chore: sync latest readme and docker-compose improvements

Author: sohanmaheshwar

agentic-rag-authorization/README.md

@@ -92,26 +92,19 @@ The agent transparently explains access limitations instead of failing silently.
 ### Steps
 
 ```bash
-# 1. Start services
+# 1. Configure
+cp .env.example .env
+# Edit .env with your actual OpenAI API key
+
+# 2. Start services
 docker-compose up -d
 
-# 2. Install dependencies
+# 3. Install dependencies
 python3 -m venv venv
 source venv/bin/activate
 pip install -r requirements.txt
-
-# 3. Configure
-cp .env.example .env
-# Edit .env with your actual OpenAI API key (never commit .env!)
-
-# 4. Initialize data
-python3 examples/setup_environment.py
-
-# 5. Run demo
-python3 examples/basic_example.py
 ```
 
-
 ## Web UI
 
 A web interface is available to demonstrate the authorization capabilities interactively.
@@ -121,7 +114,7 @@ A web interface is available to demonstrate the authorization capabilities inter
 ```bash
 # 1. Ensure services are running and data is initialized
 docker-compose up -d
-python3 examples/setup_environment.py  # If not already done
+python3 examples/setup_environment.py
 
 # 2. Install web dependencies
 pip install -r requirements.txt  # Includes fastapi and uvicorn
@@ -130,11 +123,29 @@ pip install -r requirements.txt  # Includes fastapi and uvicorn
 python3 run_ui.py
 ```
 
-The launcher will:
-- ✅ Check that Weaviate, SpiceDB, and OpenAI are configured
-- ✅ Verify documents are loaded
-- 🚀 Start the FastAPI server
-- 🌐 Open your browser to http://localhost:8000
+The `setup-environment.py` file sets up Weaviate as the vector DB and SpiceDB with sample documents and department-based access control for the agentic RAG system. 
+
+We're creating a schema and writing relationships for a hierarchical permission model with users assigned to departments, department-wide document access, 3 cross-department collaboration grants, and 3 individual user exceptions.
+
+The UI launcher will:
+- Verify documents are loaded
+- Starts the FastAPI server
+- Open your browser to http://localhost:8000
+
+Here are few sample prompts you can run:
+
+Choose "Bob" from "Sales" as the user and the query as "What are the company handbook guidelines?"
+
+You should see: 
+📊 Retrieved: 5
+✅ Authorized: 3
+❌ Denied: 2
+
+Now run the same query as the "HR Manager". You should see:
+📊 Retrieved: 5
+✅ Authorized: 5
+❌ Denied: 0
+
 
 ### Manual Start
 
@@ -149,6 +160,16 @@ uvicorn api.main:app --reload --host 0.0.0.0 --port 8000
 open http://localhost:8000
 ```
 
+## Run Without UI
+
+```
+# Initialize data
+python3 examples/setup_environment.py
+
+# Run demo
+python3 examples/basic_example.py
+```
+
 ## How It Works
 
 ### 1. Authorization Model (SpiceDB)

agentic-rag-authorization/docker-compose.yml

@@ -1,9 +1,8 @@
----
 version: '3.8'
 
 services:
   weaviate:
-    image: "cr.weaviate.io/semitechnologies/weaviate:latest"
+    image: cr.weaviate.io/semitechnologies/weaviate:latest
     ports:
       - "8080:8080"  # HTTP and gRPC both use this port
     environment:
@@ -13,19 +12,19 @@ services:
       DEFAULT_VECTORIZER_MODULE: 'text2vec-openai'
       ENABLE_MODULES: 'text2vec-openai'
       CLUSTER_HOSTNAME: 'node1'
-      OPENAI_APIKEY: "${OPENAI_API_KEY}"
+      OPENAI_APIKEY: ${OPENAI_API_KEY}
     volumes:
-      - "weaviate_data:/var/lib/weaviate"
+      - weaviate_data:/var/lib/weaviate
     env_file:
-      - ".env"
+      - .env
 
   spicedb:
-    image: "authzed/spicedb:latest"
-    command: "serve --grpc-preshared-key \"devtoken\""
+    image: authzed/spicedb:latest
+    command: serve --grpc-preshared-key "devtoken"
     ports:
       - "50051:50051"
     environment:
-      SPICEDB_DATASTORE_ENGINE: "memory"
+      SPICEDB_DATASTORE_ENGINE: memory
 
 volumes:
   weaviate_data: