add files

.gitattributes

@@ -32,4 +32,4 @@ saved_model/**/* 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
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,11 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+.env

.python-version

@@ -0,0 +1 @@
+3.12

Dockerfile

@@ -0,0 +1,21 @@
+
+FROM python:3.9
+
+# Pehle root user hai by default, to yahan packages install karo
+RUN apt-get update && apt-get install -y libgl1-mesa-glx libglib2.0-0
+
+# Ab user add karo aur switch karo
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+RUN python -m spacy download en_core_web_lg
+RUN python -c "from doctr.models import ocr_predictor; ocr_predictor(pretrained=True)"
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,11 +0,0 @@
----
-title: Text Amon API
-emoji: 📉
-colorFrom: gray
-colorTo: indigo
-sdk: docker
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,48 @@
+from fastapi import FastAPI, UploadFile , File
+from fastapi.middleware.cors import CORSMiddleware
+from agents import Runner
+from reportanalysis import Report_Agent, extract_text
+from logging import getLogger
+
+app = FastAPI()
+log = getLogger()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.get("/")
+async def root():
+    return {"message": "Welcome to the Medical Report Analysis API"}
+
+@app.post("/upload")
+async def upload_file(file: UploadFile = File(...)):
+    try:
+        pdf = file.filename.lower().endswith('.pdf')
+        doc = file.filename.lower().endswith('.docx')
+        content = await file.read()
+        text = extract_text(content, pdf, doc)
+        result = await Runner.run(
+            Report_Agent, 
+           f"""Please analyze the uploaded medical report image extrected text :
+
+{text}
+
+Do not provide any analysis before calling the tool.
+
+Once the text is extracted, continue with step-by-step medical analysis and return the final output strictly in JSON format.
+
+    """,
+    context=content,
+    
+        )
+        print(result.final_output)
+        return {"result": result.final_output.model_dump()}
+    except Exception as e:
+        return {"error": str(e)}
+
+

pyproject.toml

@@ -0,0 +1,22 @@
+[project]
+name = "backend"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "eval-type-backport>=0.2.2",
+    "fastapi[standard]>=0.116.1",
+    "numpy>=2.3.1",
+    "openai-agents>=0.2.3",
+    "pillow>=11.3.0",
+    "presidio-analyzer>=2.2.359",
+    "presidio-anonymizer>=2.2.359",
+    "pypdf2>=3.0.1",
+    "python-doctr>=1.0.0",
+    "python-docx>=1.2.0",
+    "python-dotenv>=1.1.1",
+    "torch>=2.7.1",
+    "torchvision>=0.22.1",
+    "uvicorn>=0.35.0",
+]

reportanalysis.py

@@ -0,0 +1,132 @@
+
+import io
+import re
+import os
+import docx
+from PyPDF2 import PdfReader
+import numpy as np
+from PIL import Image
+from doctr.models import ocr_predictor
+from presidio_analyzer import AnalyzerEngine
+from presidio_anonymizer import AnonymizerEngine
+from dotenv import load_dotenv  
+from pydantic import BaseModel, Field
+from typing import List, Literal
+from agents import (
+        Agent,
+        AsyncOpenAI, 
+	      OpenAIChatCompletionsModel, 
+        AgentOutputSchemaBase,
+        enable_verbose_stdout_logging,
+        set_default_openai_key
+        )
+enable_verbose_stdout_logging()
+
+
+load_dotenv()
+model = ocr_predictor(pretrained=True)
+analyzer = AnalyzerEngine()
+anonymizer = AnonymizerEngine()
+
+API = os.getenv("GEM_API_KEY")
+
+class TestItem(BaseModel):
+    name: str
+    user_value: str
+    normal_range: str
+    analysis: str | None = None
+    flag: Literal["Red", "Yellow", "Green"]
+
+class ReportSection(BaseModel):
+    title: str
+    tests: List[TestItem]
+    section_summary: str
+
+class AiTipSection(BaseModel):
+    title: str
+    risk: str
+    tips: str
+    action: str
+    diet_suggestion: List[str] = Field(default_factory=list)
+    life_style: List[str] = Field(default_factory=list)
+
+class ReportSchema(BaseModel):
+    report_summary_title: str
+    ai_tip_title: str
+    report_sections: List[ReportSection]
+    ai_tip_sections: List[AiTipSection]
+
+client = AsyncOpenAI(
+       api_key = API,
+       base_url = "https://generativelanguage.googleapis.com/v1beta/openai/",
+)
+
+agent_model = OpenAIChatCompletionsModel(
+        model = "gemini-2.0-flash",
+        openai_client = client,
+        
+)
+
+def format_json(result):   
+        analyzer_results = analyzer.analyze(text=result, language='en')
+        anonymized_text = anonymizer.anonymize(text=result, analyzer_results=analyzer_results)
+        result_text = anonymized_text.text
+        pattern = r'(<PERSON>\s+[\w\s\-]+)'
+        hospital_pattern = r'(?i)\b(?:[A-Z][a-zA-Z]+(?:\s+|,|&)?){1,6}(hospital|lab|clinic|diagnostic|medical|centre|pathology)\b'
+        result_text = re.sub(r'[,.()\'"-]', ' ', result_text).strip()
+        result_text = re.sub(pattern, r'<NAME>', result_text)
+        result_text = re.sub(hospital_pattern, r'<HOSPITAL>', result_text,)
+        print(result_text)
+        return result_text
+
+def extract_text(content ,pdf ,doc) -> str:
+        if pdf:
+            reader = PdfReader(io.BytesIO(content))
+            text = ''
+            for page in reader.pages:
+                text += page.extract_text() + '\n'
+            print(text)
+            return text.strip()
+        elif doc:
+            doc = docx.Document(io.BytesIO(content))
+            text = ''
+            for para in doc.paragraphs:
+                text += para.text + '\n'
+            print(text)
+            return text.strip()
+        
+        else:
+          image = Image.open(io.BytesIO(content)).convert("RGB")
+          npImg = np.ascontiguousarray(np.array(image, dtype='uint8'))
+          ORCresult = model([npImg])
+          clean_jason = format_json(ORCresult.render())
+          print(clean_jason)
+          return clean_jason
+
+
+Report_Agent = Agent(
+        name = "Report_Analysis_Agent",
+        instructions = """You are a Medical Report Analysis Agent.
+
+Your role is to analyze uploaded medical test reports and generate clear, accurate health advice in structured JSON format.
+
+Your Main Task:
+1. Analyze the extracted medical text carefully.
+2. Identify each test name, its result (user value), and the normal reference range.
+3. Assign a flag to each test based on the result:
+   - Red: Critical or abnormal
+   - Yellow: Slightly out of range or borderline
+   - Green: Normal or safe
+4. Provide a clear summary of the findings.
+5. Offer relevant AI-driven health tips, highlight potential risks, and suggest dietary and lifestyle improvements.
+
+Return your final response STRICTLY in the JSON structure.
+
+""",
+        model = agent_model,
+        output_type=  ReportSchema,
+)
+
+
+
+

requirements.txt

@@ -0,0 +1,14 @@
+fastapi[standard]
+numpy
+openai-agents
+uvicorn
+pillow
+presidio-analyzer
+presidio-anonymizer
+pypdf2
+python-doctr
+python-docx
+python-dotenv
+eval_type_backport
+torch
+torchvision

runtime.txt

@@ -0,0 +1 @@
+python-3.10.12