Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import os | |
| import PyPDF2 | |
| import pandas as pd | |
| import openai | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain.embeddings import OpenAIEmbeddings | |
| from langchain.vectorstores import FAISS | |
| from langchain.llms import OpenAI | |
| 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 get_text_from_pdf(pdf_files): | |
| text = "" | |
| for pdf in pdf_files: | |
| reader = PyPDF2.PdfReader(pdf) | |
| for page in reader.pages: | |
| text += page.extract_text() + "\n" | |
| return text | |
| def get_text_from_txt(txt_files): | |
| text = "" | |
| for txt in txt_files: | |
| text += txt.read().decode("utf-8") + "\n" | |
| return text | |
| def get_text_from_csv(csv_files): | |
| text = "" | |
| for csv in csv_files: | |
| df = pd.read_csv(csv) | |
| text += df.to_string() + "\n" | |
| return text | |
| def create_vector_database(text): | |
| splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100) | |
| texts = splitter.split_text(text) | |
| embeddings = OpenAIEmbeddings() | |
| vector_db = FAISS.from_texts(texts, embeddings) | |
| return vector_db | |
| def get_answer(question, vector_db): | |
| retriever = vector_db.as_retriever() | |
| docs = retriever.get_relevant_documents(question) | |
| if not docs: | |
| return "I could not find the answer in the documents. Do you want me to search external sources?" | |
| context = "\n".join([doc.page_content for doc in docs]) | |
| language = detect_language(question) | |
| response = openai.ChatCompletion.create( | |
| model="gpt-3.5-turbo", | |
| messages=[ | |
| {"role": "system", "content": f"You are a Data Analytics assistant. Answer in {language}. Use the documents to answer questions."}, | |
| {"role": "user", "content": question + "\n\nBased on the following context:\n" + context} | |
| ] | |
| ) | |
| return response["choices"][0]["message"]["content"] | |
| def chatbot_interface(pdf_files, txt_files, csv_files, question): | |
| text = "" | |
| text += get_text_from_pdf(pdf_files) if pdf_files else "" | |
| text += get_text_from_txt(txt_files) if txt_files else "" | |
| text += get_text_from_csv(csv_files) if csv_files else "" | |
| if not text: | |
| return "Please upload files before asking questions." | |
| vector_db = create_vector_database(text) | |
| return get_answer(question, vector_db) | |
| # Gradio interface | |
| demo = gr.Interface( | |
| fn=chatbot_interface, | |
| inputs=[gr.File(file_types=[".pdf"], multiple=True), | |
| gr.File(file_types=[".txt"], multiple=True), | |
| gr.File(file_types=[".csv"], multiple=True), | |
| gr.Textbox(placeholder="Type your question here...")], | |
| outputs=gr.Textbox() | |
| ) | |
| demo.launch() | |