Spaces:
Sleeping
Sleeping
Update ai_web_app.py
Browse files- ai_web_app.py +4 -30
ai_web_app.py
CHANGED
@@ -4,12 +4,11 @@ import torch
|
|
4 |
import PyPDF2
|
5 |
from io import BytesIO
|
6 |
|
7 |
-
# Set page configuration
|
8 |
st.set_page_config(
|
9 |
-
page_title="TextSphere",
|
10 |
-
page_icon="π€",
|
11 |
-
layout="wide",
|
12 |
-
initial_sidebar_state="expanded"
|
13 |
)
|
14 |
|
15 |
st.markdown("""
|
@@ -30,29 +29,24 @@ st.markdown("""
|
|
30 |
</div>
|
31 |
""", unsafe_allow_html=True)
|
32 |
|
33 |
-
# Load models from Hugging Face
|
34 |
@st.cache_resource
|
35 |
def load_models():
|
36 |
try:
|
37 |
-
# Load DistilBERT for text classification
|
38 |
text_classification_model = pipeline(
|
39 |
"text-classification",
|
40 |
model="distilbert-base-uncased-finetuned-sst-2-english"
|
41 |
)
|
42 |
|
43 |
-
# Load Question Answering model
|
44 |
question_answering_model = pipeline(
|
45 |
"question-answering",
|
46 |
model="distilbert-base-uncased-distilled-squad"
|
47 |
)
|
48 |
|
49 |
-
# Load Translation model
|
50 |
translation_model = pipeline(
|
51 |
"translation",
|
52 |
model="Helsinki-NLP/opus-mt-en-fr"
|
53 |
)
|
54 |
|
55 |
-
# Load Summarization model
|
56 |
summarization_model = pipeline(
|
57 |
"summarization",
|
58 |
model="facebook/bart-large-cnn"
|
@@ -63,8 +57,6 @@ def load_models():
|
|
63 |
|
64 |
return text_classification_model, question_answering_model, translation_model, summarization_model
|
65 |
|
66 |
-
|
67 |
-
# Function to extract text from a PDF
|
68 |
def extract_text_from_pdf(uploaded_pdf):
|
69 |
try:
|
70 |
pdf_reader = PyPDF2.PdfReader(uploaded_pdf)
|
@@ -78,43 +70,35 @@ def extract_text_from_pdf(uploaded_pdf):
|
|
78 |
return None
|
79 |
|
80 |
|
81 |
-
# Load models
|
82 |
try:
|
83 |
classification_model, qa_model, translation_model, summarization_model = load_models()
|
84 |
except Exception as e:
|
85 |
st.error(f"An error occurred while loading models: {e}")
|
86 |
|
87 |
-
# Sidebar navigation
|
88 |
st.sidebar.title("AI Solutions")
|
89 |
option = st.sidebar.selectbox(
|
90 |
"Choose a task",
|
91 |
["Question Answering", "Text Classification", "Language Translation", "Text Summarization"]
|
92 |
)
|
93 |
|
94 |
-
# Page content based on the selected option
|
95 |
if option == "Question Answering":
|
96 |
st.title("Question Answering")
|
97 |
st.markdown("<h4 style='font-size: 20px;'>- because Google wasn't enough π</h4>", unsafe_allow_html=True)
|
98 |
-
# PDF upload section
|
99 |
uploaded_pdf = st.file_uploader("Upload a PDF file (optional)", type="pdf")
|
100 |
|
101 |
-
# Text input section (when PDF is not uploaded)
|
102 |
context_input = st.text_area("Enter context (a paragraph of text, or leave empty if using PDF):")
|
103 |
question = st.text_input("Enter your question:")
|
104 |
|
105 |
if uploaded_pdf:
|
106 |
-
# Extract text from PDF
|
107 |
context_input = extract_text_from_pdf(uploaded_pdf)
|
108 |
|
109 |
if st.button("Get Answer"):
|
110 |
with st.spinner('Getting answer...'):
|
111 |
try:
|
112 |
if context_input and question:
|
113 |
-
# Use the question answering model to find the answer
|
114 |
answer = qa_model(question=question, context=context_input)
|
115 |
st.write("Answer:", answer['answer'])
|
116 |
|
117 |
-
# Show Streamlit balloons after task completion
|
118 |
st.balloons()
|
119 |
else:
|
120 |
st.error("Please enter both context and a question.")
