rm MongoDB services by AgentDiagram #3

api/README.md

@@ -10,16 +10,15 @@
 - CORS configuration
 - Azure AI Foundry provider settings
 
-### **database.py** - Database Management
-- MongoDB connection management
-- FAISS index lazy loading
+### **database.py** - Runtime Model Management
 - SentenceTransformer model initialization
-- Symptom vectors management
-- GridFS integration
+- Embedding cache/runtime hooks
+- Legacy MongoDB/FAISS startup disabled
+- Compatibility stubs for removed retrieval storage
 
-### **retrieval.py** - RAG Retrieval Engine
-- Medical information retrieval from FAISS
-- Symptom-based diagnosis retrieval
+### **retrieval.py** - Retrieval/Guidance Engine
+- Medical information retrieval interface
+- Symptom-based diagnosis retrieval interface
 - Smart deduplication and similarity matching
 - Vector similarity computations
 - Optional reranking support for guideline-heavy content

api/app.py

@@ -35,13 +35,14 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# ✅ Initialize database connections
+# ✅ Initialize model/runtime dependencies only
 try:
     db_manager.initialize_embedding_model()
-    db_manager.initialize_mongodb()
-    logger.info("✅ Database connections initialized successfully")
+    # Root Cause vs Logic: MongoDB-backed RAG initialization caused startup DNS failures,
+    # so the app now skips that legacy data plane and starts with model/runtime components only.
+    logger.info("✅ Runtime dependencies initialized successfully")
 except Exception as e:
-    logger.error(f"❌ Database initialization failed: {e}")
+    logger.error(f"❌ Runtime initialization failed: {e}")
     raise
 
 # ✅ Include routes

api/database.py

@@ -1,34 +1,20 @@
 # api/database.py
-import faiss
 import numpy as np
-import gridfs
-from pymongo import MongoClient
 from sentence_transformers import SentenceTransformer
-from .config import mongo_uri, index_uri, MODEL_CACHE_DIR, EMBEDDING_MODEL_DEVICE
+from .config import MODEL_CACHE_DIR, EMBEDDING_MODEL_DEVICE
 import logging
 
 logger = logging.getLogger("database-bot")
 
-# Motivation vs Logic: MongoDB access is retained only as a storage/index transport layer
-# for retrieval artifacts; the chatbot runtime should not expose a separate MongoDB RAG service.
+# Root Cause vs Logic: the runtime used to initialize a MongoDB/FAISS RAG data plane at import time,
+# which caused DNS failures when the index cluster was unavailable; the app now keeps only the embedder hook.
 class DatabaseManager:
     def __init__(self):
         self.embedding_model = None
         self.index = None
         self.symptom_vectors = None
         self.symptom_docs = None
-        
-        # MongoDB connections
-        self.client = None
-        self.iclient = None
-        self.symptom_client = None
-        
-        # Collections
-        self.qa_collection = None
-        self.index_collection = None
-        self.symptom_col = None
-        self.fs = None
-        
+
     def initialize_embedding_model(self):
         """Initialize the SentenceTransformer model"""
         logger.info("[Embedder] 📥 Loading SentenceTransformer Model...")
@@ -41,47 +27,20 @@ class DatabaseManager:
             raise
     
     def initialize_mongodb(self):
-        """Initialize MongoDB connections and collections"""
-        # Root Cause vs Logic: the retrieval layer depends on MongoDB only for persisted
-        # artifacts; we keep one initializer here so all collections come from a single path.
-        # QA data
-        self.client = MongoClient(mongo_uri)
-        db = self.client["MedicalChatbotDB"]
-        self.qa_collection = db["qa_data"]
-
-        # FAISS Index data
-        self.iclient = MongoClient(index_uri)
-        idb = self.iclient["MedicalChatbotDB"]
-        self.index_collection = idb["faiss_index_files"]
-
-        # Symptom Diagnosis data
-        self.symptom_client = MongoClient(mongo_uri)
-        self.symptom_col = self.symptom_client["MedicalChatbotDB"]["symptom_diagnosis"]
+        """Compatibility stub for legacy MongoDB-backed retrieval startup."""
+        # Root Cause vs Logic: all MongoDB-backed RAG wiring has been removed from the runtime;
+        # keeping this as a no-op preserves import compatibility without triggering DNS lookups.
+        logger.info("[DB] MongoDB initialization skipped (legacy RAG disabled).")
 
