LLMs/9. Image Processing.ipynb
2025-03-03 04:06:07 -08:00

112 lines
3.3 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "f65de83c-0d36-4e69-93c2-a2c5fb0f6811",
"metadata": {},
"outputs": [],
"source": [
"#Disable Proxy\n",
"\n",
"import os\n",
"\n",
"def clear_proxy_settings():\n",
" for var in [\"HTTP_PROXY\", \"HTTPS_PROXY\", \"ALL_PROXY\", \"http_proxy\", \"https_proxy\", \"all_proxy\"]:\n",
" if var in os.environ:\n",
" del os.environ[var]\n",
"\n",
"clear_proxy_settings()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "c4a3951c-fcd7-4a05-a141-f6e09aacc111",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"بر اساس متن موجود، سید محمود خلیفه سلطانی مدیرعامل محترم شرکت تکابو صنعت نامی (اینجن پارک) می باشد. \n",
"\n",
"\n",
" \n",
"\n"
]
}
],
"source": [
"import requests\n",
"import json\n",
"from ollama import chat \n",
"\n",
"def image_to_gemma_response(image_path, query):\n",
" # Extract text from image using Landing AI API\n",
" url = \"https://api.va.landing.ai/v1/tools/agentic-document-analysis\"\n",
" files = {\"image\": open(image_path, \"rb\")}\n",
" headers = {\"Authorization\": \"Basic YWdmbjl0d200emV3cjVicHFzeXpuOmFBWGJCTGZRUFBsMzZVVWF3aXFVYVduY0hGVUdIQmhq\"}\n",
" response = requests.post(url, files=files, headers=headers)\n",
" data = response.json()\n",
" \n",
" # Get markdown text from response\n",
" extracted_text = \"\"\n",
" if \"data\" in data and \"markdown\" in data[\"data\"]:\n",
" extracted_text = data[\"data\"][\"markdown\"]\n",
" \n",
" # Create prompt for Gemma\n",
" prompt = f\"\"\"\n",
" # متن استخراج شده از تصویر:\n",
" {extracted_text}\n",
" \n",
" # سوال:\n",
" {query}\n",
" \n",
" لطفاً با استفاده از اطلاعات بالا، به سوال پاسخ دهید. پاسخ را به فارسی بنویسید.\n",
" \"\"\"\n",
"\n",
" # Get response from Gemma\n",
" messages = [{\"role\": \"user\", \"content\": prompt}]\n",
" response = chat(model=\"gemma2:9b\", messages=messages)\n",
" return response['message']['content']\n",
"\n",
"# Usage\n",
"image_path = \"/home/masih/Desktop/Temp/m.jpg\"\n",
"query = \"سید محمود خلیفه سلطانی کیست؟\"\n",
"result = image_to_gemma_response(image_path, query)\n",
"print(result)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b8920fdd-80d2-4299-ab66-2809bee95f99",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python [conda env:base] *",
"language": "python",
"name": "conda-base-py"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}