Upload 4 files

README.md

@@ -1,13 +1,6 @@
 ---
-title: MongoDBpixtralOCR
-emoji: 🏆
-colorFrom: purple
-colorTo: green
+title: pixtral
+app_file: app.py
 sdk: gradio
 sdk_version: 4.44.0
-app_file: app.py
-pinned: false
-license: apache-2.0
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,96 @@
+import base64
+import requests
+from io import BytesIO
+from PIL import Image
+import gradio as gr
+from pymongo import MongoClient
+import time
+import uuid
+
+# MongoDB setup
+mongo_client = MongoClient("mongodb+srv://atharva2021:[email protected]/")
+db = mongo_client['bajaj']
+collection = db['client']
+
+# Function to encode the image to base64
+def encode_image(img):
+    buffered = BytesIO()
+    img.save(buffered, format="PNG")
+    encoded_string = base64.b64encode(buffered.getvalue()).decode("utf-8")
+    return encoded_string
+
+# Chat function with Pixtral and MongoDB saving
+def chat_with_pixtral(uploaded_file, mrn_number, user_question):
+    if uploaded_file is not None and mrn_number.strip() != "":
+        base64_img = encode_image(uploaded_file)
+
+        api = "https://api.hyperbolic.xyz/v1/chat/completions"
+        api_key = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiJyZzMyNzAyNEBnbWFpbC5jb20ifQ._frFve-BYZdb0Qo6FIj6xcDcxpY-6QlC2O-ToQxBjkc"  # Add your API key here
+
+        headers = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {api_key}",
+        }
+
+        payload = {
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": user_question},  
+                        {
+                            "type": "image_url",
+                            "image_url": {"url": f"data:image/jpeg;base64,{base64_img}"},
+                        },
+                    ],
+                }
+            ],
+            "model": "mistralai/Pixtral-12B-2409",
+            "max_tokens": 2048,
+            "temperature": 0.7,
+            "top_p": 0.9,
+        }
+
+        response = requests.post(api, headers=headers, json=payload)
+
+        # Process API response
+        if response.status_code == 200:
+            response_data = response.json()
+            if 'choices' in response_data:
+                assistant_response = response_data['choices'][0]['message']['content']
+            else:
+                assistant_response = "Response format is incorrect"
+        else:
+            assistant_response = f"API request failed: {response.status_code} - {response.text}"
+
+        # Generate a unique ID for the request
+        unique_id = str(uuid.uuid4())
+
+        # Save the result to MongoDB with the specified format
+        document = {
+            'mrn_number': mrn_number,
+            'ocr_result': assistant_response,  # This will be the OCR/API result
+            'unique_id': unique_id,
+            'got_mode': "plain texts OCR",
+            'timestamp': time.time()
+        }
+
+        collection.insert_one(document)  # Insert the document into MongoDB
+
+        return assistant_response
+    return "Upload your image, enter MRN number, and enter your question."
+
+# Gradio GUI
+iface = gr.Interface(
+    fn=chat_with_pixtral,
+    inputs=[
+        gr.Image(type="pil", label="Upload Your Image"),
+        gr.Textbox(label="Enter MRN Number"),
+        gr.Textbox(label="Please enter your question")
+    ],
+    outputs="text",
+    title="Pixtral Image Chat",
+    description="Upload your Image, enter MRN number, and get insights out of the Image"
+)
+
+iface.launch(share=True)

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

requirements.txt

@@ -0,0 +1,7 @@
+accelerate
+diffusers
+invisible_watermark
+torch
+transformers
+xformers
+pymongo