app.py

import streamlit as st  
import gradio as gr  
import numpy as np      
from audiorecorder import audiorecorder      
import whisper      
import os      
import streamlit.components.v1 as components   
import tempfile      
import io      
import requests    
import json  

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")

# Camera Input
image = st.camera_input("Camera input")

with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tf:
    if image:
        tf.write(image.read())
        temp_image_path = tf.name
    else:
        temp_image_path = None

# Audio Recording
audio = st.audio_recorder("Click to record audio", "Click to stop recording")

submit_button = st.button("Use this audio")

if submit_button:
    model = whisper.load_model("base")
    result = model.transcribe(audio)
    st.info("Transcribing...")
    st.success("Transcription complete")
    transcript = result['text']

    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!")

# 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()}")

# Claims Extraction
if st.button("Extract Claims") and api_key and transcript:
    # You should have 'transcript' available at this point
    # Ensure 'transcript' is defined before this block.

    # Split the user input into chunks
    input_chunks = chunk_text(transcript)  # Use 'transcript' instead of '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()}")

    # Display status message
    lesson_plan = st.text("Extracting Patentable Claims...")

    # Extract and display
    assistant_reply = claims_extraction_response['choices'][0]['message']['content']
    claims_extraction = st.text(assistant_reply.strip())

# Citation
st.markdown("<sub>This app was created by [Taylor Ennen](https://github.com/taylor-ennen/GPT-Streamlit-MVP) & [Tonic](https://huggingface.co/tonic)</sub>", unsafe_allow_html=True)