Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+local_db/index.faiss filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,432 @@
+import shutil
+import os
+
+# def copy_files(source_folder, destination_folder):
+#     # Create the destination folder if it doesn't exist
+#     if not os.path.exists(destination_folder):
+#         os.makedirs(destination_folder)
+
+#     # Get a list of files in the source folder
+
+#     files_to_copy = os.listdir(source_folder)
+#     for file_name in files_to_copy:
+#         source_file_path = os.path.join(source_folder, file_name)
+#         destination_file_path = os.path.join(destination_folder, file_name)
+
+#         # Copy the file to the destination folder
+#         shutil.copy(source_file_path, destination_file_path)
+
+#         print(f"Copied {file_name} to {destination_folder}")
+
+# # Specify the source folder and destination folder paths
+# source_folder = "/kaggle/input/fiver-app5210"
+# destination_folder = "/local_db"
+
+# copy_files(source_folder, destination_folder)
+
+# def copy_files(source_folder, destination_folder):
+#     # Create the destination folder if it doesn't exist
+#     if not os.path.exists(destination_folder):
+#         os.makedirs(destination_folder)
+
+#     # Get a list of files in the source folder
+#     files_to_copy = os.listdir(source_folder)
+
+#     for file_name in files_to_copy:
+#         source_file_path = os.path.join(source_folder, file_name)
+#         destination_file_path = os.path.join(destination_folder, file_name)
+
+#         # Copy the file to the destination folder
+#         shutil.copy(source_file_path, destination_file_path)
+
+#         print(f"Copied {file_name} to {destination_folder}")
+
+# # Specify the source folder and destination folder paths
+# source_folder = "/kaggle/input/fiver-app-docs"
+# destination_folder = "/docs"
+
+# copy_files(source_folder, destination_folder)
+
+import os
+import openai
+
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+os.environ["OPENAI_API_KEY"] 
+
+
+def api_key(key):
+
+    import os
+    import openai
+
+    os.environ["TOKENIZERS_PARALLELISM"] = "false"
+    os.environ["OPENAI_API_KEY"] = key
+    openai.api_key = key
+
+    return "Successful!"
+
+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 CharacterTextSplitter
+    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 = CharacterTextSplitter(
+        separator="\n",
+        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 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)
+
+        # Get the file name without the directory path
+        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 search_local(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_db/", embeddings)
+    docs = file_db.similarity_search(question)
+
+    print(docs)
+    type(docs)
+    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"
+
+import os
+
+def list_files_in_directory(directory):
+    file_list = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            file_list.append(file)
+    return file_list
+
+directory_path = '/home/user/app/docs'
+file_list = list_files_in_directory(directory_path)
+
+print("List of file names in the directory:")
+for file_name in file_list:
+    print(file_name)
+
+def soap_report(doc_name, question):
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    import openai
+    import docx
+
+    docx_path = '/home/user/app/docs/'+doc_name
+
+    doc = docx.Document(docx_path)
+    extracted_text = 'Extracted text:\n\n\n'
+
+    for paragraph in doc.paragraphs:
+        extracted_text += paragraph.text + '\n'
+
+    question = "\n\nUse the '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 = OpenAI()
+    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
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+    llm = OpenAI()
+    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
+
+    template = """Question: {question}
+
+    Answer: Let's think step by step."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+    llm = OpenAI()
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(question)
+
+    return response
+
+global output
+global response
+
+def audio_text(filepath):
+    import openai
+    global output
+
+    audio = open(filepath, "rb")
+    transcript = openai.Audio.transcribe("whisper-1", audio)
+    output = transcript["text"]
+
+    return output
+
+def text_soap():
+    from langchain.llms import OpenAI
+    from langchain import PromptTemplate, LLMChain
+    global output
+    global 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."""
+
+    prompt = PromptTemplate(template=template, input_variables=["question"])
+    llm = OpenAI()
