Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import pipeline
|
2 |
+
|
3 |
+
# Step 1: Define the sentiment analysis pipeline.
|
4 |
+
# Here, we use a text classification model.
|
5 |
+
sentiment_pipe = pipeline("text-classification", model="mixedbread-ai/mxbai-rerank-base-v1")
|
6 |
+
|
7 |
+
# Step 2: Define the text generation pipeline with Gemma.
|
8 |
+
gemma_pipe = pipeline("text-generation", model="google/gemma-3-1b-it")
|
9 |
+
|
10 |
+
# Example input text that we want to analyze.
|
11 |
+
text = "I love this new product. It has exceeded my expectations and I feel very happy about it."
|
12 |
+
|
13 |
+
# Perform sentiment analysis on the text.
|
14 |
+
sentiment_result = sentiment_pipe(text)
|
15 |
+
print("Sentiment Analysis Result:")
|
16 |
+
print(sentiment_result)
|
17 |
+
|
18 |
+
# Prepare a prompt that includes the original text and the sentiment result.
|
19 |
+
# The prompt instructs the Gemma model to generate a detailed summary report.
|
20 |
+
prompt = f"""
|
21 |
+
Generate a detailed report based on the following analysis.
|
22 |
+
|
23 |
+
Original text:
|
24 |
+
"{text}"
|
25 |
+
|
26 |
+
Sentiment analysis result:
|
27 |
+
{sentiment_result}
|
28 |
+
|
29 |
+
Please provide a concise summary report explaining the sentiment and key insights.
|
30 |
+
"""
|
31 |
+
|
32 |
+
# Use the Gemma pipeline to generate the summary report.
|
33 |
+
report = gemma_pipe(prompt, max_length=200)
|
34 |
+
print("\nGenerated Report:")
|
35 |
+
print(report[0]['generated_text'])
|