Chat Integration

Import chat histories and conversations to extract memories

POST /integrations/chat

cURL

curl -X POST 'https://api.memchat.io/integrations/chat' \
  -H 'X-API-Key: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "platform": "chatgpt",
    "chat_data": [
      {
        "timestamp": "2024-01-15T14:30:00Z",
        "role": "user",
        "content": "Tell me about machine learning applications in healthcare"
      },
      {
        "timestamp": "2024-01-15T14:30:15Z", 
        "role": "assistant",
        "content": "Machine learning has numerous applications in healthcare..."
      }
    ],
    "extract_mode": "conversations"
  }'

import requests

url = "https://api.memchat.io/integrations/chat"
headers = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "platform": "chatgpt",
    "chat_data": [
        {
            "timestamp": "2024-01-15T14:30:00Z",
            "role": "user", 
            "content": "Tell me about machine learning applications in healthcare"
        },
        {
            "timestamp": "2024-01-15T14:30:15Z",
            "role": "assistant",
            "content": "Machine learning has numerous applications in healthcare..."
        }
    ],
    "extract_mode": "conversations"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

const response = await fetch('https://api.memchat.io/integrations/chat', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    platform: 'chatgpt',
    chat_data: [
      {
        timestamp: '2024-01-15T14:30:00Z',
        role: 'user',
        content: 'Tell me about machine learning applications in healthcare'
      },
      {
        timestamp: '2024-01-15T14:30:15Z',
        role: 'assistant', 
        content: 'Machine learning has numerous applications in healthcare...'
      }
    ],
    extract_mode: 'conversations'
  }),
});

const result = await response.json();

Response

{
  "integration_id": "chat_int_789abc",
  "platform": "chatgpt",
  "status": "completed",
  "processing_stats": {
    "total_messages": 24,
    "conversations_identified": 3,
    "memories_extracted": 5,
    "topics_detected": [
      "Machine Learning in Healthcare",
      "Python Programming",
      "Career Development"
    ],
    "date_range": {
      "start": "2024-01-10T09:00:00Z",
      "end": "2024-01-15T17:30:00Z"
    }
  },
  "memories": [
    {
      "memory_id": "mem_chat_001",
      "content": "Discussed machine learning applications in medical diagnosis, specifically how neural networks can improve accuracy in identifying diseases from medical imaging. Learned about specific techniques and real-world implementations.",
      "category": "learning",
      "conversation_topic": "Machine Learning in Healthcare",
      "participants": ["user", "assistant"],
      "start_time": "2024-01-15T14:30:00Z",
      "end_time": "2024-01-15T14:45:00Z"
    }
  ]
}

Import chat histories from various platforms to automatically extract and store conversational memories.

cURL

curl -X POST 'https://api.memchat.io/integrations/chat' \
  -H 'X-API-Key: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "platform": "chatgpt",
    "chat_data": [
      {
        "timestamp": "2024-01-15T14:30:00Z",
        "role": "user",
        "content": "Tell me about machine learning applications in healthcare"
      },
      {
        "timestamp": "2024-01-15T14:30:15Z", 
        "role": "assistant",
        "content": "Machine learning has numerous applications in healthcare..."
      }
    ],
    "extract_mode": "conversations"
  }'

import requests

url = "https://api.memchat.io/integrations/chat"
headers = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "platform": "chatgpt",
    "chat_data": [
        {
            "timestamp": "2024-01-15T14:30:00Z",
            "role": "user", 
            "content": "Tell me about machine learning applications in healthcare"
        },
        {
            "timestamp": "2024-01-15T14:30:15Z",
            "role": "assistant",
            "content": "Machine learning has numerous applications in healthcare..."
        }
    ],
    "extract_mode": "conversations"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

const response = await fetch('https://api.memchat.io/integrations/chat', {
  method: 'POST',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    platform: 'chatgpt',
    chat_data: [
      {
        timestamp: '2024-01-15T14:30:00Z',
        role: 'user',
        content: 'Tell me about machine learning applications in healthcare'
      },
      {
        timestamp: '2024-01-15T14:30:15Z',
        role: 'assistant', 
        content: 'Machine learning has numerous applications in healthcare...'
      }
    ],
    extract_mode: 'conversations'
  }),
});

const result = await response.json();

