Update app.py

app.py

@@ -49,6 +49,7 @@ def transcribe_audio(openai_key, file_path, model):
         st.write(response.json())
         response2 = chat_with_model(response.json().get('text'), '')
         st.write('Responses:')
+        #st.write(response)
         st.write(response2)
         return response.json().get('text')
     else:
@@ -66,13 +67,12 @@ def save_and_play_audio(audio_recorder):
         return filename
     return None
 
-def transcribe_and_chat(openai_key, file_path, model):
-    transcription = transcribe_audio(openai_key, file_path, model)
-    if transcription is not None:
-        response = chat_with_model(transcription, '')
-        return transcription, response
-    else:
-        return None, None
+filename = save_and_play_audio(audio_recorder)
+if filename is not None:
+    if st.button("Transcribe"):
+        transcription = transcribe_audio(openai.api_key, filename, "whisper-1")
+        st.write(transcription)
+        chat_with_model(transcription, '') # push transcript through as prompt
 
 def create_file(filename, prompt, response):
     if filename.endswith(".txt"):
@@ -83,39 +83,120 @@ def create_file(filename, prompt, response):
             file.write(f"<h1>Prompt:</h1> <p>{prompt}</p> <h1>Response:</h1> <p>{response}</p>")
     elif filename.endswith(".md"):
         with open(filename, 'w') as file:
-            file.write(f"# Prompt: \n {prompt} \n # Response: \n {response}")
-    elif filename.endswith(".py"):
-        with open(filename, 'w') as file:
-            file.write(f"# Prompt: \n'''{prompt}'''\n # Response: \n'''{response}'''")
+            file.write(f"# Prompt:\n{prompt}\n# Response:\n{response}")
+
+def truncate_document(document, length):
+    return document[:length]
+
+def divide_document(document, max_length):
+    return [document[i:i+max_length] for i in range(0, len(document), max_length)]
+
+def get_table_download_link(file_path):
+    with open(file_path, 'r') as file:
+        data = file.read()
+    b64 = base64.b64encode(data.encode()).decode()  
+    file_name = os.path.basename(file_path)
+    ext = os.path.splitext(file_name)[1]  # get the file extension
+    if ext == '.txt':
+        mime_type = 'text/plain'
+    elif ext == '.htm':
+        mime_type = 'text/html'
+    elif ext == '.md':
+        mime_type = 'text/markdown'
+    else:
+        mime_type = 'application/octet-stream'  # general binary data type
+    href = f'<a href="data:{mime_type};base64,{b64}" target="_blank" download="{file_name}">{file_name}</a>'
+    return href
+
+def CompressXML(xml_text):
+    root = ET.fromstring(xml_text)
+    for elem in list(root.iter()):
+        if isinstance(elem.tag, str) and 'Comment' in elem.tag:
+            elem.parent.remove(elem)
+    return ET.tostring(root, encoding='unicode', method="xml")
+    
+def read_file_content(file,max_length):
+    if file.type == "application/json":
+        content = json.load(file)
+        return str(content)
+    elif file.type == "text/html" or file.type == "text/htm":
+        content = BeautifulSoup(file, "html.parser")
+        return content.text
+    elif file.type == "application/xml" or file.type == "text/xml":
+        tree = ET.parse(file)
+        root = tree.getroot()
+        xml = CompressXML(ET.tostring(root, encoding='unicode'))
+        return xml
+    elif file.type == "text/markdown" or file.type == "text/md":
+        md = mistune.create_markdown()
+        content = md(file.read().decode())
+        return content
+    elif file.type == "text/plain":
+        return file.getvalue().decode()
     else:
-        st.error("Unsupported file type!")
+        return ""
+
 def main():
-    st.sidebar.header("Choose your Input Method:")
-    input_choice = st.sidebar.radio("",('Type it out','Record it'))
-
-    if input_choice == 'Type it out':
-        st.header("Type your query")
-        prompt = st.text_area("Input")
-        document_section = st.text_area("Document Section")
-        if st.button("Get Response"):
-            filename = generate_filename(prompt, choice)
-            response = chat_with_model(prompt, document_section)
-            st.write('Response:')
-            st.write(response)
-            create_file(filename, prompt, response)
-    elif input_choice == 'Record it':
-        st.header("Record your query")
-        st.write("Press record to start recording")
-        recorder_instance = audio_recorder()   # Here is the error
-        filename = save_and_play_audio(recorder_instance)
-        if filename:
-            if st.button("Transcribe and Chat"):
-                transcription, response = transcribe_and_chat(openai.api_key, filename, "whisper-1")
-                if transcription and response:
-                    st.write('Transcription:')
-                    st.write(transcription)
+    user_prompt = st.text_area("Enter prompts, instructions & questions:", '', height=100)
+
+    collength, colupload = st.columns([2,3])  # adjust the ratio as needed
+    with collength:
+        #max_length = 12000 - optimal for gpt35 turbo. 2x=24000 for gpt4.  8x=96000 for gpt4-32k.
+        max_length = st.slider("File section length for large files", min_value=1000, max_value=128000, value=12000, step=1000)
+    with colupload:
+        uploaded_file = st.file_uploader("Add a file for context:", type=["xml", "json", "html", "htm", "md", "txt"])
+    
+    document_sections = deque()
+    document_responses = {}
+
+    if uploaded_file is not None:
+        file_content = read_file_content(uploaded_file, max_length)
+        document_sections.extend(divide_document(file_content, max_length))
+
+    if len(document_sections) > 0:
+        
+        if st.button("👁️ View Upload"):
+            st.markdown("**Sections of the uploaded file:**")
+            for i, section in enumerate(list(document_sections)):
+                st.markdown(f"**Section {i+1}**\n{section}")
+        
+        st.markdown("**Chat with the model:**")
+        for i, section in enumerate(list(document_sections)):
+            if i in document_responses:
+                st.markdown(f"**Section {i+1}**\n{document_responses[i]}")
+            else:
+                if st.button(f"Chat about Section {i+1}"):
+                    st.write('Reasoning with your inputs...')
+                    response = chat_with_model(user_prompt, section)
                     st.write('Response:')
                     st.write(response)
+                    document_responses[i] = response
+                    filename = generate_filename(f"{user_prompt}_section_{i+1}", choice)
+                    create_file(filename, user_prompt, response)
+                    st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
+
+    if st.button('💬 Chat'):
+        st.write('Reasoning with your inputs...')
+        response = chat_with_model(user_prompt, ''.join(list(document_sections)))
+        st.write('Response:')
+        st.write(response)
+        
+        filename = generate_filename(user_prompt, choice)
+        create_file(filename, user_prompt, response)
+        st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
 
+    all_files = glob.glob("*.*")
+    all_files = [file for file in all_files if len(os.path.splitext(file)[0]) >= 20]  # exclude files with short names
+    all_files.sort(key=lambda x: (os.path.splitext(x)[1], x), reverse=True)  # sort by file type and file name in descending order
+    
+    for file in all_files:
+        col1, col3 = st.sidebar.columns([5,1])  # adjust the ratio as needed
+        with col1:
+            st.markdown(get_table_download_link(file), unsafe_allow_html=True)
+        with col3:
+            if st.button("🗑", key="delete_"+file):
+                os.remove(file)
+                st.experimental_rerun()
+            
 if __name__ == "__main__":
-    main()
+    main()