+    llm_chain = LLMChain(prompt=prompt, llm=llm)
+    response = llm_chain.run(question)
+
+    return response
+
+def docx(name):
+    global response
+    response = response
+    import docx
+    path = f"/home/user/app/docs/{name}.docx"
+
+    doc = docx.Document()
+    doc.add_paragraph(response)
+    doc.save(path)
+
+    return "Successfully saved .docx File"
+
+import gradio as gr
+
+css = """
+.col{
+    max-width: 50%;
+    margin: 0 auto;
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("File Chatting App")
+
+    with gr.Tab("Chat with your Files"):
+      with gr.Column(elem_classes="col"):
+
+        with gr.Tab("Upload and Process your Files"):
+          with gr.Column():
+
+            api_key_input = gr.Textbox(label="Enter your API Key here")
+            api_key_button = gr.Button("Submit")
+            api_key_output = gr.Textbox(label="Output")
+
+            file_input = gr.Files(label="Upload your File(s) here")
+            upload_button = gr.Button("Upload")
+            file_output = gr.Textbox(label="Output")
+
+            process_button = gr.Button("Process")
+            process_output = gr.Textbox(label="Output")
+
+        with gr.Tab("Ask Questions to your Files"):
+          with gr.Column():
+
+            search_input = gr.Textbox(label="Enter your Question here")
+            search_button = gr.Button("Search")
+            search_output = gr.Textbox(label="Output")
+
+            search_gpt_button = gr.Button("Ask ChatGPT")
+            search_gpt_output = gr.Textbox(label="Output")
+
+            delete_button = gr.Button("Delete")
+            delete_output = gr.Textbox(label="Output")
+
+    with gr.Tab("Chat with your Local Files"):
+      with gr.Column(elem_classes="col"):
+
+        local_search_input = gr.Textbox(label="Enter your 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")
+
+    with gr.Tab("Ask Question to SOAP Report"):
+      with gr.Column(elem_classes="col"):
+
+        soap_input = gr.Dropdown(choices=file_list, label="Choose File")
+        soap_question = gr.Textbox(label="Enter your Question here")
+        soap_button = gr.Button("Submit")
+        soap_output = gr.Textbox(label="Output")
+
+    with gr.Tab("Convert Audio to SOAP Report"):
+      with gr.Column(elem_classes="col"):
+
+        audio_text_input = gr.Audio(source="microphone", type="filepath", label="Upload your Audio File here")
+        audio_text_button = gr.Button("Generate Transcript")
+        audio_text_output = gr.Textbox(label="Output")
+
+        text_soap_button = gr.Button("Generate SOAP Report")
+        text_soap_output = gr.Textbox(label="Output")
+
+        docx_input = gr.Textbox(label="Enter the Name of .docx File")
+        docx_button = gr.Button("Save .docx File")
+        docx_output = gr.Textbox(label="Output")
+
+    api_key_button.click(api_key, inputs=api_key_input, outputs=api_key_output)
+
+    upload_button.click(save_file, inputs=file_input, outputs=file_output)
+    process_button.click(process_file, inputs=None, outputs=process_output)
+
+    search_button.click(search_file, inputs=search_input, outputs=search_output)
+    search_gpt_button.click(search_gpt, inputs=search_input, outputs=search_gpt_output)
+
+    delete_button.click(delete_file, inputs=None, outputs=delete_output)
+
+    local_search_button.click(search_local, inputs=local_search_input, outputs=local_search_output)
+    local_gpt_button.click(local_gpt, inputs=local_search_input, outputs=local_gpt_output)
+
+    soap_button.click(soap_report, inputs=[soap_input, soap_question], outputs=soap_output)
+
+    audio_text_button.click(audio_text, inputs=audio_text_input, outputs=audio_text_output)
+    text_soap_button.click(text_soap, inputs=None, outputs=text_soap_output)
+
+    audio_text_button.click(audio_text, inputs=audio_text_input, outputs=audio_text_output)
+    text_soap_button.click(text_soap, inputs=None, outputs=text_soap_output)
+    docx_button.click(docx, inputs=docx_input, outputs=docx_output)
+
+
+demo.queue()
+demo.launch()
+
+
+
+# # Commented out IPython magic to ensure Python compatibility.
+# #download file_db
+
+# # %cd /kaggle/working/
+
+# !zip -r "file_db.zip" "file_db"
+
+# from IPython.display import FileLink
+# FileLink("file_db.zip")

local_db/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd0ec24292a11baff18e2d7dabd979640a377e99ee0ccbd32ea7550c439039b9
+size 2107437

local_db/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1634917e29728132745ef3406e8d38c76879f209cd4a1d1caad70e5a308443
+size 321281

requirements.txt

@@ -0,0 +1,11 @@
+numpy==1.22.0
+langchain
+PyPDF2
+docx2txt
+gradio
+faiss-gpu
+openai
+tiktoken
+python-docx
+git+https://github.com/openai/whisper.git
+sounddevice