Upload 13 files

app.py

@@ -0,0 +1,907 @@
+
+import os
+import openai
+
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+os.environ["OPENAI_API_KEY"] 
+
+def save_file(input_file):
+    import shutil
+    import os
+
+    destination_dir = "/home/user/app/file/"
+    os.makedirs(destination_dir, exist_ok=True)
+
+    output_dir="/home/user/app/file/"
+
+    for file in input_file:
+      shutil.copy(file.name, output_dir)
+
+    return "File(s) saved successfully!"
+
+def process_file():
+    from langchain.document_loaders import PyPDFLoader
+    from langchain.document_loaders import DirectoryLoader
+    from langchain.document_loaders import TextLoader
+    from langchain.document_loaders import Docx2txtLoader
+    from langchain.vectorstores import FAISS
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    import openai
+
+    loader1 = DirectoryLoader('/home/user/app/file/', glob="./*.pdf", loader_cls=PyPDFLoader)
+    document1 = loader1.load()
+
+    loader2 = DirectoryLoader('/home/user/app/file/', glob="./*.txt", loader_cls=TextLoader)
+    document2 = loader2.load()
+
+    loader3 = DirectoryLoader('/home/user/app/file/', glob="./*.docx", loader_cls=Docx2txtLoader)
+    document3 = loader3.load()
+
+    document1.extend(document2)
+    document1.extend(document3)
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len)
+
+    docs = text_splitter.split_documents(document1)
+    embeddings = OpenAIEmbeddings()
+
+    file_db = FAISS.from_documents(docs, embeddings)
+    file_db.save_local("/home/user/app/file_db/")
+
+    return "File(s) processed successfully!"
+
+def process_local():
+    from langchain.document_loaders import PyPDFLoader
+    from langchain.document_loaders import DirectoryLoader
+    from langchain.document_loaders import TextLoader
+    from langchain.document_loaders import Docx2txtLoader
+    from langchain.vectorstores import FAISS
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    import openai
+    import os
+
+    destination_dir = "/home/user/app/local_docs/"
+    os.makedirs(destination_dir, exist_ok=True)
+
+    directory_path = '/home/user/app/local_db1/'
+    if os.path.exists(directory_path):
+        os.rmdir(directory_path)
+
+    loader1 = DirectoryLoader('/home/user/app/local_docs/', glob="./*.pdf", loader_cls=PyPDFLoader)
+    document1 = loader1.load()
+
+    loader2 = DirectoryLoader('/home/user/app/local_docs/', glob="./*.txt", loader_cls=TextLoader)
+    document2 = loader2.load()
+
+    loader3 = DirectoryLoader('/home/user/app/local_docs/', glob="./*.docx", loader_cls=Docx2txtLoader)
+    document3 = loader3.load()
+
+    document1.extend(document2)
+    document1.extend(document3)
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len)
+
+    docs = text_splitter.split_documents(document1)
+    embeddings = OpenAIEmbeddings()
+
+    file_db = FAISS.from_documents(docs, embeddings)
+    file_db.save_local("/home/user/app/local_db1/")
+
+    return "File(s) processed successfully!"
