Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -95,7 +95,7 @@ def main():
|
|
95 |
uploaded_extintl_file_insight = st.file_uploader("Upload a External Reg Intel", type="pdf")
|
96 |
uploaded_interintel_file_insight = st.file_uploader("Upload a Internal Reg Intel", type="pdf")
|
97 |
if uploaded_extintl_file_insight is not None and uploaded_interintel_file_insight is not None:
|
98 |
-
uploaded_file_SOP = st.file_uploader("Upload
|
99 |
if uploaded_file_SOP is not None:
|
100 |
# Extract insight document
|
101 |
with st.spinner("Processing External Reg Intel"):
|
@@ -113,11 +113,11 @@ def main():
|
|
113 |
st.write(f"The PDF contains **{token_count_insight}** tokens.")
|
114 |
|
115 |
|
116 |
-
# Extract
|
117 |
-
with st.spinner("Processing the
|
118 |
text_SOP, page_texts_SOP = extract_text_from_pdf(uploaded_file_SOP)
|
119 |
token_count_SOP, _ = count_tokens_with_tiktoken(text_SOP)
|
120 |
-
st.sidebar.success("
|
121 |
st.write("Token Count")
|
122 |
st.write(f"The PDF contains **{token_count_SOP}** tokens.")
|
123 |
|
@@ -138,12 +138,12 @@ def main():
|
|
138 |
st.write(df_ii_insight_chunks)
|
139 |
|
140 |
|
141 |
-
# Process
|
142 |
-
with st.spinner("Processing the
|
143 |
df_input_SOP = pd.DataFrame([{ "Title": uploaded_file_SOP.name, "Text": text_SOP, "PageTexts": page_texts_SOP }])
|
144 |
df_sop_chunks = split_dataframe_with_combined_text_and_pages(df_input_SOP, 10000, 1000)
|
145 |
-
st.write("Processed
|
146 |
-
st.sidebar.success("Processed
|
147 |
st.write(df_sop_chunks)
|
148 |
|
149 |
# Evaluate Document
|
@@ -186,22 +186,22 @@ def main():
|
|
186 |
return
|
187 |
|
188 |
# Comparing to Insights
|
189 |
-
with st.spinner("Comparing Impact Classified Insights To
|
190 |
df_compare = process_compare(filtered_insights_on_impact, df_sop_chunks, topic)
|
191 |
-
st.subheader("Comparison of Insights to
|
192 |
-
st.sidebar.success("Comparison of External Intel to
|
193 |
st.write(df_compare)
|
194 |
filtered_comparisons_df = df_compare[df_compare['ReviewNeeded'] == True]
|
195 |
if filtered_comparisons_df.empty:
|
196 |
-
st.write("No reviews needed for this
|
197 |
-
st.sidebar.error("No reviews needed for this
|
198 |
return
|
199 |
|
200 |
# Risk scoring
|
201 |
-
with st.spinner("Risk Assessing Insights To
|
202 |
df_risks = risk_score_process(filtered_comparisons_df, topic)
|
203 |
-
st.subheader("Risk Score of Insights to
|
204 |
-
st.sidebar.success("Risk Score of Insights to
|
205 |
st.write(df_risks)
|
206 |
|
207 |
|
|
|
95 |
uploaded_extintl_file_insight = st.file_uploader("Upload a External Reg Intel", type="pdf")
|
96 |
uploaded_interintel_file_insight = st.file_uploader("Upload a Internal Reg Intel", type="pdf")
|
97 |
if uploaded_extintl_file_insight is not None and uploaded_interintel_file_insight is not None:
|
98 |
+
uploaded_file_SOP = st.file_uploader("Upload the draft submission file", type="pdf")
|
99 |
if uploaded_file_SOP is not None:
|
100 |
# Extract insight document
|
101 |
with st.spinner("Processing External Reg Intel"):
|
|
|
113 |
st.write(f"The PDF contains **{token_count_insight}** tokens.")
|
114 |
|
115 |
|
116 |
+
# Extract draft submission document
|
117 |
+
with st.spinner("Processing the draft submission file Text..."):
|
118 |
text_SOP, page_texts_SOP = extract_text_from_pdf(uploaded_file_SOP)
|
119 |
token_count_SOP, _ = count_tokens_with_tiktoken(text_SOP)
|
120 |
+
st.sidebar.success("draft submission file successfully processed")
|
121 |
st.write("Token Count")
|
122 |
st.write(f"The PDF contains **{token_count_SOP}** tokens.")
|
123 |
|
|
|
138 |
st.write(df_ii_insight_chunks)
|
139 |
|
140 |
|
141 |
+
# Process draft submission file into chunks
|
142 |
+
with st.spinner("Processing the draft submission file..."):
|
143 |
df_input_SOP = pd.DataFrame([{ "Title": uploaded_file_SOP.name, "Text": text_SOP, "PageTexts": page_texts_SOP }])
|
144 |
df_sop_chunks = split_dataframe_with_combined_text_and_pages(df_input_SOP, 10000, 1000)
|
145 |
+
st.write("Processed draft submission file")
|
146 |
+
st.sidebar.success("Processed draft submission file")
|
147 |
st.write(df_sop_chunks)
|
148 |
|
149 |
# Evaluate Document
|
|
|
186 |
return
|
187 |
|
188 |
# Comparing to Insights
|
189 |
+
with st.spinner("Comparing Impact Classified Insights To draft submission file"):
|
190 |
df_compare = process_compare(filtered_insights_on_impact, df_sop_chunks, topic)
|
191 |
+
st.subheader("Comparison of Insights to draft submission file's")
|
192 |
+
st.sidebar.success("Comparison of External & Internal Intel to draft submission file's Complete")
|
193 |
st.write(df_compare)
|
194 |
filtered_comparisons_df = df_compare[df_compare['ReviewNeeded'] == True]
|
195 |
if filtered_comparisons_df.empty:
|
196 |
+
st.write("No reviews needed for this draft submission file")
|
197 |
+
st.sidebar.error("No reviews needed for this draft submission file")
|
198 |
return
|
199 |
|
200 |
# Risk scoring
|
201 |
+
with st.spinner("Risk Assessing Insights To draft submission file"):
|
202 |
df_risks = risk_score_process(filtered_comparisons_df, topic)
|
203 |
+
st.subheader("Risk Score of Insights to draft submission file's")
|
204 |
+
st.sidebar.success("Risk Score of Insights to draft submission file's Completed")
|
205 |
st.write(df_risks)
|
206 |
|
207 |
|