File size: 2,710 Bytes
225a4a4 5a090b0 225a4a4 5a090b0 |
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 |
import os
import gradio as gr
import requests
import mimetypes
# Optional: load environment variables from a .env file (install python-dotenv if needed)
try:
from dotenv import load_dotenv
load_dotenv()
except ImportError:
pass # dotenv not installed, ignore
# Get the API URL from environment variable, provide a fallback or raise error if not set
API_URL = os.environ.get("API_URL")
if not API_URL:
raise ValueError("API_URL environment variable not set. Please set it before running the script.")
def ocr_from_paths(file_paths, query):
results = []
if isinstance(file_paths, str):
file_paths = [file_paths]
for path in file_paths:
filename = path.split("/")[-1]
mime_type, _ = mimetypes.guess_type(path)
if not mime_type:
results.append(f"❌ {filename}: Unsupported file type")
continue
with open(path, "rb") as f:
files_param = {"file": (filename, f, mime_type)}
data_param = {"query": query or "describe the image"} # default query if empty
try:
response = requests.post(
API_URL,
files=files_param,
data=data_param,
headers={"accept": "application/json"} # do NOT set Content-Type here
)
if response.status_code == 200:
resp_json = response.json()
extracted_text = resp_json.get("result") or resp_json.get("text") or str(resp_json)
results.append(f"✅ {filename}:\n{extracted_text}")
else:
results.append(f"❌ {filename}: API Error ({response.status_code})")
except Exception as e:
results.append(f"❌ {filename}: {str(e)}")
return "\n\n".join(results)
with gr.Blocks() as demo:
gr.Markdown("## Browse & OCR Extract PDFs/Images (Batch)")
with gr.Row():
file_input = gr.File(
label="Upload Files",
file_types=[".pdf", ".png", ".jpg", ".jpeg", ".webp"],
file_count="multiple"
)
query_input = gr.Textbox(
label="Query (optional)",
placeholder="Enter a query string for the API"
)
output_text = gr.Textbox(
label="Extracted Text Results",
interactive=False,
lines=15,
placeholder="OCR results will appear here..."
)
submit_btn = gr.Button("Extract Text")
submit_btn.click(
ocr_from_paths,
inputs=[file_input, query_input],
outputs=output_text
)
if __name__ == "__main__":
demo.launch()
|