+
+def formatted_response(docs, response):
+    formatted_output = response + "\n\nSources"
+
+    for i, doc in enumerate(docs):
+        source_info = doc.metadata.get('source', 'Unknown source')
+        page_info = doc.metadata.get('page', None)
+
+        file_name = source_info.split('/')[-1].strip()
+
+        if page_info is not None:
+            formatted_output += f"\n{file_name}\tpage no {page_info}"
+        else:
+            formatted_output += f"\n{file_name}"
+
+    return formatted_output
+
+def search_file(question):
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.vectorstores import FAISS
+    from langchain.chains.question_answering import load_qa_chain
+    from langchain.callbacks import get_openai_callback
+    from langchain.llms import OpenAI
+    import openai
+    from langchain.chat_models import ChatOpenAI
+
+    embeddings = OpenAIEmbeddings()
+    file_db = FAISS.load_local("/home/user/app/file_db/", embeddings)
+    docs = file_db.similarity_search(question)
+
+    llm = ChatOpenAI(model_name='gpt-3.5-turbo')
+    chain = load_qa_chain(llm, chain_type="stuff")
+
+    with get_openai_callback() as cb:
+        response = chain.run(input_documents=docs, question=question)
+        print(cb)
+
+    return formatted_response(docs, response)
+
+def local_search(question):
+    from langchain.embeddings.openai import OpenAIEmbeddings
+    from langchain.vectorstores import FAISS
+    from langchain.chains.question_answering import load_qa_chain
+    from langchain.callbacks import get_openai_callback
+    from langchain.llms import OpenAI
+    import openai
+    from langchain.chat_models import ChatOpenAI
+
+    embeddings = OpenAIEmbeddings()
+    file_db = FAISS.load_local("/home/user/app/local_db1/", embeddings)
+    docs = file_db.similarity_search(question)
+
+    llm = ChatOpenAI(model_name='gpt-3.5-turbo')
+    chain = load_qa_chain(llm, chain_type="stuff")
+
+    with get_openai_callback() as cb:
+        response = chain.run(input_documents=docs, question=question)
+        print(cb)
+
+    return formatted_response(docs, response)
+
+def delete_file():
+
+    import shutil
+
+    path1 = "/home/user/app/file/"
+    path2 = "/home/user/app/file_db/"
+
+    try:
+        shutil.rmtree(path1)
+        shutil.rmtree(path2)
+        return "Deleted Successfully"
+
+    except:
+        return "Already Deleted"
+
+global soap_file_list
+global sbar_file_list
+
+def soap_refresh():
+    import os
+    import gradio as gr
+    global soap_file_list
+
+    destination_folder = "/home/user/app/soap_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    directory = '/home/user/app/soap_docs/'
+    soap_file_list = []
+
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            soap_file_list.append(file)
+    return gr.CheckboxGroup.update(choices=soap_file_list)
+
+def sbar_refresh():
+    import os
+    import gradio as gr
+    global sbar_file_list
+
+    destination_folder = "/home/user/app/sbar_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    directory = '/home/user/app/sbar_docs/'
+    sbar_file_list = []
+
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            sbar_file_list.append(file)
+    return gr.CheckboxGroup.update(choices=sbar_file_list)
+
+def ask_soap(doc_names, question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+    import openai
+    import docx
+    import os
+
+    destination_folder = "/home/user/app/soap_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    extracted_text = "Extracted text:\n\n\n"
+
+    for doc_name in doc_names:
+        docx_path = "/home/user/app/soap_docs/" + doc_name
+        doc = docx.Document(docx_path)
+
+        for paragraph in doc.paragraphs:
+            extracted_text += paragraph.text + "\n"
+
+        extracted_text += "\nExtracted text:\n\n\n"
+
+    question = (
+        "\n\nUse the suitable 'Extracted text' to answer the following question:\n" + question
+    )
+    extracted_text += question
+
+    if extracted_text:
+        print(extracted_text)
+    else:
+        print("failed")
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(extracted_text)
+
+    return response
+
