diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..7f079ce
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+/ollama
+/venv
diff --git a/app.py b/app.py
new file mode 100644
index 0000000..00a842d
--- /dev/null
+++ b/app.py
@@ -0,0 +1,22 @@
+import requests
+import gradio as gr
+
+def ask(text):
+    url = "http://localhost:7869/           "
+    payload = {"text": text}
+    response = requests.post(url, json=payload)
+    
+    if response.status_code == 200:
+        return response.json().get("response", "No response from API")
+    else:
+        return f"Error: {response.status_code}"
+
+with gr.Blocks() as server:
+    with gr.Tab("LLM Inferencing"):
+        input_text = gr.Textbox(label="Input Text", placeholder="Enter your text here...")
+        output_text = gr.Textbox(label="Output Text")
+        submit_button = gr.Button("Submit")
+        
+        submit_button.click(fn=ask, inputs=input_text, outputs=output_text)
+
+server.launch()
\ No newline at end of file
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..6217ed2
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,15 @@
+services:
+  ollama:
+    image: ollama/ollama:latest
+    ports:
+      - 7869:11434
+    volumes:
+      - .:/code
+      - ./ollama/ollama:/root/.ollama
+    container_name: ollama
+    pull_policy: always
+    tty: true
+    restart: always
+    environment:
+      - OLLAMA_KEEP_ALIVE=24h
+      - OLLAMA_HOST=0.0.0.0
\ No newline at end of file