Update README.md

README.md

@@ -64,4 +64,52 @@ export KIND_TEACHER_HOST="localhost"
 Once the environment is configured, you can execute the program by running the following command:
 ```bash
 llamafactory-cli api run_api_inference_1.yaml
+```
+
+**API Call Format**
+```python
+address="localhost"
+port=8000
+type_message = {"GET": "/models", "POST": "/chat/completions"}
+url = f'http://{address}:{port}/v1{type_message["POST"]}'
+
+headers = {
+  'accept': 'application/json',
+  'Content-Type': 'application/json'
+}
+
+messages = [
+  {
+    "role": "system",    # "user", "assistant" or "system"
+    "content": "You are a kind teacher that help students with their problems.",
+  },
+  {
+    "role": "user",    # "user", "assistant" or "system"
+    "content": "Hello teacher",
+    "tool_calls": []
+  },
+  {
+    "role": "assistant",    # "user", "assistant" or "system"
+    "content": "Hello student!",
+  },
+  {
+    "role": "user",    # "user", "assistant" or "system"
+    "content": "Can you help me to understand the past perfect of english?",
+    "tool_calls": []
+  },
+]
+
+data = {
+    "model": "Transducens/kind_teacher",
+    "messages": messages,   # messages must be formatted in the required format
+    "tools": [],
+    "do_sample": True,
+    "temperature": 1.0,
+    "top_p": 0.7,
+    "n": 1,                 # number of completions (responses) to generate
+    "max_tokens": 150,
+    "stream": False
+}
+
+response = requests.post(url, headers=headers, data=json.dumps(data))
 ```