+def ask_sbar(doc_names, question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+    import openai
+    import docx
+    import os
+
+    destination_folder = "/home/user/app/sbar_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    extracted_text = "Extracted text:\n\n\n"
+
+    for doc_name in doc_names:
+        docx_path = "/home/user/app/sbar_docs/" + doc_name
+        doc = docx.Document(docx_path)
+
+        for paragraph in doc.paragraphs:
+            extracted_text += paragraph.text + "\n"
+
+        extracted_text += "\nExtracted text:\n\n\n"
+
+    question = (
+        "\n\nUse the suitable 'Extracted text' to answer the following question:\n" + question
+    )
+    extracted_text += question
+
+    if extracted_text:
+        print(extracted_text)
+    else:
+        print("failed")
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(extracted_text)
+
+    return response
+
+soap_refresh()
+
+def ask_all_soap(question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+    import openai
+    import docx
+    import os
+    global soap_file_list
+    soap_file_list = soap_file_list
+
+    destination_folder = "/home/user/app/soap_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    extracted_text = "Extracted text:\n\n\n"
+
+    for file in soap_file_list:
+        docx_path = "/home/user/app/soap_docs/" + file
+        doc = docx.Document(docx_path)
+
+        for paragraph in doc.paragraphs:
+            extracted_text += paragraph.text + "\n"
+
+        extracted_text += "\nExtracted text:\n\n\n"
+
+    question = (
+        "\n\nUse the suitable 'Extracted text' to answer the following question:\n" + question
+    )
+    extracted_text += question
+
+    if extracted_text:
+        print(extracted_text)
+    else:
+        print("failed")
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(extracted_text)
+
+    return response
+
+sbar_refresh()
+
+def ask_all_sbar(question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+    import openai
+    import docx
+    import os
+    global sbar_file_list
+    sbar_file_list = sbar_file_list
+
+    destination_folder = "/home/user/app/sbar_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    extracted_text = "Extracted text:\n\n\n"
+
+    for file in sbar_file_list:
+        docx_path = "/home/user/app/sbar_docs/" + file
+        doc = docx.Document(docx_path)
+
+        for paragraph in doc.paragraphs:
+            extracted_text += paragraph.text + "\n"
+
+        extracted_text += "\nExtracted text:\n\n\n"
+
+    question = (
+        "\n\nUse the suitable 'Extracted text' to answer the following question:\n" + question
+    )
+    extracted_text += question
+
+    if extracted_text:
+        print(extracted_text)
+    else:
+        print("failed")
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(extracted_text)
+
+    return response
+
+def search_gpt(question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(question)
+
+    return response
+
+def local_gpt(question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo")
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(question)
+
+    return response
+
+global output
+
+def audio_text(filepath):
+    import openai
+    global output
+
+    audio = open(filepath, "rb")
+    transcript = openai.Audio.transcribe("whisper-1", audio)
+    output = transcript["text"]
+
+    return output
+
+global soap_response
+global sbar_response
+
+def transcript_soap(text):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+
+    global soap_response
+
+    question = (
+        "Use the following context given below to generate a detailed SOAP Report:\n\n"
+    )
+    question += text
+    print(question)
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    word_count = len(text.split())
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    if word_count < 2000:
+        llm = ChatOpenAI(model="gpt-3.5-turbo")
+    elif word_count < 5000:
+        llm = ChatOpenAI(model="gpt-4")
+    else:
+        llm = ChatOpenAI(model="gpt-4-32k")
+
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    soap_response = llm_chain.run(question)
+
+    return soap_response
+
+def transcript_sbar(text):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+
