fixed :changed everything config

config.py

@@ -13,3 +13,33 @@ class Config:
     REPO_ID_LANG = os.getenv("English_model") or "Pujan-Dev/Ai_vs_HUMAN"
     LANG_MODEL = os.getenv("LANG_MODEL")
     HF_TOKEN = os.getenv("HF_TOKEN") or os.getenv("HUGGINGFACE_TOKEN")
+    SECRET_TOKEN = os.getenv("MY_SECRET_TOKEN")
+
+    IMAGE_CLASSIFIER_REPO_ID = os.getenv("IMAGE_CLASSIFIER_REPO_ID", "can-org/AI-VS-HUMAN-IMAGE-classifier")
+    IMAGE_CLASSIFIER_MODEL_DIR = os.getenv("IMAGE_CLASSIFIER_MODEL_DIR", "./IMG_Models")
+    IMAGE_CLASSIFIER_WEIGHTS_FILE = os.getenv("IMAGE_CLASSIFIER_WEIGHTS_FILE", "latest-my_cnn_model.h5")
+
+    AI_HUMAN_CLIP_MODEL_NAME = os.getenv("AI_HUMAN_CLIP_MODEL_NAME", "ViT-L/14")
+    AI_HUMAN_SVM_REPO_ID = os.getenv("AI_HUMAN_SVM_REPO_ID", "rhnsa/ai_human_image_detector")
+    AI_HUMAN_SVM_FILENAME = os.getenv("AI_HUMAN_SVM_FILENAME", "svm_model_real.joblib")
+
+    REAL_FORGED_MODEL_REPO_ID = os.getenv("REAL_FORGED_MODEL_REPO_ID", "rhnsa/real_forged_classifier")
+    REAL_FORGED_MODEL_FILENAME = os.getenv("REAL_FORGED_MODEL_FILENAME", "fft_cnn_model_78.pth")
+
+    RAG_CHROMA_HOST = os.getenv("CHROMA_HOST", "localhost")
+    RAG_CHROMA_PORT = int(os.getenv("CHROMA_PORT", "8000"))
+    RAG_COLLECTION_NAME = os.getenv("RAG_COLLECTION_NAME", "company_docs_collection")
+
+    RAG_LLM_PROVIDER = os.getenv("LLM_PROVIDER", "openai").lower()
+    RAG_LLM_API_KEY = os.getenv("LLM_API_KEY")
+    RAG_LLM_MODEL = os.getenv("LLM_MODEL", "gpt-3.5-turbo")
+    RAG_LLM_TEMPERATURE = float(os.getenv("LLM_TEMPERATURE", "0"))
+    RAG_LLM_MAX_TOKENS = int(os.getenv("LLM_MAX_TOKENS", "2048"))
+
+    RAG_MAX_FILE_SIZE = int(os.getenv("RAG_MAX_FILE_SIZE", str(100 * 1024 * 1024)))
+    RAG_MAX_QUERY_LENGTH = int(os.getenv("RAG_MAX_QUERY_LENGTH", "1000"))
+    RAG_SUPPORTED_CONTENT_TYPES = {
+        "application/pdf",
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+        "text/plain",
+    }

features/ai_human_image_classifier/model_loader.py

@@ -69,9 +69,9 @@ class ModelLoader:
 
 # --- Global Model Instance ---
 # This creates a single instance of the models that can be imported by other modules.
-CLIP_MODEL_NAME = 'ViT-L/14'
-SVM_REPO_ID = 'rhnsa/ai_human_image_detector'
-SVM_FILENAME = 'svm_model_real.joblib' # The name of your model file in the Hugging Face repo
+CLIP_MODEL_NAME = Config.AI_HUMAN_CLIP_MODEL_NAME
+SVM_REPO_ID = Config.AI_HUMAN_SVM_REPO_ID
+SVM_FILENAME = Config.AI_HUMAN_SVM_FILENAME
 
 # This instance will be created when the application starts.
 models = ModelLoader(

features/image_classifier/model_loader.py

@@ -4,12 +4,13 @@ import logging
 import tensorflow as tf
 from tensorflow.keras.layers import Layer
 from huggingface_hub import snapshot_download
+from config import Config
 
