المواجهة النهائية للتعرف الضوئي على الحروف العربية: أي ذكاء اصطناعي يقرأ بشكل أفضل؟

from PIL import Image  
from vllm import LLM, SamplingParams

MODEL = "nanonets/Nanonets-OCR-s"  
PROMPT = """Extract the text from the above document as if you were  
reading it naturally. Return tables in html format. Return equations  
in LaTeX. If there is an image, add a description inside <img></img>.  
Watermarks: <watermark>TEXT</watermark>."""

img = Image.open("document.jpg").convert("RGB")

llm = LLM(  
   model=MODEL,  
   gpu_memory_utilization=0.95,  
   max_model_len=8192,  
   max_num_seqs=1,  
   mm_processor_kwargs={"min_pixels": 28*28, "max_pixels": 1280*28*28},  
   limit_mm_per_prompt={"image": 1},  
   trust_remote_code=True,  
)

prompt_text = (  
   "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"  
   "<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>"  
   f"{PROMPT}<|im_end|>\n"  
   "<|im_start|>assistant\n"  
)

params = SamplingParams(  
   max_tokens=8192, temperature=0, repetition_penalty=1.1,  
   stop_token_ids=[151645, 151643],  
)

output = llm.generate(  
   [{"prompt": prompt_text, "multi_modal_data": {"image": img}}], params  
)  
print(output[0].outputs[0].text.strip()) 

from vllm import LLM, SamplingParams  
from vllm.model_executor.models.deepseek_ocr import NGramPerReqLogitsProcessor  
from PIL import Image

MODEL = "deepseek-ai/DeepSeek-OCR"  
img   = Image.open("document.jpg").convert("RGB")

llm = LLM(  
   model=MODEL,  
   enable_prefix_caching=False,  
   mm_processor_cache_gb=0,  
   logits_processors=[NGramPerReqLogitsProcessor],  
   limit_mm_per_prompt={"image": 1},  
   trust_remote_code=True,  
   max_model_len=8192,  
   max_num_seqs=2,  
)

params = SamplingParams(  
   temperature=0.0, max_tokens=8192,  
   skip_special_tokens=False,  
   extra_args={  
       "ngram_size": 30, "window_size": 90,  
       "whitelist_token_ids": {128821, 128822},  # <bbox>, </bbox>  
   },  
)

output = llm.generate(  
   [{"prompt": "<image>\nFree OCR.", "multi_modal_data": {"image": img}}],  
   params,  
)  
print(output[0].outputs[0].text.strip()) 

from transformers import AutoTokenizer  
from vllm import LLM, SamplingParams  
from PIL import Image

MODEL = "PaddlePaddle/PaddleOCR-VL"  
img   = Image.open("document.jpg").convert("RGB")

llm = LLM(  
   model=MODEL, trust_remote_code=True,  
   max_model_len=4096, max_num_seqs=5,  
   limit_mm_per_prompt={"image": 1},  
   gpu_memory_utilization=0.95,  
   enable_prefix_caching=False, mm_processor_cache_gb=0,  
)

tokenizer = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True)  
messages = [{"role": "user", "content": [  
   {"type": "image"}, {"type": "text", "text": "OCR:"}  
]}]

prompt_text = tokenizer.apply_chat_template(  
   messages, tokenize=False, add_generation_prompt=True  
)

params = SamplingParams(  
   max_tokens=4096, temperature=0,  
   repetition_penalty=1.1, stop_token_ids=[151645, 151643],  
)

output = llm.generate(  
   [{"prompt": prompt_text, "multi_modal_data": {"image": img}}], params  
)  
print(output[0].outputs[0].text.strip())

from vllm import LLM, SamplingParams  
from PIL import Image

MODEL  = "NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct"  
PROMPT = ("Below is the image of one page of a document, as well as "  
         "some raw textual content that was previously extracted for it. "  
         "Just return the plain text representation of this document as if "  
         "you were reading it naturally. Do not hallucinate.")

img = Image.open("document.jpg").convert("RGB")

llm = LLM(  
   model=MODEL,  
   gpu_memory_utilization=0.95, max_model_len=8192, max_num_seqs=1,  
   mm_processor_kwargs={"min_pixels": 28*28, "max_pixels": 1280*28*28},  
   limit_mm_per_prompt={"image": 1}, trust_remote_code=True,  
)

prompt_text = (  
   "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n"  
   "<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>"  
   f"{PROMPT}<|im_end|>\n"  
   "<|im_start|>assistant\n"  
)

params = SamplingParams(  
   max_tokens=8192, temperature=0,  
   repetition_penalty=1.1, stop_token_ids=[151645, 151643],  
)

output = llm.generate(  
   [{"prompt": prompt_text, "multi_modal_data": {"image": img}}], params  
)  
print(output[0].outputs[0].text.strip() 

from transformers import AutoProcessor  
from vllm import LLM, SamplingParams  
from PIL import Image

MODEL  = "tencent/HunyuanOCR"  
PROMPT = ("Extract the text from the above document as if you were reading "  
         "it naturally. Return tables in html format. If there is an image "  
         "wrap it as <img>image here</img>. Watermarks: "  
         "<watermark>TEXT</watermark>.")

img = Image.open("document.jpg").convert("RGB")

llm = LLM(  
   model=MODEL, trust_remote_code=True,  
   gpu_memory_utilization=0.90,  
   max_model_len=16384, limit_mm_per_prompt={"image": 1},  
)

processor = AutoProcessor.from_pretrained(MODEL, trust_remote_code=True)  
messages = [  
   {"role": "system", "content": ""},  
   {"role": "user", "content": [  
       {"type": "image"}, {"type": "text", "text": PROMPT}  
   ]}  
]

prompt_text = processor.apply_chat_template(  
   messages, tokenize=False, add_generation_prompt=True  
)

params = SamplingParams(  
   max_tokens=16384, temperature=0, repetition_penalty=1.1,  
)

output = llm.generate(  
   [{"prompt": prompt_text, "multi_modal_data": {"image": img}}], params  
)  
print(output[0].outputs[0].text.strip())

# Install the client

# pip install kawn.ai

import os

from kawn import KawnClient

from kawn.services import OCRService

# Set your API key (or pass directly to KawnClient)

os.environ["MISRAJ_API_KEY"] = "your_api_key_here"

client      = KawnClient(os.environ["MISRAJ_API_KEY"])

ocr_service = OCRService(client)

# Process an image or PDF - it's one call

result = ocr_service.process_file(file_path="document.jpg")

# result.pages is a list of OCRPage objects

for page in result.pages:

   print(f"--- Page {page.index} ---")

   print(page.content)