Errors with Code: Requesting Human Input

[tayloreeves]

Hi all,
I am currently trying to set up the Gemini Assistant API with 2 converable agents working together. When I try to run this code, it asks for keyboard input, and then I get the following error when anything is inputted: "Error during agent setup or execution: Missing required arguments; Expected either ('messages' and 'model') or ('messages', 'model' and 'stream') arguments to be given"

Here is my code for reference:

`# Imported Modules
import os
from autogen import AssistantAgent
import google.generativeai as genai

Load API Key from a file

try:
with open("API KEY.txt", "r") as file:
API_KEY = file.read().strip() # Ensure no trailing newlines or spaces
except FileNotFoundError:
raise FileNotFoundError("API KEY.txt file not found. Ensure the file exists in the script's directory.")

Test to ensure API key is valid

try:
genai.configure(api_key=API_KEY)
print("Google Generative AI configured successfully.")
except Exception as e:
raise Exception(f"Failed to configure Google Generative AI: {e}")

AssistantAgent Configuration

try:
Gemini1 = AssistantAgent(
name="Gemini1",
system_message="Always answer questions within one sentence.",
llm_config={"model_name": "gemini-1.5-flash", "api_key": API_KEY, "seed": 25},
max_consecutive_auto_reply=3
)

Gemini2 = AssistantAgent(
    name="Gemini2",
    system_message="You should ask weird, tricky, and concise questions. "
                   "Ask the next question based on (by evolving) the previous one.",
    llm_config={"model_name": "gemini-1.5-flash", "api_key": API_KEY, "seed": 25},
    max_consecutive_auto_reply=4
)

# Simulate Conversation Between Two Agents
initial_message = [
    {"role": "system", "content": Gemini1.system_message},
    {"role": "user", "content": "Should Spider-Man invest in a 401K?"}
]

# Run the conversation
result = Gemini1.initiate_chat(
    Gemini2,  # Gemini2 is the target conversational agent
    messages=initial_message,  # Initial conversation messages
    model={"name": "gemini-1.5-flash", "api_key": API_KEY, "seed": 25},  # Explicit model config
    max_turns=2,  # Define the maximum number of turns
)

print("Agent Conversation Result:", result)

except Exception as e:
print(f"Error during agent setup or execution: {e}")`

If someone could help out, that'd be great!