 # Model config
-REPO_ID = "can-org/AI-VS-HUMAN-IMAGE-classifier"
-MODEL_DIR = "./IMG_Models"
-WEIGHTS_PATH = os.path.join(MODEL_DIR, "latest-my_cnn_model.h5")
-HF_TOKEN = os.getenv("HF_TOKEN") or os.getenv("HUGGINGFACE_TOKEN")
+REPO_ID = Config.IMAGE_CLASSIFIER_REPO_ID
+MODEL_DIR = Config.IMAGE_CLASSIFIER_MODEL_DIR
+WEIGHTS_PATH = os.path.join(MODEL_DIR, Config.IMAGE_CLASSIFIER_WEIGHTS_FILE)
+HF_TOKEN = Config.HF_TOKEN
 
 # Device info (for logging)
 gpus = tf.config.list_physical_devices("GPU")

features/image_edit_detector/controller.py

@@ -7,8 +7,9 @@ from .detectors.ela import run_ela
 from .preprocess import preprocess_image
 from fastapi import HTTPException,status,Depends
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
+from config import Config
 security=HTTPBearer()
-import os
+
 async def process_image_ela(image_bytes: bytes, quality: int=90):
     image = Image.open(io.BytesIO(image_bytes))
 
@@ -40,7 +41,7 @@ async def process_meta_image(image_bytes: bytes) -> dict:
 
 async def verify_token(credentials: HTTPAuthorizationCredentials = Depends(security)):
     token = credentials.credentials
-    expected_token = os.getenv("MY_SECRET_TOKEN")
+    expected_token = Config.SECRET_TOKEN
     if token != expected_token:
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN,

features/nepali_text_classifier/controller.py

@@ -3,7 +3,7 @@ import logging
 from io import BytesIO
 from fastapi import HTTPException, UploadFile, status, Depends
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
-import os
+from config import Config
 from features.nepali_text_classifier.inferencer import classify_text
 from  features.nepali_text_classifier.preprocess import *
 import re
@@ -25,7 +25,7 @@ def contains_english(text: str) -> bool:
 
 async def verify_token(credentials: HTTPAuthorizationCredentials = Depends(security)):
     token = credentials.credentials
-    expected_token = os.getenv("MY_SECRET_TOKEN")
+    expected_token = Config.SECRET_TOKEN
     if token != expected_token:
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN,

features/rag_chatbot/controller.py

@@ -1,11 +1,10 @@
-import os
 import asyncio
 import logging
-from io import BytesIO
 from typing import Dict, Any
 
 from fastapi import HTTPException, UploadFile, status, Depends
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
+from config import Config
 
 from .rag_pipeline import route_and_process_query, add_document_to_rag, check_system_health
 from .document_handler import extract_text_from_file
@@ -17,18 +16,15 @@ logger = logging.getLogger(__name__)
 security = HTTPBearer()
 
 # Supported file types
-SUPPORTED_CONTENT_TYPES = {
-    "application/pdf",
-    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-    "text/plain"
-}
+SUPPORTED_CONTENT_TYPES = Config.RAG_SUPPORTED_CONTENT_TYPES
 
-MAX_FILE_SIZE = 100 * 1024 * 1024  # 100MB
+MAX_FILE_SIZE = Config.RAG_MAX_FILE_SIZE
+MAX_QUERY_LENGTH = Config.RAG_MAX_QUERY_LENGTH
 
 async def verify_token(credentials: HTTPAuthorizationCredentials = Depends(security)):
     """Verify Bearer token from Authorization header."""
     token = credentials.credentials
-    expected_token = os.getenv("MY_SECRET_TOKEN")
+    expected_token = Config.SECRET_TOKEN
     
     if not expected_token:
         logger.error("MY_SECRET_TOKEN not configured")
@@ -55,10 +51,10 @@ async def handle_rag_query(query: str) -> Dict[str, Any]:
             detail="Query cannot be empty"
         )
     
-    if len(query) > 1000:  # Reasonable limit
+    if len(query) > MAX_QUERY_LENGTH:
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
-            detail="Query too long. Please limit to 1000 characters."
+            detail=f"Query too long. Please limit to {MAX_QUERY_LENGTH} characters."
         )
     
     try:

features/rag_chatbot/rag_pipeline.py

@@ -10,20 +10,22 @@ from langchain_community.vectorstores import Chroma
 from langchain.chains import LLMChain
 from langchain.prompts import PromptTemplate
 from langchain.chat_models import ChatOpenAI
+from config import Config
 
 
 load_dotenv()
 