|
@@ -131,7 +115,6 @@ elif option == "Text Classification":
|
|
131 |
classification = classification_model(text)
|
132 |
st.json(classification)
|
133 |
|
134 |
-
# Show Streamlit balloons after task completion
|
135 |
st.balloons()
|
136 |
except Exception as e:
|
137 |
st.error(f"An error occurred: {e}")
|
@@ -139,10 +122,8 @@ elif option == "Text Classification":
|
|
139 |
elif option == "Language Translation":
|
140 |
st.title("Language Translation (English to Multiple Languages)")
|
141 |
st.markdown("<h4 style='font-size: 20px;'>- when 'translate' is the only button you know π</h4>", unsafe_allow_html=True)
|
142 |
-
# Language options for translation
|
143 |
target_language = st.selectbox("Choose target language", ["French", "Spanish", "German", "Italian", "Portuguese", "Hindi"])
|
144 |
|
145 |
-
# Map of selected language to corresponding Hugging Face translation model
|
146 |
language_models = {
|
147 |
"French": "Helsinki-NLP/opus-mt-en-fr",
|
148 |
"Spanish": "Helsinki-NLP/opus-mt-en-es",
|
@@ -152,7 +133,6 @@ elif option == "Language Translation":
|
|
152 |
"Hindi": "Helsinki-NLP/opus-mt-en-hi"
|
153 |
}
|
154 |
|
155 |
-
# Update translation model based on selected language
|
156 |
selected_model = language_models.get(target_language)
|
157 |
if selected_model:
|
158 |
translation_model = pipeline("translation", model=selected_model)
|
@@ -165,7 +145,6 @@ elif option == "Language Translation":
|
|
165 |
translated_text = translation_model(text_to_translate)
|
166 |
st.write(f"Translated Text ({target_language}):", translated_text[0]['translation_text'])
|
167 |
|
168 |
-
# Show Streamlit balloons after task completion
|
169 |
st.balloons()
|
170 |
else:
|
171 |
st.error("Please enter text to translate.")
|
@@ -175,25 +154,20 @@ elif option == "Language Translation":
|
|
175 |
elif option == "Text Summarization":
|
176 |
st.title("Text Summarization")
|
177 |
st.markdown("<h4 style='font-size: 20px;'>- because who needs to read the whole article, anyway? π₯΅</h4>", unsafe_allow_html=True)
|
178 |
-
# PDF upload section
|
179 |
uploaded_pdf = st.file_uploader("Upload a PDF file (optional)", type="pdf")
|
180 |
|
181 |
-
# Text input section (when PDF is not uploaded)
|
182 |
text_to_summarize = st.text_area("Enter text to summarize (or leave empty if using PDF):")
|
183 |
|
184 |
if uploaded_pdf:
|
185 |
-
# Extract text from PDF
|
186 |
text_to_summarize = extract_text_from_pdf(uploaded_pdf)
|
187 |
|
188 |
if st.button("Summarize"):
|
189 |
with st.spinner('Summarizing text...'):
|
190 |
try:
|
191 |
if text_to_summarize:
|
192 |
-
# Use the summarization model to generate a summary
|
193 |
summary = summarization_model(text_to_summarize, max_length=130, min_length=30, do_sample=False)
|
194 |
st.write("Summary:", summary[0]['summary_text'])
|
195 |
|
196 |
-
# Show Streamlit balloons after task completion
|
197 |
st.balloons()
|
198 |
else:
|
199 |
st.error("Please enter text or upload a PDF for summarization.")
|
|
|
4 |
import PyPDF2
|
5 |
from io import BytesIO
|
6 |
|
|
|
7 |
st.set_page_config(
|
8 |
+
page_title="TextSphere",
|
9 |
+
page_icon="π€",
|
10 |
+
layout="wide",
|
11 |
+
initial_sidebar_state="expanded"
|
12 |
)
|
13 |
|
14 |
st.markdown("""
|
|
|
29 |
</div>
|
30 |
""", unsafe_allow_html=True)
|
31 |
|
|
|
32 |
@st.cache_resource
|
33 |
def load_models():
|
34 |
try:
|
|
|
35 |
text_classification_model = pipeline(
|
36 |
"text-classification",
|
37 |
model="distilbert-base-uncased-finetuned-sst-2-english"
|
38 |
)
|
39 |
|
|
|
40 |
question_answering_model = pipeline(
|
41 |
"question-answering",
|
42 |
model="distilbert-base-uncased-distilled-squad"
|
43 |
)
|
44 |
|
|
|
45 |
translation_model = pipeline(
|
46 |
"translation",
|
47 |
model="Helsinki-NLP/opus-mt-en-fr"
|
48 |
)
|
49 |
|
|
|
50 |
summarization_model = pipeline(
|
51 |
