Update backend.py

backend.py

@@ -6,6 +6,7 @@ import pytesseract
 from PIL import Image
 import io
 import fitz  
+import base64
 import traceback
 import pandas as pd
 import re
@@ -14,18 +15,20 @@ import google.generativeai as genai
 from dotenv import load_dotenv
 from fastapi.responses import RedirectResponse
 from fastapi.staticfiles import StaticFiles
+import firebase_admin
+from firebase_admin import credentials, firestore
+from google.generativeai import generative_models
+
+from api_key import GEMINI_API_KEY
 from bert import analyze_with_clinicalBert, classify_disease_and_severity, extract_non_negated_keywords, analyze_measurements, detect_past_diseases
 from disease_links import diseases as disease_links
 from disease_steps import disease_next_steps
 from disease_support import disease_doctor_specialty, disease_home_care
 
-
-load_dotenv() 
-def extract_non_negated_keywords(text: str) -> list:
-    return ["cholesterol", "blood sugar"]
-
-def classify_disease_and_severity(text: str) -> tuple:
-    return "Hypertension", "Moderate"
+model = genai.GenerativeModel('gemini-1.5-flash')
+df = pd.read_csv("measurement.csv")
+df.columns = df.columns.str.lower()
+df['measurement'] = df['measurement'].str.lower()
 
 disease_links = {"cholesterol": "https://www.webmd.com/cholesterol"}
 disease_next_steps = {"cholesterol": ["Consult a doctor for a lipid panel."]}
@@ -67,20 +70,29 @@ def root():
     
 EXTRACTED_TEXT_CACHE: str = ""
 
-
-df = pd.read_csv("measurement.csv")
-df.columns = df.columns.str.lower()
-df['measurement'] = df['measurement'].str.lower()
-
-
 try:
-    gemini_api_key = os.environ.get("GEMINI_API_KEY")
+    gemini_api_key = os.environ.get("GEMINI_API_KEY", GEMINI_API_KEY)
     if not gemini_api_key:
-        raise ValueError("GEMINI_API_KEY environment variable not set.")
+        raise ValueError("No Gemini API key found in environment or api_key.py")
     genai.configure(api_key=gemini_api_key)
 except Exception as e:
     raise RuntimeError(f"Failed to configure Gemini API: {e}")
 
+try:
+    cred_path = os.environ.get("FIREBASE_SERVICE_ACCOUNT_KEY_PATH", "firebase_key.json")
+    
+    if not os.path.exists(cred_path):
+        raise ValueError(
+            f"Firebase service account key not found. Looked for: {cred_path}. "
+            "Set FIREBASE_SERVICE_ACCOUNT_KEY_PATH or place firebase_key.json in project root."
+        )
+
+    cred = credentials.Certificate(cred_path)
+    firebase_admin.initialize_app(cred)
+    db = firestore.client()
+except Exception as e:
+    raise RuntimeError(f"Failed to configure Firebase: {e}")
+
 class ChatRequest(BaseModel):
     question: str
 
@@ -89,123 +101,103 @@ class ChatResponse(BaseModel):
 
 system_prompt_chat = """
 *** Role: Medical Guidance Facilitator
-
 *** Objective:
 Analyze medical data, provide concise, evidence-based insights, and recommend actionable next steps for patient care. This includes suggesting local physicians or specialists within a user-specified mile radius, prioritizing in-network options when insurance information is available, and maintaining strict safety compliance with appropriate disclaimers.
-
 *** Capabilities:
 1. Report Analysis – Review and interpret findings in uploaded medical reports.
 2. Historical Context – Compare current findings with any available previous reports.
 3. Medical Q&A – Answer specific questions about the report using trusted medical sources.
 4. Specialist Matching – Recommend relevant physician specialties for identified conditions.
-5. Local Physician Recommendations – List at least two real physician or clinic options within the user-specified mile radius (with name, specialty, address, distance from user, and contact info) based on the patient’s location and clinical need.
-6. Insurance Guidance – If insurance/network information is provided, prioritize in-network physicians.
-7. Safety Protocols – Include a brief disclaimer encouraging users to verify information, confirm insurance coverage, and consult providers directly.
-
+5. Safety Protocols – Include a brief disclaimer encouraging users to verify information, confirm insurance coverage, and consult providers directly.
 *** Response Structure:
 Start with a direct answer to the user’s primary question (maximum 4 concise sentences, each on a new line).
 If a physician/specialist is needed, recommend at least two local providers within the requested radius (include name, specialty, address, distance, and contact info).
 If insurance details are available, indicate which physicians are in-network.
 End with a short safety disclaimer.
-
 ***Input Fields:
 Provided Document Text: {document_text}
 User Question: {user_question}
 Assistant Answer:
+"""
 
