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")