diff --git a/examples/python/README.md b/examples/python/README.md
new file mode 100644
index 000000000..ce621a5bc
--- /dev/null
+++ b/examples/python/README.md
@@ -0,0 +1,15 @@
+# Python
+
+This is a simple example of calling the Ollama api from a python app.
+
+First, download a model:
+
+```
+curl -L https://huggingface.co/TheBloke/orca_mini_3B-GGML/resolve/main/orca-mini-3b.ggmlv3.q4_1.bin -o orca.bin
+```
+
+Then run it using the example script. You'll need to have Ollama running on your machine.
+
+```
+python3 main.py orca.bin
+```
diff --git a/examples/python/main.py b/examples/python/main.py
new file mode 100644
index 000000000..b6791b548
--- /dev/null
+++ b/examples/python/main.py
@@ -0,0 +1,32 @@
+import http.client
+import json
+import os
+import sys
+
+if len(sys.argv) < 2:
+    print("Usage: python main.py <model file>")
+    sys.exit(1)
+
+conn = http.client.HTTPConnection('localhost', 11434)
+
+headers = { 'Content-Type': 'application/json' }
+
+# generate text from the model
+conn.request("POST", "/api/generate", json.dumps({
+    'model': os.path.join(os.getcwd(), sys.argv[1]),
+    'prompt': 'write me a short story',
+    'stream': True
+}), headers)
+
+response = conn.getresponse()
+
+def parse_generate(data):
+    for event in data.decode('utf-8').split("\n"):
+        if not event:
+            continue
+        yield event
+
+if response.status == 200:
+    for chunk in response:
+        for event in parse_generate(chunk):
+            print(json.loads(event)['response'], end="", flush=True)