Save a Conversation to a File

Agents in CogniCoreAI use a memory module to keep track of the conversation. While VolatileMemory forgets the history when your script ends, you can easily access this history and save it to a file for later analysis or to create a persistent record.

The Core Concept

The agent’s memory object stores the entire conversation as a list of Python dictionaries. You can retrieve this list at any time by calling agent.memory.get_history(). You can then use standard Python libraries like json to write this data to a file.

Step 1: Have a Conversation

First, let’s create an agent and have a short conversation with it so there is something in its memory.

from cognicoreai import Agent, OpenAI_LLM, VolatileMemory, CalculatorTool

agent = Agent(
    llm=OpenAI_LLM(),
    memory=VolatileMemory(),
    tools=[CalculatorTool()]
)

agent.chat("Hi, my name is Alex.")
agent.chat("What is 5 plus 3?")

Step 2: Retrieve and Save the History

After the conversation, the agent’s memory contains a complete record. We can now get this history and save it as a JSON file.

import json

# Get the history from the agent's memory
conversation_history = agent.memory.get_history()

# Save the history to a file
with open("conversation_log.json", "w") as f:
    # Use indent=2 for a nicely formatted, human-readable file
    json.dump(conversation_history, f, indent=2)

print("Conversation saved to conversation_log.json")

After running this script, you will have a file named conversation_log.json with the following content:

[
  {
    "role": "system",
    "content": "You are a friendly and helpful assistant named Cogni. You have access to a calculator."
  },
  {
    "role": "user",
    "content": "Hi, my name is Alex."
  },
  {
    "role": "assistant",
    "content": "Hello Alex! It's nice to meet you. How can I help you today?"
  },
  {
    "role": "user",
    "content": "What is 5 plus 3?"
  },
  {
    "role": "assistant",
    "content": null,
    "tool_calls": [
      {
        "id": "call_123",
        "type": "function",
        "function": {
          "name": "calculator",
          "arguments": "{\"tool_input\": \"5 + 3\"}"
        }
      }
    ]
  },
  {
    "role": "tool",
    "tool_call_id": "call_123",
    "name": "calculator",
    "content": "8.0"
  },
  {
    "role": "assistant",
    "content": "5 plus 3 is 8."
  }
]

This simple recipe allows you to easily log, debug, or store any conversation had with your agent.