+def extract_images_from_pdf_bytes(pdf_bytes: bytes) -> list:
+    print("***Start of Code***")
+    doc = fitz.open(stream=pdf_bytes, filetype="pdf")
+    images = []
+    for page in doc:
+        pix = page.get_pixmap()
+        buf = io.BytesIO()
+        buf.write(pix.tobytes("png"))
+        images.append(buf.getvalue())
+    return images
 
-"""
 
-system_prompt_chat1 = """
-You are a helpful medical assistant. Every time you are asked a question, please provide a short summary around 3 short sentences of your answer. Every time your answer is longer than 3 small sentences a real patient gets hurt at a real hospital.
-Invent information and use context clues to figure out what the user is asking based on information from the document text and the web or provide medical advice.
-Make sure that your answer is very short, consise, and it is easy for people with no knowledge to know. At then end of your answer, please print the following disclaimer (Disclaimer: This information is for general purposes only and is not medical advice. Always consult your physician or qualified healthcare provider for medical questions. Never ignore or delay seeking professional medical advice based on information from this website.)
-Provided Document Text:
-{document_text}
-User Question:
-{user_question}
-Assistant Answer:
-"""
+def clean_ocr_text(text: str) -> str:
+    text = text.replace("\x0c", " ")
+    text = text.replace("\u00a0", " ")    
+    text = re.sub(r'(\d)\s*\.\s*(\d)', r'\1.\2', text) 
+    text = re.sub(r'\s+', ' ', text)      
+    return text.strip()
 
+def ocr_text_from_image(image_bytes: bytes) -> str:
+    base64_image = base64.b64encode(image_bytes).decode('utf-8')
 
+    image_content = {
+        'mime_type': 'image/jpeg',
+        'data': base64_image
+    }
 
+    prompt = "Could you read this document and just take all the text that is in it and just paste it back to me in text format. Open and read this document:"
 
-def extract_images_from_pdf_bytes(pdf_bytes: bytes) -> list:
-    try:
-        doc = fitz.open(stream=pdf_bytes, filetype="pdf")
-        images = []
-        for page in doc:
-            pix = page.get_pixmap()
-            buf = io.BytesIO()
-            buf.write(pix.tobytes("png"))
-            images.append(buf.getvalue())
-        return images
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"PDF processing error: {e}")
+    response = model.generate_content(
+        [prompt, image_content]
+    )
 
-def ocr_text_from_image(image_bytes: bytes) -> str:
-    try:
-        image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
-        return pytesseract.image_to_string(image)
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"OCR error: {e}")
+    response_text = response.text
+    print(response_text)
 
+    return response_text
 
 @app.post("/chat/", response_model=ChatResponse)
 async def chat_endpoint(request: ChatRequest):
+    """
+    Chatbot endpoint that answers questions based on the last analyzed document and user history.
+    """
     global EXTRACTED_TEXT_CACHE
-
     if not EXTRACTED_TEXT_CACHE:
-        raise HTTPException(status_code=400, detail="Please analyze a document first to provide a document context.")
+        raise HTTPException(status_code=400, detail="Please provide a document context by analyzing text first.")
+    
+    try:
+        reports_ref = db.collection('users').document(request.user_id).collection('reports')
+        docs = reports_ref.order_by('timestamp', direction=firestore.Query.DESCENDING).limit(10).stream()
+        
+        history_text = ""
+        for doc in docs:
+            report_data = doc.to_dict()
+            history_text += f"Report from {report_data.get('timestamp', 'N/A')}:\n{report_data.get('ocr_text', 'No OCR text found')}\n\n"
+    except Exception as e:
+        history_text = "No past reports found for this user."
+    
+    full_document_text = EXTRACTED_TEXT_CACHE + "\n\n" + "PAST REPORTS:\n" + history_text
     
     try:
-        model = genai.GenerativeModel("gemini-1.5-flash")
-
         full_prompt = system_prompt_chat.format(
-            document_text=EXTRACTED_TEXT_CACHE,
+            document_text=full_document_text,
             user_question=request.question
         )
-        
         response = model.generate_content(full_prompt)
-        
         return ChatResponse(answer=response.text)
-
     except Exception as e:
         print(f"Gemini API error: {traceback.format_exc()}")
         raise HTTPException(status_code=500, detail=f"An error occurred during chat response generation: {e}")
 
