File size: 3,644 Bytes
397e766 20eae19 397e766 20eae19 b7bd810 20eae19 397e766 b7bd810 397e766 20eae19 1665597 20eae19 4c6b01f 1665597 4c6b01f 397e766 4c6b01f 397e766 6d1db57 397e766 75ef3f7 397e766 4c6b01f 397e766 20eae19 |
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 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
import gradio as gr
from huggingface_hub import InferenceClient
import fitz # PyMuPDF
"""
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("HuggingFaceH4/zephyr-7b-beta")
def extract_text_from_pdf(pdf_path):
# Open the provided PDF file
doc = fitz.open(pdf_path)
text = ""
# Extract text from each page
for page in doc:
text += page.get_text()
doc.close() # Ensure the PDF file is closed
return text
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
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
print(f"Token: {token}") # Debugging statement to trace tokens
yield response
def process_resume_and_respond(pdf_file, message, history, system_message, max_tokens, temperature, top_p):
# Extract text from the PDF file
resume_text = extract_text_from_pdf(pdf_file.name)
# Combine the resume text with the user message
combined_message = f"Resume:\n{resume_text}\n\nUser message:\n{message}"
# Respond using the combined message
response_gen = respond(combined_message, history, system_message, max_tokens, temperature, top_p)
response = "".join([token for token in response_gen])
return response
# Store the uploaded PDF content globally
uploaded_resume_text = ""
def upload_resume(pdf_file):
global uploaded_resume_text
uploaded_resume_text = extract_text_from_pdf(pdf_file.name)
return "Resume uploaded successfully!"
def respond_with_resume(message, history, system_message, max_tokens, temperature, top_p):
global uploaded_resume_text
# Combine the uploaded resume text with the user message
combined_message = f"Resume:\n{uploaded_resume_text}\n\nUser message:\n{message}"
# Respond using the combined message
response_gen = respond(combined_message, history, system_message, max_tokens, temperature, top_p)
response = "".join([token for token in response_gen])
return response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
upload_interface = gr.Interface(
upload_resume,
inputs=gr.File(label="Upload Resume PDF"),
outputs=gr.Textbox(label="Upload Status"),
)
chat_interface = gr.ChatInterface(
respond_with_resume,
additional_inputs=[
gr.Textbox(value="You are a Job Advisor Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
)
demo = gr.TabbedInterface(
[upload_interface, chat_interface],
["Upload Resume", "Chat with Job Advisor"]
)
if __name__ == "__main__":
demo.launch()
|