+    global sbar_response
+
+    question = (
+        "Use the following context given below to generate a detailed SBAR Report:\n\n"
+    )
+    question += text
+    print(question)
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    word_count = len(text.split())
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    if word_count < 2000:
+        llm = ChatOpenAI(model="gpt-3.5-turbo")
+    elif word_count < 5000:
+        llm = ChatOpenAI(model="gpt-4")
+    else:
+        llm = ChatOpenAI(model="gpt-4-32k")
+
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    sbar_response = llm_chain.run(question)
+
+    return sbar_response
+
+def text_soap():
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+
+    global output
+    global soap_response
+    output = output
+
+    question = (
+        "Use the following context given below to generate a detailed SOAP Report:\n\n"
+    )
+    question += output
+    print(question)
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    word_count = len(output.split())
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    if word_count < 2000:
+        llm = ChatOpenAI(model="gpt-3.5-turbo")
+    elif word_count < 5000:
+        llm = ChatOpenAI(model="gpt-4")
+    else:
+        llm = ChatOpenAI(model="gpt-4-32k")
+
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    soap_response = llm_chain.run(question)
+
+    return soap_response
+
+def text_sbar():
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    from langchain.chat_models import ChatOpenAI
+
+    global output
+    global sbar_response
+    output = output
+
+    question = (
+        "Use the following context given below to generate a detailed SBAR Report:\n\n"
+    )
+    question += output
+    print(question)
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    word_count = len(output.split())
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+
+    if word_count < 2000:
+        llm = ChatOpenAI(model="gpt-3.5-turbo")
+    elif word_count < 5000:
+        llm = ChatOpenAI(model="gpt-4")
+    else:
+        llm = ChatOpenAI(model="gpt-4-32k")
+
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    sbar_response = llm_chain.run(question)
+
+    return sbar_response
+
+global soap_path
+global sbar_path
+
+def soap_docx(name):
+    global soap_response
+    soap_response = soap_response
+    import docx
+    import os
+    global soap_path
+
+    destination_folder = "/home/user/app/soap_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    soap_path = f"/home/user/app/soap_docs/SOAP_{name}.docx"
+
+    doc = docx.Document()
+    doc.add_paragraph(soap_response)
+    doc.save(soap_path)
+
+    return "Successfully saved SOAP .docx File"
+
+def sbar_docx(name):
+    global sbar_response
+    sbar_response = sbar_response
+    import docx
+    import os
+    global sbar_path
+
+    destination_folder = "/home/user/app/sbar_docs/"
+    if not os.path.exists(destination_folder):
+        os.makedirs(destination_folder)
+
+    sbar_path = f"/home/user/app/sbar_docs/SBAR_{name}.docx"
+
+    doc = docx.Document()
+    doc.add_paragraph(sbar_response)
+    doc.save(sbar_path)
+
+    return "Successfully saved SBAR .docx File"
+
+def download_soap():
+    global soap_path
+    soap_path = soap_path
+
+    return soap_path
+
+def download_sbar():
+    global sbar_path
+    sbar_path = sbar_path
+
+    return sbar_path
+
+import gradio as gr
+
+css = """
+.col{
+    max-width: 50%;
+    margin: 0 auto;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+}
+"""
+
+theme = gr.Theme.from_hub("shivi/calm_seafoam")
+
+with gr.Blocks(theme=theme, css=css) as demo:
+    gr.Markdown("## <center>Medical App</center>")
+
+    with gr.Tab("Create SOAP and SBAR Reports"):
+      with gr.Column(elem_classes="col"):
+
+        with gr.Tab("From Recorded Audio"):
+          with gr.Column():
+
+            mic_audio_input = gr.Audio(source="microphone", type="filepath", label="Speak to the Microphone")
+            mic_audio_button = gr.Button("Generate Transcript")
+            mic_audio_output = gr.Textbox(label="Transcription")
+
+            gr.ClearButton([mic_audio_input, mic_audio_output])
+
+            with gr.Tab("SOAP Report"):
