A Modern Usage Example for the Official Python SDK: From Environment Setup to Multi-Turn Conversation History Management
Build a chatbot with memory in Python! Use minimal hands-on code based on the official google-generativeai library, with a visual explanation of the chat = model.start_chat() history management technique.
1. Environment Installation and Initialization
Run the following in your terminal: pip install google-generativeai
2. Concise Python Code with Full Conversation History Memory
import os
import google.generativeai as genai
genai.configure(api_key=os.environ["GEMINI_API_KEY"])
model = genai.GenerativeModel("gemini-1.5-flash")
chat = model.start_chat(history=[])
while True:
user_input = input("User: ")
if user_input.lower() == "exit":
break
response = chat.send_message(user_input)
print(f"Gemini: {response.text}")
With the start_chat object, all back-and-forth question history is automatically maintained in the background, so developers do not need to manually assemble complex JSON message arrays!