 # ChromaDB configuration
-CHROMA_HOST = os.getenv("CHROMA_HOST", "localhost") # change in env in production when hosted
-COLLECTION_NAME = "company_docs_collection"
+CHROMA_HOST = Config.RAG_CHROMA_HOST
+CHROMA_PORT = Config.RAG_CHROMA_PORT
+COLLECTION_NAME = Config.RAG_COLLECTION_NAME
 
 # LLM Provider Configuration
-LLM_PROVIDER = os.getenv("LLM_PROVIDER", "openai").lower()  
-LLM_API_KEY = os.getenv("LLM_API_KEY")
-LLM_MODEL = os.getenv("LLM_MODEL", "gpt-3.5-turbo")
-LLM_TEMPERATURE = float(os.getenv("LLM_TEMPERATURE", "0"))
-LLM_MAX_TOKENS = int(os.getenv("LLM_MAX_TOKENS", "2048"))
+LLM_PROVIDER = Config.RAG_LLM_PROVIDER
+LLM_API_KEY = Config.RAG_LLM_API_KEY
+LLM_MODEL = Config.RAG_LLM_MODEL
+LLM_TEMPERATURE = Config.RAG_LLM_TEMPERATURE
+LLM_MAX_TOKENS = Config.RAG_LLM_MAX_TOKENS
 
 # Provider-specific configurations
 PROVIDER_CONFIGS = {
@@ -93,7 +95,7 @@ def initialize_pipelines():
         
         # Initialize ChromaDB client 
         try:
-            chroma_client = chromadb.HttpClient(host=CHROMA_HOST, port=8000)
+            chroma_client = chromadb.HttpClient(host=CHROMA_HOST, port=CHROMA_PORT)
             chroma_client.heartbeat()
         except Exception as e:
             raise ConnectionError("Failed to connect to ChromaDB.") from e

features/rag_chatbot/routes.py

@@ -4,7 +4,7 @@ from pydantic import BaseModel, Field
 from slowapi.util import get_remote_address
 from slowapi import Limiter
 from typing import Optional
-from config import ACCESS_RATE
+from config import ACCESS_RATE, Config
 from .controller import (
     handle_rag_query,
     handle_document_upload,
@@ -101,11 +101,7 @@ async def get_system_info(request: Request):
             "Cybersecurity knowledge and best practices",
             "Document upload and processing (PDF, DOCX, TXT)"
         ],
-        "supported_file_types": [
-            "application/pdf",
-            "application/vnd.openxmlformats-officedocument.wordprocessingml.document", 
-            "text/plain"
-        ],
-        "max_file_size_mb": 10,
-        "max_query_length": 1000
+        "supported_file_types": sorted(Config.RAG_SUPPORTED_CONTENT_TYPES),
+        "max_file_size_mb": round(Config.RAG_MAX_FILE_SIZE / (1024 * 1024), 2),
+        "max_query_length": Config.RAG_MAX_QUERY_LENGTH
     }

features/real_forged_classifier/model_loader.py

@@ -55,7 +55,7 @@ class ModelLoader:
             raise
 
 # --- Global Model Instance ---
-MODEL_REPO_ID = 'rhnsa/real_forged_classifier' 
-MODEL_FILENAME = 'fft_cnn_model_78.pth'
+MODEL_REPO_ID = Config.REAL_FORGED_MODEL_REPO_ID
+MODEL_FILENAME = Config.REAL_FORGED_MODEL_FILENAME
 models = ModelLoader(model_repo_id=MODEL_REPO_ID, model_filename=MODEL_FILENAME)
 

features/text_classifier/controller.py

@@ -1,10 +1,10 @@
 import asyncio
 import logging
-import os
 from io import BytesIO
 
 from fastapi import Depends, HTTPException, UploadFile, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
+from config import Config
 
 from .inferencer import analyze_text_with_sentences, classify_text
 from .preprocess import parse_docx, parse_pdf, parse_txt
@@ -33,7 +33,7 @@ def build_bias_summary(ai_likelihood: float) -> dict[str, object]:
 # Verify Bearer token from Authorization header
 async def verify_token(credentials: HTTPAuthorizationCredentials = Depends(security)):
     token = credentials.credentials
-    expected_token = os.getenv("MY_SECRET_TOKEN")
+    expected_token = Config.SECRET_TOKEN
     if token != expected_token:
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN, detail="Invalid or expired token"