+              with gr.Column():
+
+                mic_text_soap_button = gr.Button("Generate SOAP Report")
+                mic_text_soap_output = gr.Textbox(label="SOAP Report")
+
+                mic_soap_docx_input = gr.Textbox(label="Enter the name of SOAP .docx File")
+                mic_soap_docx_button = gr.Button("Save SOAP Document")
+                mic_soap_docx_output = gr.Textbox(label="File save status")
+
+                mic_soap_download_button = gr.Button("Download SOAP .docx File")
+                mic_soap_download_output = gr.Files(label="Download Link")
+
+                gr.ClearButton([mic_text_soap_output, mic_soap_docx_input, mic_soap_docx_output, mic_soap_download_output])
+
+            with gr.Tab("SBAR Report"):
+              with gr.Column():
+
+                mic_text_sbar_button = gr.Button("Generate SBAR Report")
+                mic_text_sbar_output = gr.Textbox(label="SBAR Report")
+
+                mic_sbar_docx_input = gr.Textbox(label="Enter the name of SBAR .docx File")
+                mic_sbar_docx_button = gr.Button("Save SBAR Document")
+                mic_sbar_docx_output = gr.Textbox(label="File save status")
+
+                mic_sbar_download_button = gr.Button("Download SBAR .docx File")
+                mic_sbar_download_output = gr.Files(label="Download Link")
+
+                gr.ClearButton([mic_text_sbar_output, mic_sbar_docx_input, mic_sbar_docx_output, mic_sbar_download_output])
+
+        with gr.Tab("From Uploaded Audio"):
+          with gr.Column():
+
+            upload_audio_input = gr.Audio(source="upload", type="filepath", label="Upload Audio File here")
+            upload_audio_button = gr.Button("Generate Transcript")
+            upload_audio_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([upload_audio_input, upload_audio_output])
+
+            with gr.Tab("SOAP Report"):
+              with gr.Column():
+
+                upload_text_soap_button = gr.Button("Generate SOAP Report")
+                upload_text_soap_output = gr.Textbox(label="SOAP Report")
+
+                upload_soap_docx_input = gr.Textbox(label="Enter the name of SOAP .docx File")
+                upload_soap_docx_button = gr.Button("Save SOAP Document")
+                upload_soap_docx_output = gr.Textbox(label="File save status")
+
+                upload_soap_download_button = gr.Button("Download SOAP .docx File")
+                upload_soap_download_output = gr.Files(label="Download Link")
+
+                gr.ClearButton([upload_text_soap_output, upload_soap_docx_input, upload_soap_docx_output, upload_soap_download_output])
+
+            with gr.Tab("SBAR Report"):
+              with gr.Column():
+
+                upload_text_sbar_button = gr.Button("Generate SBAR Report")
+                upload_text_sbar_output = gr.Textbox(label="SBAR Report")
+
+                upload_sbar_docx_input = gr.Textbox(label="Enter the name of SBAR .docx File")
+                upload_sbar_docx_button = gr.Button("Save SBAR Document")
+                upload_sbar_docx_output = gr.Textbox(label="File save status")
+
+                upload_sbar_download_button = gr.Button("Download SBAR .docx File")
+                upload_sbar_download_output = gr.Files(label="Download Link")
+
+                gr.ClearButton([upload_text_sbar_output, upload_sbar_docx_input, upload_sbar_docx_output, upload_sbar_download_output])
+
+        with gr.Tab("From Text Transcript"):
+          with gr.Column():
+
+            text_transcript_input = gr.Textbox(label="Enter your Transcript here")
+
+            gr.ClearButton([text_transcript_input])
+
+            with gr.Tab("SOAP Report"):
+              with gr.Column():
+
+                text_text_soap_button = gr.Button("Generate SOAP Report")
+                text_text_soap_output = gr.Textbox(label="SOAP Report")
+
+                text_soap_docx_input = gr.Textbox(label="Enter the name of SOAP .docx File")
+                text_soap_docx_button = gr.Button("Save SOAP Document")
+                text_soap_docx_output = gr.Textbox(label="File save status")
+
+                text_soap_download_button = gr.Button("Download SOAP .docx File")
