Move the Python client library instructions into a quickstart

README.md

@@ -102,25 +102,6 @@ $ curl http://127.0.0.1:5555/v1/embeddings \
 }
 ```
 
-OpenAI client library could be configured to use the proxy:
-
-```python
-from openai import OpenAI
-
-client = OpenAI(
-    base_url="http://127.0.0.1:5555/v1", # or set OPENAI_BASE_URL environmental variable
-)
-chat_completion = client.chat.completions.create(
-    model = "gemini-1.5-pro",
-    messages=[
-        {
-            "role": "user",
-            "content": "Say this is a test",
-        }
-    ],
-)
-```
-
 ### Known OpenAI Limitations
 
 * Only [chat completions](https://platform.openai.com/docs/api-reference/chat) and [embeddings](https://platform.openai.com/docs/api-reference/embeddings/create) are planned to be supported.

docs/quickstart.md

@@ -0,0 +1,42 @@
+# Quickstart
+
+## OpenAI API
+
+Obtain a Gemini API key from the [AI Studio](https://aistudio.google.com/).
+Then set the following environmental variable to the key and run the proxy:
+
+```sh
+$ export GEMINI_API_KEY=<YOUR_API_KEY>
+$ docker run -p 5555:5555 -e GEMINI_API_KEY=$GEMINI_API_KEY googlegemini/proxy-to-gemini
+```
+
+Set the following environment variable to the proxy:
+
+```sh
+$ export OPENAI_BASE_URL="http://127.0.0.1:5555/v1"
+```
+
+Then the OpenAI Python client library will use the proxy.
+Save the following code in test.py:
+
+```python
+from openai import OpenAI
+
+client = OpenAI()
+chat_completion = client.chat.completions.create(
+    model = "gemini-1.5-pro",
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test",
+        }
+    ],
+)
+print(chat_completion)
+```
+
+Run the Python file:
+
+```sh
+$ python3 test.py
+```