feat: pdf extract

app.py

@@ -1,63 +1,30 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import requests
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForCausalLM
 
-"""
-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 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})
+model = AutoModelForCausalLM.from_pretrained(
+    "yifeihu/TFT-ID-1.0", trust_remote_code=True
+)
+processor = AutoProcessor.from_pretrained("yifeihu/TFT-ID-1.0", trust_remote_code=True)
 
-    response = ""
+prompt = "<OD>"
 
-    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
+url = "https://huggingface.co/yifeihu/TF-ID-base/resolve/main/arxiv_2305_10853_5.png?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
 
-        response += token
-        yield response
+inputs = processor(text=prompt, images=image, return_tensors="pt")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly 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)",
-        ),
-    ],
+generated_ids = model.generate(
+    input_ids=inputs["input_ids"],
+    pixel_values=inputs["pixel_values"],
+    max_new_tokens=1024,
+    do_sample=False,
+    num_beams=3,
 )
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
 
+parsed_answer = processor.post_process_generation(
+    generated_text, task="<OD>", image_size=(image.width, image.height)
+)
 
-if __name__ == "__main__":
-    demo.launch()
+print(parsed_answer)