Update app.py

app.py

@@ -110,58 +110,35 @@ 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()}")
-    with st.expander("See transcript"):
-        st.markdown(transcript)
 
-# Model Selection Dropdown
-model_choice = st.selectbox(
-    "Select the model you want to use:",
-    ["gpt-3.5-turbo-0301", "gpt-3.5-turbo-0613", "gpt-3.5-turbo", "gpt-4-0314", "gpt-4-0613", "gpt-4"]
-)
+from transformers import AutoConfig, AutoTokenizer, AutoModel
+from summarizer import Summarizer
 
-# Context, Subject, and Level
-context = "You are a patent claims identifier and extractor. You will freeform text, identify any claims contained therein that may be patentable. You identify, extract, print such claims, briefly explain why each claim is patentable."
-# userinput = st.text_input("Input Text:", "Freeform text here!")  # Commented out, as it's updated above
+# Define the BERT-based model name
+model_name = 'nlpaueb/legal-bert-base-uncased'
 
-# Initialize OpenAI API
-if api_key:
-    openai.api_key = api_key
+# Initialize BERT-based model and tokenizer
+custom_config = AutoConfig.from_pretrained(model_name)
+custom_config.output_hidden_states = True
+custom_tokenizer = AutoTokenizer.from_pretrained(model_name)
+custom_model = AutoModel.from_pretrained(model_name, config=custom_config)
+bert_legal_model = Summarizer(custom_model=custom_model, custom_tokenizer=custom_tokenizer)
+print('Using model {}\n'.format(model_name))
 
-# Learning Objectives
-st.write("### Patentable Claims:")
-# Initialize autogenerated objectives
-claims_extraction = ""
-# Initialize status placeholder
-learning_status_placeholder = st.empty()
-disable_button_bool = False
+# Get the extracted claims from Streamlit's session state
+claims_extracted = st.session_state.claims_extraction
 
-if userinput and api_key and st.button("Extract Claims", key="claims_extraction", disabled=disable_button_bool):
-    # Split the user input into chunks
-    input_chunks = chunk_text(userinput)
+# Define the chunk size
+chunk_size = 350
 
-    # Initialize a variable to store the extracted claims
-    all_extracted_claims = ""
+# Split the extracted claims into chunks
+chunks = [claims_extracted[i:i+chunk_size] for i in range(0, len(claims_extracted), chunk_size)]
 
-    for chunk in input_chunks:
-        # Display status message for the current chunk
-        learning_status_placeholder.text(f"Extracting Patentable Claims for chunk {input_chunks.index(chunk) + 1}...")
-
-        # API call to generate objectives for the current chunk
-        claims_extraction_response = openai.ChatCompletion.create(
-            model=model_choice,
-            messages=[
-                {"role": "user", "content": f"Extract any patentable claims from the following: \n {chunk}. \n Extract each claim. Briefly explain why you extracted this word phrase. Exclude any additional commentary."}
-            ]
-        )
+# Process each chunk with the BERT-based model
+summaries = []
+for chunk in chunks:
+    summary = bert_legal_model(chunk, min_length=8, ratio=0.05)
+    summaries.append(summary)
 
-        # Extract the generated objectives from the API response
-        claims_extraction = claims_extraction_response['choices'][0]['message']['content']
-
-        # Append the extracted claims from the current chunk to the overall results
-        all_extracted_claims += claims_extraction.strip()
-
-    # Save the generated objectives to session state
-    st.session_state.claims_extraction = all_extracted_claims
-
-    # Display generated objectives for all chunks
-    learning_status_placeholder.text(f"Patentable Claims Extracted!\n{all_extracted_claims.strip()}")
+# Now you have a list of summaries for each chunk
+# You can access them using `summaries[0]`, `summaries[1]`, etc.