> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memobase.io/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatBlob

ChatBlob is for user/AI messages.
Memobase will automatically understand and extract the messages into structured profiles.

An example of ChatBlob is below:

<Accordion title="Example to insert ChatBlob">
  <CodeGroup>
    ```python Python theme={null}
    from memobase import ChatBlob

    b = ChatBlob(messages=[
        {"role": "user", "content": "Hello, how are you?"},
        {
            "role": "assistant", 
            "content": "I'm fine, thank you!", 
            "alias": "Her", 
            "created_at": "2025-01-01"
        },
    ])


    u.insert(b)
    ```

    ```bash https theme={null}
    curl -X POST "$PROJECT_URL/api/v1/blobs/insert/{uid}" \
         -H "Authorization: Bearer $PROJECT_TOKEN" \
         -H "Content-Type: application/json" \
         -d '{ "blob_type": "chat", "blob_data": { "messages": [ {"role": "user","content": "Hi, Im here again"}, {"role": "assistant", "content": "Hi, Gus! How can I help you?", "alias": "Her", "created_at": "2025-01-01"}] }}'
    ```
  </CodeGroup>
</Accordion>

The message format is OpenAI Message format:

```json theme={null}
{
  "role": "user" | "assistant",
  "content": "string",
  "alias": "string, optional",
  "created_at": "string, optional"
}
```

* `role`: user or assistant
* `content`: message content
* `alias`: optional. You can set the name of the character(user or assistant), it will reflect in the memory profile.
* `created_at`: optional. You can set the date of the message.