Request Body

platform · string · required

Chat platform source. Supported: chatgpt, claude, telegram, whatsapp, slack, discord

chat_data · array · required

Array of chat messages

Show Message Properties

timestamp · string · required

ISO 8601 timestamp of the message

role · string · required

Message role: user, assistant, system, or participant name

content · string · required

Message content/text

message_id · string

Unique identifier for the message

metadata · object

Additional message metadata

extract_mode · string · default: "conversations"

Extraction strategy. Options: conversations, insights, topics, all

conversation_settings · object

Settings for conversation processing

Show Conversation Settings

min_length · number · default: "50"

Minimum message length to consider

group_by_topic · boolean · default: "true"

Whether to group related messages by topic

include_system_messages · boolean · default: "false"

Whether to include system messages

time_gap_threshold · number · default: "3600"

Seconds gap to separate conversations

auto_categorize · boolean · default: "true"

Whether to automatically categorize extracted memories

Response

integration_id · string

Unique identifier for the chat integration

platform · string

Chat platform that was processed

status · string

Processing status: processing, completed, error

processing_stats · object

Statistics about the processing

Show Processing Statistics

total_messages · number

Total number of messages processed

conversations_identified · number

Number of distinct conversations found

memories_extracted · number

Number of memories created

topics_detected · array

Main topics identified in conversations

date_range · object

Date range of the chat history

memories · array

List of extracted memories

Show Memory Properties

memory_id · string

Unique identifier for the memory

content · string

Extracted conversation content

category · string

Assigned category

conversation_topic · string

Main topic of the conversation

participants · array

Participants in the conversation

start_time · string

When the conversation started

end_time · string

When the conversation ended

Response

{
  "integration_id": "chat_int_789abc",
  "platform": "chatgpt",
  "status": "completed",
  "processing_stats": {
    "total_messages": 24,
    "conversations_identified": 3,
    "memories_extracted": 5,
    "topics_detected": [
      "Machine Learning in Healthcare",
      "Python Programming",
      "Career Development"
    ],
    "date_range": {
      "start": "2024-01-10T09:00:00Z",
      "end": "2024-01-15T17:30:00Z"
    }
  },
  "memories": [
    {
      "memory_id": "mem_chat_001",
      "content": "Discussed machine learning applications in medical diagnosis, specifically how neural networks can improve accuracy in identifying diseases from medical imaging. Learned about specific techniques and real-world implementations.",
      "category": "learning",
      "conversation_topic": "Machine Learning in Healthcare",
      "participants": ["user", "assistant"],
      "start_time": "2024-01-15T14:30:00Z",
      "end_time": "2024-01-15T14:45:00Z"
    }
  ]
}

Extraction Modes

Conversations

Groups related messages into conversation memories, preserving context and flow.

Insights

Extracts key insights, learnings, and important information from conversations.

Topics

Creates memories organized by topics discussed across conversations.

All

Combines all extraction modes for comprehensive memory creation.

Supported Platforms

ChatGPT

• Export conversations from ChatGPT
• Identifies learning topics and insights
• Categories: primarily learning, productivity

Claude

• Claude conversation exports
• Focus on analytical discussions
• Categories: learning, productivity, interests

Telegram/WhatsApp

• Personal and group conversations
• Relationship and social memories
• Categories: relationships, interests, travel

Slack/Discord

• Professional and community discussions
• Work-related and interest-based memories
• Categories: career, relationships, interests

Privacy and Security

• Data Processing: Chat data is processed securely and not stored permanently
• Participant Privacy: Names and identifiers can be anonymized
• Content Filtering: Sensitive content is automatically filtered out
• Retention: Original chat data is deleted after processing