# Conversation

Schema reference for the tables that back conversations, individual messages, and the memories extracted from them.

### Conversations Table

**Table Name:** `conversations`\
**Description:** Conversation sessions and their metadata

{% tabs %}
{% tab title="Schema" %}

| Column                       | Type      | Description               |
| ---------------------------- | --------- | ------------------------- |
| `_id`                        | string    | Internal identifier       |
| `completed_post_processings` | json      | Post-processing status    |
| `created_at`                 | timestamp | Conversation start time   |
| `interactions`               | json      | Interaction history       |
| `is_finished`                | boolean   | Completion status         |
| `org_id`                     | string    | Organization identifier   |
| `region_name`                | string    | Deployment region         |
| `service_id`                 | string    | Associated service ID     |
| `updated_at`                 | timestamp | Last update timestamp     |
| `user_id`                    | string    | Associated user ID        |
| `version_set_info`           | json      | Version set metadata      |
| `working_memories`           | json      | Conversation memory state |
| {% endtab %}                 |           |                           |

{% tab title="Query Example" %}

```sql
SELECT
  _id AS conversation_id,
  user_id,
  service_id,
  created_at,
  is_finished
FROM conversations
WHERE is_finished = false
  AND created_at >= CURRENT_DATE - INTERVAL '7 days'
ORDER BY created_at DESC;
```

{% endtab %}
{% endtabs %}

### Messages Table

**Table Name:** `messages`\
**Description:** Individual messages within conversations

{% tabs %}
{% tab title="Schema" %}

| Column             | Type      | Description                                                                                     |
| ------------------ | --------- | ----------------------------------------------------------------------------------------------- |
| `_id`              | string    | Message identifier                                                                              |
| `content`          | string    | Message body                                                                                    |
| `conversation_id`  | string    | Parent conversation ID                                                                          |
| `created_at`       | timestamp | Message timestamp                                                                               |
| `format`           | string    | Message format (one of: `text`, `voice`)                                                        |
| `interaction_id`   | string    | Parent interaction ID                                                                           |
| `message_metadata` | json      | Additional message metadata                                                                     |
| `message_type`     | string    | Message type (one of: `user-message`, `agent-message`, `agent-inner-thought`, `external-event`) |
| `org_id`           | string    | Organization identifier                                                                         |
| `region_name`      | string    | Deployment region                                                                               |
| `sender`           | string    | Sender identifier (user/agent)                                                                  |
| `updated_at`       | timestamp | Last update timestamp                                                                           |
| `user_id`          | string    | Associated user ID                                                                              |
| {% endtab %}       |           |                                                                                                 |

{% tab title="Query Example" %}

```sql
SELECT
  conversation_id,
  sender,
  message_type,
  content,
  created_at
FROM messages
WHERE conversation_id = 'conv-123'
ORDER BY created_at ASC;
```

{% endtab %}
{% endtabs %}

### Memories Table

**Table Name:** `memories`\
**Description:** Stored conversation memories

{% tabs %}
{% tab title="Schema" %}

| Column            | Type      | Description                                                        |
| ----------------- | --------- | ------------------------------------------------------------------ |
| `_id`             | string    | Memory identifier                                                  |
| `content`         | json      | Memory content `{ reference, content, context, importance_score }` |
| `conversation_id` | string    | Associated conversation ID                                         |
| `created_at`      | timestamp | Creation timestamp                                                 |
| `org_id`          | string    | Organization identifier                                            |
| `region_name`     | string    | Deployment region                                                  |
| `updated_at`      | timestamp | Last update timestamp                                              |
| `user_id`         | string    | Associated user ID                                                 |
| {% endtab %}      |           |                                                                    |

{% tab title="Query Example" %}

```sql
SELECT
  user_id,
  conversation_id,
  content,
  created_at
FROM memories
WHERE user_id = 'user-123'
ORDER BY created_at DESC
LIMIT 20;
```

{% endtab %}
{% endtabs %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.amigo.ai/developer-guide/classic-api/data-access/organization-tables/conversation.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.