Update app.py

app.py

@@ -1,7 +1,6 @@
 import streamlit as st
-import sounddevice as sd
+import gradio as gr
 import numpy as np
-import wave
 import whisper
 import os
 import streamlit.components.v1 as components
@@ -32,49 +31,85 @@ st.title("Patent Claims Extraction")
 # API Key Input
 api_key = st.text_input("Enter your OpenAI API Key:", type="password")
 
-# Audio Recording
-record_audio = st.checkbox("Record Audio")
-if record_audio:
-    audio_frames = []
+# Audio Upload
+audio_file = st.file_uploader("Upload an audio file", type=["mp3", "wav", "ogg"])
+audio_data = None
 
-    def audio_callback(indata, frames, time, status):
-        if status:
-            print(status, flush=True)
-        if any(indata):
-            audio_frames.append(indata.copy())
+if audio_file is not None:
+    audio_data = audio_file.read()
 
-    if st.button("Stop Recording"):
-        sd.stop()
+# Moved the submit_button check here
+if 'submit_button' in st.session_state:
+    model = whisper.load_model("base")
 
-    with st.spinner("Recording..."):
-        with sd.InputStream(callback=audio_callback):
-            st.text("Recording audio. Click 'Stop Recording' when finished.")
+    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']
 
-    st.success("Recording stopped")
+            with st.expander("See transcript"):
+                st.markdown(transcript)
 
-    if audio_frames:
-        audio_data = np.concatenate(audio_frames, axis=0)
-        with wave.open("recorded_audio.wav", "wb") as wf:
-            wf.setnchannels(1)
-            wf.setsampwidth(2)
-            wf.setframerate(44100)
-            wf.writeframes(audio_data.tobytes())
+            # Update the user input field with the transcription
+            userinput = st.text_area("Input Text:", transcript)
 
-# Moved the submit_button check here
-if 'submit_button' in st.session_state:
-    model = whisper.load_model("base")
-    audio_data = audio.export().read()
-    audio_bytes_io = io.BytesIO(audio_data)
-
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as audio_file:
-        audio_file.write(audio_bytes_io.read())
-        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']
+# 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)
 
@@ -86,7 +121,7 @@ model_choice = st.selectbox(
 
 # 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!")
+# userinput = st.text_input("Input Text:", "Freeform text here!")  # Commented out, as it's updated above
 
 # Initialize OpenAI API
 if api_key:
@@ -132,4 +167,4 @@ if userinput and api_key and st.button("Extract Claims", key="claims_extraction"
     learning_status_placeholder.text(f"Patentable Claims Extracted!\n{all_extracted_claims.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)
+st.markdown("<sub>This app was created by [Taylor Ennen](https://github.com/taylor-ennen/GPT-Streamlit-MVP)</sub>")