Beta version

app.py

@@ -0,0 +1,207 @@
+import gradio as gr
+import requests
+from PIL import Image
+from pdf2image import convert_from_path
+from typing import List, Union, Dict, Optional, Tuple
+from io import BytesIO
+import base64
+import numpy as np
+import json
+
+prompt = """You are an advanced document parsing bot. Given the fixture schedule I provided, you need to parse out 
+
+1. the name of the fixture
+2. the company that produces this fixture
+3. the part number of this fixture. It is a series of specification codes connected with - , and you can get the info by reading the texts marked in a different color or reading the top bar. Include every specification code in a correct order in your answer. 
+4. the input wattage of this fixture, short answer. Please answer the wattage according to the part number you found in question 3 
+
+Please format your response in json format
+{
+    "fixture_name": <fixture name>,
+    "manufacture_name": <company name>,
+    "mfr": <part number>,
+    "input wattage": <numerical input wattage>
+}
+
+---
+For example
+{
+    "fixture_name": "SW24/1.5 Led Strips - Static White",
+    "manufacture_name": "Q-Tran Inc.",
+    "mfr": "SW24-1.5-DRY-30-BW-BW-WH-CL2-535",
+    "input wattage": "1.5W"
+}"""
+
+def query_openai_api(messages, model, temperature=0, api_key=None, organization_key=None, json_mode=False):
+    try:
+        url = "https://api.openai.com/v1/chat/completions"
+        if organization_key is not None:
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {api_key}",
+                "OpenAI-Organization": f"{organization_key}",
+            }
+        else:
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {api_key}",
+            }
+        data = {"model": model, "messages": messages, "temperature": temperature}
+        if json_mode:
+            data["response_format"] = {"type": "json_object"}
+
+        # Make the POST request and return the response
+        response = requests.post(url, headers=headers, data=json.dumps(data)).json()
+        print(response)
+        return response["choices"][0]["message"]["content"].lstrip(), response
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return f"API_ERROR: {e}", None
+
+class GPT4V_Client:
+    def __init__(self, api_key, organization_key, model_name="gpt-4-vision-preview", max_tokens=512):
+        self.api_key = api_key
+        self.organization_key = organization_key
+        # self.client = OpenAI(api_key=api_key)
+        self.model_name = model_name
+        self.max_tokens = max_tokens
+
+    def chat(self, messages, json_mode):
+        return query_openai_api(messages, self.model_name, api_key=self.api_key, organization_key=self.organization_key, json_mode=json_mode)
+
+    def one_step_chat(
+        self,
+        text,
+        image: Union[Image.Image, np.ndarray],
+        system_msg: Optional[str] = None,
+        json_mode=False,
+    ):
+        jpeg_buffer = BytesIO()
+
+        # Save the image as JPEG to the buffer
+        if isinstance(image, np.ndarray):
+            image = Image.fromarray(image)
+        image = image.convert("RGB")
+        image.save(jpeg_buffer, format="JPEG")
+
+        # Get the byte data from the buffer
+        jpeg_data = jpeg_buffer.getvalue()
+
+        # Encode the JPEG image data in base64
+        jpg_base64 = base64.b64encode(jpeg_data)
+
+        # If you need it in string format
+        jpg_base64_str = jpg_base64.decode("utf-8")
+        messages = []
+        if system_msg is not None:
+            messages.append({"role": "system", "content": system_msg})
+        messages += [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": text},
+                    {
+                        "type": "image_url",
+                        "image_url": {
+                            "url": f"data:image/jpeg;base64,{jpg_base64_str}"
+                        },
+                    },
+                ],
+            }
+        ]
+        return self.chat(messages, json_mode=json_mode)
+
+    def one_step_multi_image_chat(
+        self,
+        text,
+        images: list[Union[Image.Image, np.ndarray]],
+        system_msg: Optional[str] = None,
+        json_mode=False,
+    ):
+        """
+        images: [{"image": PIL.image, "detail": "high" or "low }]
+
+        For low res mode, we expect a 512px x 512px image. For high res mode, the short side of the image should be less than 768px and the long side should be less than 2,000px.
+        """
+        details = [i["detail"] for i in images]
+        img_strs = []
+        for img_info in images:
+            image = img_info["image"]
+            jpeg_buffer = BytesIO()
+
+            # Save the image as JPEG to the buffer
+            if isinstance(image, np.ndarray):
+                image = Image.fromarray(image)
+            image = image.convert("RGB")
+            image.save(jpeg_buffer, format="JPEG")
+
+            # Get the byte data from the buffer
+            jpeg_data = jpeg_buffer.getvalue()
+
+            # Encode the JPEG image data in base64
+            jpg_base64 = base64.b64encode(jpeg_data)
+
+            # If you need it in string format
+            jpg_base64_str = jpg_base64.decode("utf-8")
+            img_strs.append(f"data:image/jpeg;base64,{jpg_base64_str}")
+        messages = []
+        if system_msg is not None:
+            messages.append({"role": "system", "content": system_msg})
+
+        img_sub_msg = [
+            {
+                "type": "image_url",
+                "image_url": {"url": img_str, "detail": detail},
+            }
+            for img_str, detail in zip(img_strs, details)
+        ]
+        messages += [
+            {
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": text},
+                ]
+                + img_sub_msg,
+            }
+        ]
+        return self.chat(messages, json_mode=json_mode)
+    
+def markdown_json_to_table(markdown_json_string, iteration):
+    if markdown_json_string[0] == '`':
+        json_string = markdown_json_string.strip("```json\n").rstrip("```")
+        json_object = json.loads(json_string)
+        values = json_object.values()
+        if iteration == 0:
+            headers = json_object.keys()
+            markdown_table = "| " + " | ".join(headers) + " |\n" + \
+                            "|---" * len(json_object) + "|\n" + \
+                            "| " + " | ".join(map(str, values)) + " |"
+        else:
+            markdown_table =  "|---" * len(json_object) + "|\n" + \
+                        "| " + " | ".join(map(str, values)) + " |"
+    else: 
+        markdown_table = ""
+    return markdown_table
+
+def gptRead(cutsheets, api_key, organization_key):
+    fixtureInfo = ""
+    iteration = 0
+    for cutsheet in cutsheets:
+        source = (convert_from_path(cutsheet.name))[0]
+        client = GPT4V_Client(api_key=api_key, organization_key=organization_key)
+        fixtureInfo += markdown_json_to_table(client.one_step_chat(prompt, source)[0], iteration)
+        iteration += 1
+    return fixtureInfo
+
+if __name__ == "__main__":
+    with gr.Blocks() as demo:
+        gr.Markdown("# Lighting Manufacture Cutsheet GPT Tool")
+        api_key = gr.Textbox(label = "Input your ChatGPT4 API Key: ")
+        organization_key = gr.Textbox(label = "Input your ChatGPT4 API Organization Key: ", info = "(optional)")
+        # image = gr.Image()
+        file_uploader = gr.UploadButton("Upload cutsheets", type="filepath", file_count="multiple")
+        form = gr.Markdown()
+        file_uploader.upload(gptRead, [file_uploader, api_key, organization_key], form)
+
+    demo.launch(share=True)
+