chore: code cleanup, add .env.example, update README

.env .example

@@ -0,0 +1,4 @@
+MODEL_PATH=./models/merged/exp2_lr2e-4_r16
+PINECONE_API_KEY=your_pinecone_api_key_here
+PINECONE_INDEX=llmops-rag
+EMBED_MODEL=sentence-transformers/all-MiniLM-L6-v2

README.MD

@@ -17,7 +17,7 @@ Most LLM projects stop at inference. This one goes further:
 - **Serving layer** — FastAPI with async lifespan model loading, typed Pydantic request/response models, CORS, health check, and a clean browser UI served from the same process
 - **Containerized** — Dockerfile built for slim Python 3.12, model loaded at runtime via env-configurable path (not baked in)
 - **Cloud-ready** — One-shot Azure deployment via ACR + Container Apps, with Pinecone key injected as a secret
-- **Intelligence-area** — Trained a personalized Corpus with Genshin Impact Game's Vast Lore and Character Builds
+- **Domain knowledge** — RAG corpus built around Genshin Impact lore, character builds, and elemental mechanics, serving as a rich real-world knowledge base for retrieval evaluation
 
 ---
 

embedder.py

@@ -1,6 +1,7 @@
-from sentence_transformers import SentenceTransformer
 import os
 
+from sentence_transformers import SentenceTransformer
+
 EMBED_MODEL = os.getenv("EMBED_MODEL", "sentence-transformers/all-MiniLM-L6-v2")
 
 _model = None

ingest.py

@@ -11,7 +11,9 @@ import uuid
 import argparse
 import logging
 from pathlib import Path
+
 from dotenv import load_dotenv 
+
 load_dotenv()                  
 
 from pinecone import Pinecone, ServerlessSpec

main.py

@@ -10,7 +10,8 @@ from rag import RAGChain
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-rag_chain: RAGChain = None
+from typing import Optional
+rag_chain: Optional[RAGChain] = None
 
 
 @asynccontextmanager

pyvenv.cfg

@@ -0,0 +1,5 @@
+home = C:\Users\mukul\AppData\Local\Programs\Python\Python312
+include-system-site-packages = false
+version = 3.12.9
+executable = C:\Users\mukul\AppData\Local\Programs\Python\Python312\python.exe
+command = C:\Users\mukul\AppData\Local\Programs\Python\Python312\python.exe -m venv E:\Projects\llmops-serve\venv

rag.py

@@ -1,5 +1,6 @@
 import os
 import logging
+
 import torch
 from dotenv import load_dotenv
 
@@ -72,7 +73,6 @@ class RAGChain:
             return_full_text=False,
             eos_token_id=tokenizer.eos_token_id,
             pad_token_id=tokenizer.eos_token_id,
-        
         )
         llm = HuggingFacePipeline(pipeline=hf_pipe)
         logger.info("Model loaded.")