Update app.py

app.py

@@ -10,9 +10,10 @@ import requests
 import json
 import openai
 
-# initialize userinput
+# Initialize user input
 userinput = ""
-# Initialize session state
+
+# Initialize session state for claims_extraction
 if 'claims_extraction' not in st.session_state:
     st.session_state.claims_extraction = ""
 
@@ -56,17 +57,17 @@ if st.button('Start Transcription'):
         with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as audio_file:
             audio_file.write(audio_data)
             audio_file_path = audio_file.name
-            st.audio(audio_file_path, format="audio/wav")
-            st.info("Transcribing...")
-            st.success("Transcription complete")
-            result = model.transcribe(audio_file_path)
-            transcript = result['text']
+        st.audio(audio_file_path, format="audio/wav")
+        st.info("Transcribing...")
+        st.success("Transcription complete")
+        result = model.transcribe(audio_file_path)
+        transcript = result['text']
 
-            with st.expander("See transcript"):
-                st.markdown(transcript)
+        with st.expander("See transcript"):
+            st.markdown(transcript)
 
-            # Update the user input field with the transcription
-            userinput = st.text_area("Input Text:", transcript)  # Moved up here
+        # Update the user input field with the transcription
+        userinput = st.text_area("Input Text:", transcript)  # Moved up here
 
 # Model Selection Dropdown
 model_choice = st.selectbox(
@@ -121,6 +122,10 @@ if userinput and api_key and st.button("Extract Claims", key="claims_extraction"
     # Display generated objectives for all chunks
     learning_status_placeholder.text(f"Patentable Claims Extracted!\n{all_extracted_claims.strip()}")
 
+
+# Get the extracted claims from Streamlit's session state
+claims_extracted = st.session_state.claims_extraction
+
 from transformers import AutoConfig, AutoTokenizer, AutoModel
 from summarizer import Summarizer
 
@@ -153,11 +158,9 @@ for chunk in chunks:
     summary = bert_legal_model(chunk, min_length=8, ratio=0.05)
     summaries.append(summary)
 
-    
 # Now you have a list of summaries for each chunk
 # You can access them using `summaries[0]`, `summaries[1]`, etc.
 # After generating summaries
 for i, summary in enumerate(summaries):
     st.write(f"### Summary {i+1}")
     st.write(summary)
-