Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import os | |
| import PyPDF2 | |
| import pandas as pd | |
| import openai | |
| import docx | |
| import requests | |
| import json | |
| from docx import Document | |
| from langchain_community.embeddings import OpenAIEmbeddings | |
| from langchain_community.vectorstores import FAISS | |
| from langchain_community.llms import OpenAI | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| def detect_language(text): | |
| """Detects the language of the input text using OpenAI.""" | |
| response = openai.ChatCompletion.create( | |
| model="gpt-3.5-turbo", | |
| messages=[ | |
| {"role": "system", "content": "Detect the language of this text."}, | |
| {"role": "user", "content": text} | |
| ] | |
| ) | |
| return response["choices"][0]["message"]["content"].strip() | |
| # Set up OpenAI API key (replace with your key) | |
| openai.api_key = "YOUR_OPENAI_API_KEY" | |
| def extract_files_from_folder(folder_path): | |
| """Scans a folder and its subfolders for PDF, TXT, CSV, DOCX, and IPYNB files.""" | |
| extracted_files = {"pdf": [], "txt": [], "csv": [], "docx": [], "ipynb": []} | |
| print(f"Scanning folder: {folder_path}") | |
| for root, subdirs, files in os.walk(folder_path): | |
| print(f"Checking folder: {root}") # Debugging log for subfolders | |
| for file_name in files: | |
| file_path = os.path.join(root, file_name) | |
| print(f"Found file: {file_path}") | |
| if file_name.endswith(".pdf"): | |
| extracted_files["pdf"].append(file_path) | |
| elif file_name.endswith(".txt"): | |
| extracted_files["txt"].append(file_path) | |
| elif file_name.endswith(".csv"): | |
| extracted_files["csv"].append(file_path) | |
| elif file_name.endswith(".docx"): | |
| extracted_files["docx"].append(file_path) | |
| elif file_name.endswith(".ipynb"): | |
| extracted_files["ipynb"].append(file_path) | |
| print("Files found:", extracted_files) # Debugging log | |
| return extracted_files | |
| def combine_text_from_files(extracted_files): | |
| """Combines text from all extracted files.""" | |
| text = ( | |
| get_text_from_pdf(extracted_files["pdf"]) + | |
| read_text_from_files(extracted_files["txt"]) + | |
| get_text_from_csv(extracted_files["csv"]) + | |
| get_text_from_docx(extracted_files["docx"]) + | |
| get_text_from_ipynb(extracted_files["ipynb"]) | |
| ) | |
| return text | |
| def generate_response(question, text): | |
| """Uses OpenAI to answer a question based on extracted text.""" | |
| response = openai.ChatCompletion.create( | |
| model="gpt-3.5-turbo", | |
| messages=[ | |
| {"role": "system", "content": "You are a data analytics assistant. Answer the question based on the provided document content."}, | |
| {"role": "user", "content": f"{question}\n\nBased on the following document content:\n{text[:3000]}"} # Limit to 3000 characters to avoid excessive token usage | |
| ] | |
| ) | |
| return response["choices"][0]["message"]["content"].strip() | |
| def chatbot_interface(question): | |
| folder_path = "New_Data_Analytics/" | |
| extracted_files = extract_files_from_folder(folder_path) | |
| text = combine_text_from_files(extracted_files) | |
| print("Final extracted text for chatbot processing:", text[:500]) # Debugging log (First 500 chars) | |
| if not text.strip(): | |
| return "The folder does not contain valid PDF, TXT, CSV, DOCX, or IPYNB files. Please upload supported file types." | |
| return generate_response(question, text) | |
| # Gradio interface | |
| demo = gr.Interface( | |
| fn=chatbot_interface, | |
| inputs=gr.Textbox(label="Ask a question", placeholder="Type your question here..."), | |
| outputs=gr.Textbox(label="Answer") | |
| ) | |
| demo.launch() | |