diff --git a/store-all/api/Dockerfile b/store-all/api/Dockerfile
new file mode 100644
index 0000000..207addb
--- /dev/null
+++ b/store-all/api/Dockerfile
@@ -0,0 +1,6 @@
+FROM python:3.9-slim
+WORKDIR /usr/src/app
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+CMD ["python", "app.py"]
diff --git a/store-all/api/app.py b/store-all/api/app.py
new file mode 100644
index 0000000..68bb8b7
--- /dev/null
+++ b/store-all/api/app.py
@@ -0,0 +1,30 @@
+from flask import Flask, jsonify, request
+from neo4j import GraphDatabase
+from pymilvus import connections, Collection
+
+app = Flask(__name__)
+
+# Neo4j Connection
+neo4j_driver = GraphDatabase.driver("bolt://neo4j:7687", auth=("neo4j", "testpassword"))
+
+# Milvus Connection
+connections.connect("default", host="milvus", port="19530")
+
+@app.route('/')
+def home():
+    return jsonify({'message': 'Hello, World!'})
+
+@app.route('/neo4j_test')
+def neo4j_test():
+    with neo4j_driver.session() as session:
+        result = session.run("MATCH (n) RETURN count(n) AS count")
+        count = result.single()["count"]
+    return jsonify({'neo4j_node_count': count})
+
+@app.route('/milvus_test')
+def milvus_test():
+    collections = Collection.list()
+    return jsonify({'milvus_collections': collections})
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5000)
diff --git a/store-all/api/requirements.txt b/store-all/api/requirements.txt
new file mode 100644
index 0000000..907fa4d
--- /dev/null
+++ b/store-all/api/requirements.txt
@@ -0,0 +1,4 @@
+Flask==2.0.3
+neo4j==4.4.1
+pymilvus==2.0.2
+gunicorn==20.1.0
diff --git a/store-all/docker-compose.yml b/store-all/docker-compose.yml
new file mode 100644
index 0000000..25aa22f
--- /dev/null
+++ b/store-all/docker-compose.yml
@@ -0,0 +1,45 @@
+version: '3.8'
+
+services:
+  neo4j:
+    image: neo4j:latest
+    container_name: neo4j
+    ports:
+      - "7474:7474" # HTTP
+      - "7687:7687" # Bolt
+    volumes:
+      - ./neo4j/data:/data
+      - ./neo4j/logs:/logs
+      - ./neo4j/import:/var/lib/neo4j/import
+      - ./neo4j/plugins:/plugins
+    environment:
+      NEO4J_AUTH: neo4j/testpassword
+
+  milvus:
+    image: milvusdb/milvus:v2.0.0
+    container_name: milvus
+    ports:
+      - "19530:19530" # Milvus default port
+    volumes:
+      - ./milvus/db:/var/lib/milvus/db
+      - ./milvus/conf:/var/lib/milvus/conf
+      - ./milvus/logs:/var/lib/milvus/logs
+    environment:
+      TZ: UTC
+
+  api:
+    build: ./api
+    container_name: api
+    ports:
+      - "5000:5000"
+    volumes:
+      - ./api:/usr/src/app
+    depends_on:
+      - neo4j
+      - milvus
+    environment:
+      NEO4J_URI: bolt://neo4j:7687
+      NEO4J_USER: neo4j
+      NEO4J_PASSWORD: testpassword
+      MILVUS_HOST: milvus
+      MILVUS_PORT: 19530
diff --git a/store-all/story.md b/store-all/story.md
new file mode 100644
index 0000000..dcad1e6
--- /dev/null
+++ b/store-all/story.md
@@ -0,0 +1,21 @@
+<!-- Graph Database -->
+
+
+Rich Relationships: Graph databases excel at managing highly interconnected data, allowing you to efficiently model, store, and query complex networks of relationships.
+
+Performance: They are optimized for traversing complex relationships and can perform deep queries very fast, unlike traditional databases where join-intensive queries can be slow.
+
+Flexibility: They typically allow for schema-less or schema-flexible data, making them adaptable to evolving data models without significant redesign.
+
+Intuitive Query Language: Many graph databases use query languages like Cypher (Neo4j), which are powerful yet readable, making complex queries more straightforward to construct and understand.
+
+Cons:
+
+Scalability: Horizontal scaling can be challenging with graph databases, as they are inherently designed for deep, computationally intense traversals.
+
+Specialized Knowledge: The need for understanding specific query languages and graph theory can steepen the learning curve.
+
+Resource Intensity: Maintaining high-performance levels, especially with very large datasets, can require significant computational resources.
+
+
+Python is widely adopted in the data science community, offering extensive libraries and frameworks for both graph databases (like py2neo for Neo4j) and vector databases (like milvus-py for Milvus). It’s particularly strong in analytics, machine learning, and AI, which aligns well with the use cases of vector databases.
\ No newline at end of file