+                text_soap_download_output = gr.Files(label="Download Link")
+
+                gr.ClearButton([text_text_soap_output, text_soap_docx_input, text_soap_docx_output, text_soap_download_output])
+
+            with gr.Tab("SBAR Report"):
+              with gr.Column():
+
+                text_text_sbar_button = gr.Button("Generate SBAR Report")
+                text_text_sbar_output = gr.Textbox(label="SBAR Report")
+
+                text_sbar_docx_input = gr.Textbox(label="Enter the name of SBAR .docx File")
+                text_sbar_docx_button = gr.Button("Save SBAR Document")
+                text_sbar_docx_output = gr.Textbox(label="File save status")
+
+                text_sbar_download_button = gr.Button("Download SBAR .docx File")
+                text_sbar_download_output = gr.Files(label="Download Link")
+
+                gr.ClearButton([text_text_sbar_output, text_sbar_docx_input, text_sbar_docx_output, text_sbar_download_output])
+
+    with gr.Tab("Query SOAP and SBAR Reports"):
+      with gr.Column(elem_classes="col"):
+
+        with gr.Tab("Query SOAP Reports"):
+          with gr.Column():
+
+            soap_refresh_button = gr.Button("Refresh")
+            ask_soap_input = gr.CheckboxGroup(label="Choose File(s)")
+
+            ask_soap_question = gr.Textbox(label="Enter Question here")
+            ask_soap_button = gr.Button("Submit")
+            ask_soap_output = gr.Textbox(label="Output")
+
+            ask_all_soap_button = gr.Button("Ask all SOAP Reports")
+            ask_all_soap_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([ask_soap_input, ask_soap_question, ask_soap_output, ask_all_soap_output])
+
+        with gr.Tab("Query SBAR Reports"):
+          with gr.Column():
+
+            sbar_refresh_button = gr.Button("Refresh")
+            ask_sbar_input = gr.CheckboxGroup(label="Choose File(s)")
+
+            ask_sbar_question = gr.Textbox(label="Enter Question here")
+            ask_sbar_button = gr.Button("Submit")
+            ask_sbar_output = gr.Textbox(label="Output")
+
+            ask_all_sbar_button = gr.Button("Ask all SBAR Reports")
+            ask_all_sbar_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([ask_sbar_input, ask_sbar_question, ask_sbar_output, ask_all_sbar_output])
+
+    with gr.Tab("Query your Documents"):
+      with gr.Column(elem_classes="col"):
+
+        with gr.Tab("Upload and Process Documents"):
+          with gr.Column():
+
+            file_upload_input = gr.Files(label="Upload File(s) here")
+            file_upload_button = gr.Button("Upload")
+            file_upload_output = gr.Textbox(label="Output")
+
+            file_process_button = gr.Button("Process")
+            file_process_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([file_upload_input, file_upload_output, file_process_output])
+
+        with gr.Tab("Query Documents"):
+          with gr.Column():
+
+            file_search_input = gr.Textbox(label="Enter Question here")
+            file_search_button = gr.Button("Search")
+            file_search_output = gr.Textbox(label="Output")
+
+            search_gpt_button = gr.Button("Ask ChatGPT")
+            search_gpt_output = gr.Textbox(label="Output")
+
+            file_delete_button = gr.Button("Delete")
+            file_delete_output = gr.Textbox(label="Output")
+
+            gr.ClearButton([file_search_input, file_search_output, search_gpt_output, file_delete_output])
+
+    with gr.Tab("Query all Local Documents"):
+      with gr.Column(elem_classes="col"):
+
+        local_process_button = gr.Button("Process")
+        local_process_output = gr.Textbox(label="Output")
+
+        local_search_input = gr.Textbox(label="Enter Question here")
+        local_search_button = gr.Button("Search")
+        local_search_output = gr.Textbox(label="Output")
+
+        local_gpt_button = gr.Button("Ask ChatGPT")
+        local_gpt_output = gr.Textbox(label="Output")
+
+        gr.ClearButton([local_process_output, local_search_input, local_search_output, local_gpt_output])
+
+    #########################################################################################################
+    file_upload_button.click(save_file, inputs=file_upload_input, outputs=file_upload_output)
