Spaces:
Running
Running
File size: 2,765 Bytes
2a20c6b cd2ca57 2a20c6b cd2ca57 2a20c6b 0d944ef 01cb892 2a20c6b e1dd907 0d944ef 188ef10 1a8ed74 188ef10 2a20c6b 1a8ed74 2a20c6b 1a8ed74 2a20c6b 01cb892 2a20c6b 6982b56 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
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()
|