\n')
|
|
|
|
|
|
|
|
|
|
| 11 |
lists = []
|
| 12 |
+
for line in lines:
|
| 13 |
+
# Strip whitespace and check if the line is not empty
|
| 14 |
+
line = line.strip()
|
| 15 |
+
if line:
|
| 16 |
+
# Split the line by spaces and strip any remaining whitespace
|
| 17 |
+
keywords = [item.strip() for item in line.split() if item.strip()]
|
| 18 |
+
if keywords:
|
| 19 |
+
lists.append(keywords)
|
| 20 |
return lists
|
| 21 |
|
| 22 |
def compare_embeddings(query, lists_text):
|
| 23 |
# Extract lists from the input text
|
| 24 |
keyword_lists = extract_lists(lists_text)
|
|
|
|
| 25 |
if not keyword_lists:
|
| 26 |
return "No valid lists found in the input. Please check the format."
|
| 27 |
|
|
|
|
| 38 |
|
| 39 |
# Calculate average similarity for the list
|
| 40 |
avg_similarity = similarities.mean().item()
|
|
|
|
| 41 |
results.append((i, avg_similarity, keywords))
|
| 42 |
|
| 43 |
# Sort results by similarity score (descending)
|
|
|
|
| 47 |
output = ""
|
| 48 |
for i, score, keywords in results:
|
| 49 |
output += f"List {i}: Similarity score {score:.4f}\n"
|
| 50 |
+
output += f" Keywords: {' '.join(keywords)}\n\n"
|
| 51 |
|
| 52 |
return output
|
| 53 |
|
|
|
|
| 58 |
gr.Textbox(label="Query"),
|
| 59 |
gr.Textbox(
|
| 60 |
label="Lists of keywords",
|
| 61 |
+
placeholder="Enter each list of keywords on a new line, with keywords separated by spaces.",
|
| 62 |
lines=5
|
| 63 |
),
|
| 64 |
],
|
| 65 |
outputs=gr.Textbox(label="Results"),
|
| 66 |
title="Keyword Lists Comparison App",
|
| 67 |
+
description="Compare a query with multiple lists of keywords and find the most relevant lists. Enter each list on a new line, with keywords separated by spaces."
|
| 68 |
)
|
| 69 |
|
| 70 |
# Launch the app
|