"summarization",
|
52 |
model="facebook/bart-large-cnn"
|
|
|
57 |
|
58 |
return text_classification_model, question_answering_model, translation_model, summarization_model
|
59 |
|
|
|
|
|
60 |
def extract_text_from_pdf(uploaded_pdf):
|
61 |
try:
|
62 |
pdf_reader = PyPDF2.PdfReader(uploaded_pdf)
|
|
|
70 |
return None
|
71 |
|
72 |
|
|
|
73 |
try:
|
74 |
classification_model, qa_model, translation_model, summarization_model = load_models()
|
75 |
except Exception as e:
|
76 |
st.error(f"An error occurred while loading models: {e}")
|
77 |
|
|
|
78 |
st.sidebar.title("AI Solutions")
|
79 |
option = st.sidebar.selectbox(
|
80 |
"Choose a task",
|
81 |
["Question Answering", "Text Classification", "Language Translation", "Text Summarization"]
|
82 |
)
|
83 |
|
|
|
84 |
if option == "Question Answering":
|
85 |
st.title("Question Answering")
|
86 |
st.markdown("<h4 style='font-size: 20px;'>- because Google wasn't enough π</h4>", unsafe_allow_html=True)
|
|
|
87 |
uploaded_pdf = st.file_uploader("Upload a PDF file (optional)", type="pdf")
|
88 |
|
|
|
89 |
context_input = st.text_area("Enter context (a paragraph of text, or leave empty if using PDF):")
|
90 |
question = st.text_input("Enter your question:")
|
91 |
|
92 |
if uploaded_pdf:
|
|
|
93 |
context_input = extract_text_from_pdf(uploaded_pdf)
|
94 |
|
95 |
if st.button("Get Answer"):
|
96 |
with st.spinner('Getting answer...'):
|
97 |
try:
|
98 |
if context_input and question:
|
|
|
99 |
answer = qa_model(question=question, context=context_input)
|
100 |
st.write("Answer:", answer['answer'])
|
101 |
|
|
|
102 |
st.balloons()
|
103 |
else:
|
104 |
st.error("Please enter both context and a question.")
|
|
|
115 |
classification = classification_model(text)
|
116 |
st.json(classification)
|
117 |
|
|
|
118 |
st.balloons()
|
119 |
except Exception as e:
|
120 |
st.error(f"An error occurred: {e}")
|
|
|
122 |
elif option == "Language Translation":
|
123 |
st.title("Language Translation (English to Multiple Languages)")
|
124 |
st.markdown("<h4 style='font-size: 20px;'>- when 'translate' is the only button you know π</h4>", unsafe_allow_html=True)
|
|
|
125 |
target_language = st.selectbox("Choose target language", ["French", "Spanish", "German", "Italian", "Portuguese", "Hindi"])
|
126 |
|
|
|
127 |
language_models = {
|
128 |
"French": "Helsinki-NLP/opus-mt-en-fr",
|
129 |
"Spanish": "Helsinki-NLP/opus-mt-en-es",
|
|
|
133 |
"Hindi": "Helsinki-NLP/opus-mt-en-hi"
|
134 |
}
|
135 |
|
|
|
136 |
selected_model = language_models.get(target_language)
|
137 |
if selected_model:
|
138 |
translation_model = pipeline("translation", model=selected_model)
|
|
|
145 |
translated_text = translation_model(text_to_translate)
|
146 |
st.write(f"Translated Text ({target_language}):", translated_text[0]['translation_text'])
|
147 |
|
|
|
148 |
st.balloons()
|
149 |
else:
|
150 |
st.error("Please enter text to translate.")
|
|
|
154 |
elif option == "Text Summarization":
|
155 |
st.title("Text Summarization")
|
156 |
st.markdown("<h4 style='font-size: 20px;'>- because who needs to read the whole article, anyway? π₯΅</h4>", unsafe_allow_html=True)
|
|
|
157 |
uploaded_pdf = st.file_uploader("Upload a PDF file (optional)", type="pdf")
|
158 |
|
|
|
159 |
text_to_summarize = st.text_area("Enter text to summarize (or leave empty if using PDF):")
|
160 |
|
161 |
if uploaded_pdf:
|
|
|
162 |
text_to_summarize = extract_text_from_pdf(uploaded_pdf)
|
163 |
|
164 |
if st.button("Summarize"):
|
165 |
with st.spinner('Summarizing text...'):
|
166 |
try:
|
167 |
if text_to_summarize:
|
|
|
168 |
summary = summarization_model(text_to_summarize, max_length=130, min_length=30, do_sample=False)
|
169 |
st.write("Summary:", summary[0]['summary_text'])
|
170 |
|
|
|
171 |
st.balloons()
|
172 |
else:
|
173 |
st.error("Please enter text or upload a PDF for summarization.")
|