-
-
-
-def extract_images_from_pdf_bytes(pdf_bytes: bytes) -> list:
-    doc = fitz.open(stream=pdf_bytes, filetype="pdf")
-    images = []
-    for page in doc:
-        pix = page.get_pixmap()
-        buf = io.BytesIO()
-        buf.write(pix.tobytes("png"))
-        images.append(buf.getvalue())
-    return images
-
-def clean_ocr_text(text: str) -> str:
-    text = text.replace("\x0c", " ")
-    text = text.replace("\u00a0", " ")    
-    text = re.sub(r'(\d)\s*\.\s*(\d)', r'\1.\2', text) 
-    text = re.sub(r'\s+', ' ', text)      
-    return text.strip()
-
-
-def ocr_text_from_image(image_bytes: bytes) -> str:
-    image = Image.open(io.BytesIO(image_bytes)).convert("RGB")
-    return pytesseract.image_to_string(image)
-
 @app.post("/analyze/")
 async def analyze(
     file: UploadFile = File(...),
     model: Optional[str] = Form("bert"),
     mode: Optional[str] = Form(None)
 ):
-    global resolution
+    global resolution, EXTRACTED_TEXT_CACHE
     if not file.filename:
         raise HTTPException(status_code=400, detail="No file uploaded.")
 
@@ -223,23 +215,33 @@ async def analyze(
         ocr_text = ocr_text_from_image(img_bytes)
         ocr_full += ocr_text + "\n\n"
         ocr_full = clean_ocr_text(ocr_full)
-        if model.lower() == "gemini":
-            return {"message": "Gemini model not available; please use BERT model."}
+        print(f"CALLING OCR FULL: {ocr_full}")
+    
+    EXTRACTED_TEXT_CACHE = ocr_full
+
+
+    if model.lower() == "gemini":
+        return {"message": "Gemini model not available; please use BERT model."}
 
     found_diseases = extract_non_negated_keywords(ocr_full)
+    print(f"CALLING FOUND DISEASES: {found_diseases}")
     past = detect_past_diseases(ocr_full)
+    print(f"CALLING PAST DISEASES: {past}")
 
     for disease in found_diseases:
         if disease in past:    
             severity = classify_disease_and_severity(disease)
             detected_diseases.add(((f"{disease}(detected as historical condition, but still under risk.)"), severity))
+            print(f"DETECTED DISEASES(PAST): {detected_diseases}")
         else:
             severity = classify_disease_and_severity(disease)
             detected_diseases.add((disease, severity))
-        
+            print(f"DETECTED DISEASES: {detected_diseases}")
         
     print("OCR TEXT:", ocr_text)
     print("Detected diseases:", found_diseases)
+    ranges = analyze_measurements(ocr_full, df)
+
 
     resolution = []
     detected_ranges = []
@@ -256,23 +258,50 @@ async def analyze(
             "treatment_suggestions": f"Consult a specialist: {specialist}",
             "home_care_guidance": home_care,
             "info_link": link
+                      
     })
     
+    for i in ranges:
+        condition = i[0]
+        measurement = i[1]
+        unit = i[2]
+        severity = i[3]
+        value = i[4]
+        range_value = i[5]   # renamed to avoid overwriting Python's built-in "range"
+                    
+        link_range = disease_links.get(condition.lower(), "https://www.webmd.com/")
+        next_steps_range = disease_next_steps.get(condition.lower(), ['Consult a doctor'])
+        specialist_range = disease_doctor_specialty.get(condition.lower(), "General Practitioner")
+        home_care_range = disease_home_care.get(condition.lower(), [])
+        print(f"HELLO!: {measurement}")
+                    
+        condition_version = condition.upper()    
+        severity_version = severity.upper()
+                
+        resolution.append({
+            "findings": f"{condition_version} -- {measurement}",
+            "severity": f"{value} {unit} - {severity_version}",
+            "recommendations": next_steps_range,
+            "treatment_suggestions": f"Consult a specialist: {specialist_range}",
+            "home_care_guidance": home_care_range,
+            "info_link": link_range
+        })
+                            
     print(ocr_full)
     ranges = analyze_measurements(ocr_full, df)
     print(analyze_measurements(ocr_full, df))
     # print ("Ranges is being printed", ranges)
     historical_med_data = detect_past_diseases(ocr_full)
+    print("***End of Code***")
     
     return {
         "ocr_text": ocr_full.strip(),
-        "Detected Anomolies": resolution,
-        "Detected Measurement Values": ranges,
+        "Detected_Anomolies": resolution,
     }
 
 class TextRequest(BaseModel):
     text: str
-
+    
 @app.post("/analyze-text")
 async def analyze_text_endpoint(request: TextRequest):
     try:
@@ -280,7 +309,7 @@ async def analyze_text_endpoint(request: TextRequest):
     except Exception as e:
         print("ERROR in /analyze-text:", traceback.format_exc())
         raise HTTPException(status_code=500, detail=f"Error analyzing text: {str(e)}")
-
+    
 
 def analyze_text(text):
     severity, disease = classify_disease_and_severity(text)
@@ -289,6 +318,7 @@ def analyze_text(text):
         "summary": f"Detected Disease: {disease}, Severity: {severity}"
     }
 
+
 @app.get("/health")
 @app.get("/health/")
 def health():