Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from huggingface_hub import InferenceClient | |
| import pymupdf | |
| from duckduckgo_search import DDGS | |
| """ | |
| For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference | |
| """ | |
| client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1") | |
| # PDF Parsing | |
| def extract_text_from_pdf(pdf_file): | |
| doc = pymupdf.open(pdf_file) | |
| text = " ".join([page.get_textpage().extractTEXT() for page in doc]) | |
| return text | |
| # Web search fallback | |
| def search_web(query): | |
| with DDGS() as ddgs: | |
| results = ddgs.text(query) | |
| if results: | |
| return results[0]["body"] | |
| return "No relevant results found on the web." | |
| SYSTEM_PROMPT = """ | |
| You are an intelligent and friendly AI assistant. | |
| Your goals: | |
| - Answer user questions clearly and concisely. | |
| - If a PDF document is provided, use its content to give informed answers. | |
| - For questions about recent or live topics (e.g., news, prices, events), you may perform a web search and summarize the result. | |
| - If no document or web context is available, still try to help using general knowledge. | |
| - Be honest if you don’t know something. | |
| - Always be polite, helpful, and respectful. | |
| """ | |
| def respond( | |
| message, | |
| history: list[tuple[str, str]], | |
| max_tokens, | |
| temperature, | |
| top_p, | |
| ): | |
| messages = [{"role": "system", "content": SYSTEM_PROMPT}] | |
| for val in history: | |
| if val[0]: | |
| messages.append({"role": "user", "content": val[0]}) | |
| if val[1]: | |
| messages.append({"role": "assistant", "content": val[1]}) | |
| messages.append({"role": "user", "content": message}) | |
| response = "" | |
| for message in client.chat_completion( | |
| messages, | |
| max_tokens=max_tokens, | |
| stream=True, | |
| temperature=temperature, | |
| top_p=top_p, | |
| ): | |
| token = message.choices[0].delta.content | |
| response += token | |
| yield response | |
| """ | |
| For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface | |
| """ | |
| with gr.Blocks() as demo: | |
| gr.Markdown("## 🤖 Smart AI Chatbot (PDF + Web + General QA)") | |
| pdf_file = gr.File(label="📄 Upload a PDF", file_types=[".pdf"]) | |
| chat = gr.ChatInterface( | |
| respond, | |
| additional_inputs=[ | |
| gr.Textbox(value="You are a helpful assistant.", label="System message"), | |
| gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"), | |
| gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"), | |
| gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"), | |
| pdf_file, # ✅ Works now | |
| ], | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch() | |