+    file_process_button.click(process_file, inputs=None, outputs=file_process_output)
+
+    file_search_button.click(search_file, inputs=file_search_input, outputs=file_search_output)
+    search_gpt_button.click(search_gpt, inputs=file_search_input, outputs=search_gpt_output)
+
+    file_delete_button.click(delete_file, inputs=None, outputs=file_delete_output)
+
+    #########################################################################################################
+    local_process_button.click(process_local, inputs=None, outputs=local_process_output)
+    local_search_button.click(local_search, inputs=local_search_input, outputs=local_search_output)
+    local_gpt_button.click(local_gpt, inputs=local_search_input, outputs=local_gpt_output)
+
+    ########################################################################################################
+    soap_refresh_button.click(soap_refresh, inputs=None, outputs=ask_soap_input)
+    ask_soap_button.click(ask_soap, inputs=[ask_soap_input, ask_soap_question], outputs=ask_soap_output)
+
+    sbar_refresh_button.click(sbar_refresh, inputs=None, outputs=ask_sbar_input)
+    ask_sbar_button.click(ask_sbar, inputs=[ask_sbar_input, ask_sbar_question], outputs=ask_sbar_output)
+
+    ask_all_soap_button.click(ask_all_soap, inputs=ask_soap_question, outputs=ask_all_soap_output)
+    ask_all_sbar_button.click(ask_all_sbar, inputs=ask_sbar_question, outputs=ask_all_sbar_output)
+
+    ########################################################################################################
+    mic_audio_button.click(audio_text, inputs=mic_audio_input, outputs=mic_audio_output)
+
+    mic_text_soap_button.click(text_soap, inputs=None, outputs=mic_text_soap_output)
+    mic_text_sbar_button.click(text_sbar, inputs=None, outputs=mic_text_sbar_output)
+
+    mic_soap_docx_button.click(soap_docx, inputs=mic_soap_docx_input, outputs=mic_soap_docx_output)
+    mic_sbar_docx_button.click(sbar_docx, inputs=mic_sbar_docx_input, outputs=mic_sbar_docx_output)
+
+    mic_soap_download_button.click(download_soap, inputs=None, outputs=mic_soap_download_output)
+    mic_sbar_download_button.click(download_sbar, inputs=None, outputs=mic_sbar_download_output)
+    ##########################################################################################################
+    upload_audio_button.click(audio_text, inputs=upload_audio_input, outputs=upload_audio_output)
+
+    upload_text_soap_button.click(text_soap, inputs=None, outputs=upload_text_soap_output)
+    upload_text_sbar_button.click(text_sbar, inputs=None, outputs=upload_text_sbar_output)
+
+    upload_soap_docx_button.click(soap_docx, inputs=upload_soap_docx_input, outputs=upload_soap_docx_output)
+    upload_sbar_docx_button.click(sbar_docx, inputs=upload_sbar_docx_input, outputs=upload_sbar_docx_output)
+
+    upload_soap_download_button.click(download_soap, inputs=None, outputs=upload_soap_download_output)
+    upload_sbar_download_button.click(download_sbar, inputs=None, outputs=upload_sbar_download_output)
+    ############################################################################################################
+    text_text_soap_button.click(transcript_soap, inputs=text_transcript_input, outputs=text_text_soap_output)
+    text_text_sbar_button.click(transcript_sbar, inputs=text_transcript_input, outputs=text_text_sbar_output)
+
+    text_soap_docx_button.click(soap_docx, inputs=text_soap_docx_input, outputs=text_soap_docx_output)
+    text_sbar_docx_button.click(sbar_docx, inputs=text_sbar_docx_input, outputs=text_sbar_docx_output)
+
+    text_soap_download_button.click(download_soap, inputs=None, outputs=text_soap_download_output)
+    text_sbar_download_button.click(download_sbar, inputs=None, outputs=text_sbar_download_output)
+    #############################################################################################################
+
+
+demo.queue()
+demo.launch()

local_db/test01.txt

@@ -0,0 +1 @@
+test file 

requirements.txt

@@ -0,0 +1,13 @@
+numpy==1.22.0
+langchain
+pypdf
+PyPDF2
+streamlit
+docx2txt
+gradio
+faiss-gpu
+openai
+tiktoken
+python-docx
+git+https://github.com/openai/whisper.git
+sounddevice