import streamlit as st import gradio as gr import numpy as np import whisper import os import streamlit.components.v1 as components import tempfile import io import requests import json import openai # Define a function to split text into chunks def chunk_text(text, chunk_size=2000): chunks = [] start = 0 while start < len(text): end = start + chunk_size chunk = text[start:end] chunks.append(chunk) start = end return chunks # Streamlit Session State if 'learning_objectives' not in st.session_state: st.session_state.learning_objectives = "" # Streamlit User Input Form st.title("Patent Claims Extraction") # API Key Input api_key = st.text_input("Enter your OpenAI API Key:", type="password") # Audio Upload audio_file = st.file_uploader("Upload an audio file", type=["mp3", "wav", "ogg"]) audio_data = None if audio_file is not None: audio_data = audio_file.read() # Moved the submit_button check here if 'submit_button' in st.session_state: model = whisper.load_model("base") if audio_data: 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'] with st.expander("See transcript"): st.markdown(transcript) # Update the user input field with the transcription userinput = st.text_area("Input Text:", 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"] ) # 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 # Initialize OpenAI API if api_key: openai.api_key = api_key # Learning Objectives st.write("### Patentable Claims:") # Initialize autogenerated objectives claims_extraction = "" # Initialize status placeholder learning_status_placeholder = st.empty() disable_button_bool = False 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) # Initialize a variable to store the extracted claims all_extracted_claims = "" 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."} ] ) # 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()}") 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"] ) # 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 # Initialize OpenAI API if api_key: openai.api_key = api_key # Learning Objectives st.write("### Patentable Claims:") # Initialize autogenerated objectives claims_extraction = "" # Initialize status placeholder learning_status_placeholder = st.empty() disable_button_bool = False 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) # Initialize a variable to store the extracted claims all_extracted_claims = "" 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."} ] ) # 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()}") # Citation st.markdown("This app was created by [Taylor Ennen](https://github.com/taylor-ennen/GPT-Streamlit-MVP)")