Spaces:
Paused
Paused
File size: 8,614 Bytes
ac5e4ff 7ae77ed e45ea87 ac5e4ff 7ae77ed 7268d90 ac5e4ff 7ae77ed ac5e4ff edc46ec ac5e4ff | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 | import gradio as gr
import PyPDF2
import io
import os
import time
from together import Together
import textwrap
import tempfile
# 1st work is to extract the pdf file
def extract_pdf(pdf_file):
text= ""
try:
if hasattr(pdf_file, "read"): #convert pf into bytes format (data byte bit type)
pdf_content= pdf_file.read()
if hasattr(pdf_file,"seek"):
pdf_file.seek(0)
else:
#if it already in bites and read
pdf_content= pdf_file
pdf_reader= PyPDF2.PdfReader(io.BytesIO(pdf_content)) #START reading and need to extract the pdf
for page_num in range(len(pdf_reader.pages)):
page_text= pdf_reader.pages[page_num].extract_text()
if page_text: # check the extract is working or not
print("okay")
text= text + page_text + "\n"
else:
print("no extractable text is found there")
text += f"[Page{page_num+1}]"
if not text.strip():
return "no text extracted from PDF it a scanned file or image"
return text
except Exception as e:
return f"Error when extracting text from pdf : {str(e)}"
## create a function to chat with the pdf
def chat_with_pdf(api_key, pdf_text, user_question, history):
if not api_key.strip():
return history + [(user_question,"Error: plase enter your own api key")], history
if not pdf_text.strip() or pdf_text.startswith("Error") or pdf_text.startswith("No text"):
return history + [(user_question,"Error: plase upload a valid pdf file with extractable text format")], history
if not user_question.strip():
return history + [(user_question,"Error: please enter a valid question")], history
try:
# model connections all for same
client= Together(api_key=api_key) # server e giye hi dibe and server response korbe vhul hole server response korbe na
max_content_len= 150000 # check for the number of word
if len(pdf_text) > max_content_len:
half_len = max_content_len//2
pdf_context= pdf_text[: half_len]+ "\n\n[....Content truncated due to length ....]\n\n" + pdf_text[-half_len:]
else:
pdf_content= pdf_text
system_message= f"""You are an intelligent assistant designed to read, understand, and extract information from PDF documents.
Based on any question or query the user asks—whether it's about content, summaries, data extraction, definitions, insights, or interpretation—you will
analyze the following PDF content and provide an accurate, helpful response grounded in the document. Always respond with clear, concise, and context-aware information.
PDF CONTENT:
{pdf_context}
Answer the user's questions only based on the PDF content above. If the answer cannot be found in the PDF, politely state that the information is not available in the provided document."""
# Prepare message history for Together API
messages = [
{"role": "system", "content": system_message},
]
# Add chat history
for h_user, h_bot in history:
messages.append({"role": "user", "content": h_user})
messages.append({"role": "assistant", "content": h_bot})
# Add the current user question
messages.append({"role": "user", "content": user_question})
#connect the model with the app
reponse = client.chat.completions.create(
model= "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
messages= messages,
max_tokens= 5000, #5000
temperature= .7,
)
assistance_reponse = response.choices[0].message.content
# update the chat history
new_history= history + [(user_question, assistance_reponse)] #history update purono conversation + current conver= new history
return new_history, new_history
except Exception as e:
error_message= f"Error:{str(e)}"
return history + [(user_question, error_message)], history
# now process the pdf before the chat
def process_pdf(pdf_file, api_key_input):
if pdf_file is None:
return "please upload a PDF file.","",[]
try:
file_name= os.path.basename(pdf_file.name) if hasattr(pdf_file,"name") else "please Upload"
pdf_text= extract_pdf(pdf_file)
if pdf_text.startswith("Error extracting text from PDF"):
return f"❌ {pdf_text}", "", []
if not pdf_text.strip() or pdf_text.startswith("No text could be extracted"):
return f"⚠️ {pdf_text}", "", []
word_count= len(pdf_text.split())
# Return a message with the file name and text content
status_message = f"✅ Successfully processed PDF: {file_name} ({word_count} words extracted)"
return status_message, pdf_text,[]
except Exception as e:
return f"❌ Error processing PDF: {str(e)}", "", []
#
def validate_api_key(api_key):
"""Simple validation for API key format"""
if not api_key or not api_key.strip():
return "❌ API Key is required"
if len(api_key.strip()) < 10:
return "❌ API Key appears to be too short"
return "✓ API Key format looks valid (not verified with server)"
with gr.Blocks(title="chatsPDFsupport", theme=gr.themes.Ocean()) as app:
gr.Markdown("# 📄 ChatPDF with Together AI")
gr.Markdown("Upload a PDF and chat with it using the Llama-3.3-70B model.")
with gr.Row():
with gr.Column(scale=1)
api_key_input = gr.Textbox(
label="Together API Key",
placeholder="Enter your Together API key here...",
type="password")
# API key validation
api_key_status = gr.Textbox(
label="API Key Status",
interactive=False
)
# PDF upload
pdf_file = gr.File(
label="Upload PDF",
file_types=[".pdf"],
type="binary" # Ensure we get binary data
)
# Process PDF button
process_button = gr.Button("Process PDF")
# Status message
status_message = gr.Textbox(
label="Status",
interactive=False
)
# Hidden field to store the PDF text
pdf_text = gr.Textbox(visible=False)
# Optional: Show PDF preview
with gr.Accordion("PDF Content Preview", open=False):
pdf_preview = gr.Textbox(
label="Extracted Text Preview",
interactive=False,
max_lines=10,
show_copy_button=True
)
with gr.Column(scale=2): #right side column row
# Chat interface
chatbot = gr.Chatbot(
label="Chat with PDF",
height=500,
show_copy_button=True
)
# Question input
question = gr.Textbox(
label="Ask a question about the PDF",
placeholder="What is the main topic of this document?",
lines=2
)
#submit button
sumbit_button= gr.Button("Submit Question")
# Event handlers
def update_preview(text):
"""Update the preview with the first few lines of the PDF text"""
if not text or text.startswith("Error") or text.startswith("No text"):
return text
# Get the first ~500 characters for preview
preview = text[:500]
if len(text) > 500:
preview += "...\n[Text truncated for preview. Full text will be used for chat.]"
return preview
# API key validation event
api_key_input.change(
fn=validate_api_key,
inputs=[api_key_input],
outputs=[api_key_status]
)
process_button.click(
fn=process_pdf,
inputs=[pdf_file, api_key_input],
outputs=[status_message, pdf_text, chatbot]
).then(
fn=update_preview,
inputs=[pdf_text],
outputs=[pdf_preview]
)
submit_button.click(
fn=chat_with_pdf,
inputs=[api_key_input, pdf_text, question, chatbot],
outputs=[chatbot, chatbot]
).then(
fn=lambda: "",
outputs=question
)
question.submit(
fn=chat_with_pdf,
inputs=[api_key_input, pdf_text, question, chatbot],
outputs=[chatbot, chatbot]
).then(
fn=lambda: "",
outputs=question
)
# Launch the app
if __name__ == "__main__":
app.launch(share=True)
|