Create main.py

main.py

@@ -0,0 +1,89 @@
+import os
+import json
+import base64
+import httpx
+import google.generativeai as genai
+
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel, HttpUrl
+
+app = FastAPI(title="Business Card Analyzer")
+
+# Input model for the API
+class ImageRequest(BaseModel):
+    image_url: HttpUrl
+
+# Configure the Google Generative AI client using an environment variable.
+# Make sure to set the GOOGLE_API_KEY variable when running the app.
+GOOGLE_API_KEY = "AIzaSyDcYyq3w21iwipYn17wCAQo3AYWhUIGDSI"
+if not GOOGLE_API_KEY:
+    raise Exception("Please set the GOOGLE_API_KEY environment variable.")
+
+genai.configure(api_key=GOOGLE_API_KEY)
+
+# Define the prompt to instruct the model.
+PROMPT = """
+Analyze the business card and extract the following information in JSON format:
+{
+  "name": "Full Name",
+  "mobile_number": "Mobile Number",
+  "company_name": "Company Name",
+  "email": "Email Address",
+  "job_title": "Job Title",
+  "address": "Address",
+  "website": "Website URL"
+}
+
+Ensure that the response is strictly in JSON format and includes all the fields mentioned above. If any information is missing or unclear, set the corresponding field to null.
+"""
+
+@app.post("/analyze", summary="Analyze a business card image")
+async def analyze_business_card(request: ImageRequest):
+    # Fetch the image from the provided URL
+    try:
+        async with httpx.AsyncClient() as client:
+            response = await client.get(str(request.image_url))
+            response.raise_for_status()
+            img_bytes = response.content
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Failed to fetch image: {e}")
+
+    # Encode the image in base64
+    encoded_image = base64.b64encode(img_bytes).decode("utf-8")
+
+    # Create an instance of the Gemini model
+    model = genai.GenerativeModel(model_name="gemini-1.5-pro")
+
+    # Call the model and process its response
+    try:
+        result = model.generate_content([
+            {
+                "mime_type": "image/jpeg",
+                "data": encoded_image,
+            },
+            PROMPT,
+        ])
+        # Get the raw text response
+        raw = result.text.strip()
+
+        # Remove markdown formatting if present (i.e. ```json ... ```)
+        if raw.startswith("```"):
+            lines = raw.splitlines()
+            if lines[0].startswith("```"):
+                lines = lines[1:]
+            if lines and lines[-1].startswith("```"):
+                lines = lines[:-1]
+            raw = "\n".join(lines).strip()
+
+        data = json.loads(raw)
+    except json.JSONDecodeError as jde:
+        raise HTTPException(status_code=500, detail=f"JSON decoding error: {jde}. Response text was: {raw}")
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"An error occurred while processing the image: {e}")
+
+    return data
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run("main:app", host="0.0.0.0", port=7860, reload=True)