Error when trying to do multiturn chat with gemini-pro

Question

This is the code I took from the API docs in order to start multiturn chat

model = genai.GenerativeModel("gemini-pro")
messages = [{'role':'user', 'parts': ['hello']}]
response = model.generate_content(messages) # "Hello, how can I help"
messages.append(response.candidates[0].content)
messages.append({'role':'user', 'parts': ['How does quantum physics work?']})
response = model.generate_content(messages)

But I'm getting the following error:

TypeError: Could not create Blob, expected Blob, dict or an Image type(PIL.Image.Image or IPython.display.Image). Got a: <class 'google.ai.generativelanguage_v1beta.types.content.Content'> Value: parts { text: "hello" }

I also tried using the send_message feature, but I got the same error after I tried to use send_message the second time.

Answer 1

As a simple modification, how about the following modification?

Modified script 1:

genai.configure(api_key=apiKey)
model = genai.GenerativeModel("gemini-pro")
messages = [{"role": "user", "parts": ["hello"]}]
response = model.generate_content(messages)
messages.append({"role": "model", "parts": [response.text]})
print("--- response 1")
print(response.text)

messages.append({"role": "user", "parts": ["How does quantum physics work?"]})
response = model.generate_content(messages)
print("--- response 2")
print(response.text)

Modified script 2:

As another modification, how about the following modification? Ref

import google.generativeai as genai

apiKey = "###" # If you use API key, please set your API key.


genai.configure(api_key=apiKey)
model = genai.GenerativeModel("gemini-pro")

chat = model.start_chat()


def get_chat_response(chat: genai.ChatSession, prompt: str) -> str:
    response = chat.send_message(prompt)
    return response.text


prompt = "hello"
print(get_chat_response(chat, prompt))

prompt = "How does quantum physics work?"
print(get_chat_response(chat, prompt))