-        # GridFS for FAISS index
-        self.fs = gridfs.GridFS(idb, collection="faiss_index_files")
-    
     def load_faiss_index(self):
-        """Lazy load FAISS index from GridFS"""
-        if self.index is None:
-            logger.info("[KB] ⏳ Loading FAISS index from GridFS...")
-            existing_file = self.fs.find_one({"filename": "faiss_index.bin"})
-            if existing_file:
-                stored_index_bytes = existing_file.read()
-                index_bytes_np = np.frombuffer(stored_index_bytes, dtype='uint8')
-                self.index = faiss.deserialize_index(index_bytes_np)
-                logger.info("[KB] ✅ FAISS Index Loaded")
-            else:
-                logger.error("[KB] ❌ FAISS index not found in GridFS.")
-        return self.index
-    
+        """Legacy FAISS loading disabled."""
+        return None
+
     def load_symptom_vectors(self):
-        """Lazy load symptom vectors for diagnosis"""
-        if self.symptom_vectors is None:
-            all_docs = list(self.symptom_col.find({}, {"embedding": 1, "answer": 1, "question": 1, "prognosis": 1}))
-            self.symptom_docs = all_docs
-            self.symptom_vectors = np.array([doc["embedding"] for doc in all_docs], dtype=np.float32)
-    
+        """Legacy symptom vector loading disabled."""
+        self.symptom_docs = []
+        self.symptom_vectors = np.empty((0, 0), dtype=np.float32)
+
     def get_embedding_model(self):
         """Get the embedding model"""
         if self.embedding_model is None:
@@ -89,16 +48,12 @@ class DatabaseManager:
         return self.embedding_model
     
     def get_qa_collection(self):
-        """Get QA collection"""
-        if self.qa_collection is None:
-            self.initialize_mongodb()
-        return self.qa_collection
-    
+        """Legacy QA collection access disabled."""
+        return None
+
     def get_symptom_collection(self):
-        """Get symptom collection"""
-        if self.symptom_col is None:
-            self.initialize_mongodb()
-        return self.symptom_col
+        """Legacy symptom collection access disabled."""
+        return None
 
 # Global database manager instance
 db_manager = DatabaseManager()

utils/clear_mongo.py

@@ -1,48 +1,7 @@
-from pymongo import MongoClient
-from dotenv import load_dotenv
-import os
+"""Legacy MongoDB cleanup helpers removed with the retired RAG data plane."""
 
-# # Load environment variables from .env
-# load_dotenv()
+# Root Cause vs Logic: this utility existed only to delete MongoDB-hosted QA/FAISS artifacts,
+# so the live code path is intentionally replaced with a harmless stub to avoid accidental use.
 
-##-------------##
-# FOR QA CLUSTER
-##-------------##
-
-# mongo_uri = os.getenv("MONGO_URI")
-# if not mongo_uri:
-#     raise ValueError("❌ MongoDB URI (MongoURI) is missing!")
-
-# client = MongoClient(mongo_uri)
-# db = client["MedicalChatbotDB"]  # Use the same database name as in your main script
-
-# # To drop just the collection storing the FAISS index:
-# db.drop_collection("qa_data")
-# print("Dropped collection 'qa_data' from MedicalChatbotDB.")
-
-# # Alternatively, to drop the entire database:
-# client.drop_database("MedicalChatbotDB")
-# print("Dropped database 'MedicalChatbotDB'.")
-
-
-##-------------##
-# FOR INDEX CLUSTER
-##-------------##
-
-# Load environment variables from .env
-# load_dotenv()
-# index_uri = os.getenv("INDEX_URI")
-# if not index_uri:
-#     raise ValueError("❌ MongoDB URI (IndexURI) is missing!")
-
-# iclient = MongoClient(index_uri)
-# idb = iclient["MedicalChatbotDB"]  # Use the same database name as in your main script
-
-# # To drop just the collection storing the FAISS index:
-# idb.drop_collection("faiss_index_files.files")
-# idb.drop_collection("faiss_index_files.chunks")
-# print("Dropped collection 'faiss_index_files' and chunks from MedicalChatbotDB.")
-
-# # Alternatively, to drop the entire database:
-# iclient.drop_database("MedicalChatbotDB")
-# print("Dropped database 'MedicalChatbotDB'.")
+def __getattr__(name):
+    raise AttributeError(f"legacy cleanup utility disabled: {name}")