mirror of
https://github.com/cpacker/MemGPT.git
synced 2025-06-03 04:30:22 +00:00
406a49ab60
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com> Co-authored-by: Shubham Naik <shub@letta.com> Co-authored-by: Shubham Naik <shub@memgpt.ai> Co-authored-by: Charles Packer <packercharles@gmail.com>
417 lines
15 KiB
JSON
417 lines
15 KiB
JSON
{
|
|
"agent_type": "memgpt_agent",
|
|
"core_memory": [
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.570593+00:00",
|
|
"description": "A default test block",
|
|
"is_template": false,
|
|
"label": "default_label",
|
|
"limit": 1000,
|
|
"metadata_": {
|
|
"type": "test"
|
|
},
|
|
"template_name": null,
|
|
"updated_at": "2025-03-28T01:11:04.570593+00:00",
|
|
"value": "Default Block Content"
|
|
},
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.609286+00:00",
|
|
"description": null,
|
|
"is_template": false,
|
|
"label": "human",
|
|
"limit": 5000,
|
|
"metadata_": {},
|
|
"template_name": null,
|
|
"updated_at": "2025-03-28T01:11:04.609286+00:00",
|
|
"value": "BananaBoy"
|
|
},
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.612946+00:00",
|
|
"description": null,
|
|
"is_template": false,
|
|
"label": "persona",
|
|
"limit": 5000,
|
|
"metadata_": {},
|
|
"template_name": null,
|
|
"updated_at": "2025-03-28T01:11:04.612946+00:00",
|
|
"value": "I am a helpful assistant"
|
|
}
|
|
],
|
|
"created_at": "2025-03-28T01:11:04.624794+00:00",
|
|
"description": "test_description",
|
|
"embedding_config": {
|
|
"embedding_endpoint_type": "openai",
|
|
"embedding_endpoint": "https://api.openai.com/v1",
|
|
"embedding_model": "text-embedding-ada-002",
|
|
"embedding_dim": 1536,
|
|
"embedding_chunk_size": 300,
|
|
"handle": null,
|
|
"azure_endpoint": null,
|
|
"azure_version": null,
|
|
"azure_deployment": null
|
|
},
|
|
"llm_config": {
|
|
"model": "gpt-4o-mini",
|
|
"model_endpoint_type": "openai",
|
|
"model_endpoint": "https://api.openai.com/v1",
|
|
"model_wrapper": null,
|
|
"context_window": 128000,
|
|
"put_inner_thoughts_in_kwargs": true,
|
|
"handle": null,
|
|
"temperature": 0.7,
|
|
"max_tokens": 4096,
|
|
"enable_reasoner": false,
|
|
"max_reasoning_tokens": 0
|
|
},
|
|
"message_buffer_autoclear": true,
|
|
"in_context_message_indices": [0, 1],
|
|
"messages": [
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.654912+00:00",
|
|
"group_id": null,
|
|
"model": "gpt-4o-mini",
|
|
"name": null,
|
|
"role": "system",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "test system\n### Memory [last modified: 2025-03-27 06:11:04 PM PDT-0700]\n0 previous messages between you and the user are stored in recall memory (use functions to access them)\n0 total memories you created are stored in archival memory (use functions to access them)\n\n\nCore memory shown below (limited in size, additional information stored in archival / recall memory):\n<default_label characters=\"21/1000\">\nDefault Block Content\n</default_label>\n<human characters=\"9/5000\">\nBananaBoy\n</human>\n<persona characters=\"24/5000\">\nI am a helpful assistant\n</persona>"
|
|
}
|
|
],
|
|
"tool_call_id": null,
|
|
"tool_calls": [],
|
|
"tool_returns": [],
|
|
"updated_at": "2025-03-28T01:11:04.654783+00:00"
|
|
},
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.654966+00:00",
|
|
"group_id": null,
|
|
"model": "gpt-4o-mini",
|
|
"name": null,
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "{\n \"type\": \"user_message\",\n \"message\": \"hello world\",\n \"time\": \"2025-03-27 06:11:04 PM PDT-0700\"\n}"
|
|
}
|
|
],
|
|
"tool_call_id": null,
|
|
"tool_calls": [],
|
|
"tool_returns": [],
|
|
"updated_at": "2025-03-28T01:11:04.654783+00:00"
|
|
}
|
|
],
|
|
"metadata_": {
|
|
"test_key": "test_value"
|
|
},
|
|
"multi_agent_group": null,
|
|
"name": "EffervescentYacht",
|
|
"system": "test system",
|
|
"tags": [
|
|
{
|
|
"tag": "a"
|
|
},
|
|
{
|
|
"tag": "b"
|
|
}
|
|
],
|
|
"tool_exec_environment_variables": [
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.638338+00:00",
|
|
"description": null,
|
|
"key": "test_env_var_key_a",
|
|
"updated_at": "2025-03-28T01:11:04.638338+00:00",
|
|
"value": ""
|
|
},
|
|
{
|
|
"created_at": "2025-03-28T01:11:04.638338+00:00",
|
|
"description": null,
|
|
"key": "test_env_var_key_b",
|
|
"updated_at": "2025-03-28T01:11:04.638338+00:00",
|
|
"value": ""
|
|
}
|
|
],
|
|
"tool_rules": [
|
|
{
|
|
"tool_name": "archival_memory_search",
|
|
"type": "continue_loop"
|
|
},
|
|
{
|
|
"tool_name": "archival_memory_insert",
|
|
"type": "continue_loop"
|
|
},
|
|
{
|
|
"tool_name": "send_message",
|
|
"type": "exit_loop"
|
|
},
|
|
{
|
|
"tool_name": "conversation_search",
|
|
"type": "continue_loop"
|
|
}
|
|
],
|
|
"tools": [
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.575001+00:00",
|
|
"description": "Fetches the current weather for a given location.",
|
|
"json_schema": {
|
|
"name": "get_weather",
|
|
"description": "Fetches the current weather for a given location.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"location": {
|
|
"type": "string",
|
|
"description": "The location to get the weather for."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": ["location", "request_heartbeat"]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "get_weather",
|
|
"return_char_limit": 6000,
|
|
"source_code": "def get_weather(location: str) -> str:\n \"\"\"\n Fetches the current weather for a given location.\n\n Parameters:\n location (str): The location to get the weather for.\n\n Returns:\n str: A formatted string describing the weather in the given location.\n\n Raises:\n RuntimeError: If the request to fetch weather data fails.\n \"\"\"\n import requests\n\n url = f\"https://wttr.in/{location}?format=%C+%t\"\n\n response = requests.get(url)\n if response.status_code == 200:\n weather_data = response.text\n return f\"The weather in {location} is {weather_data}.\"\n else:\n raise RuntimeError(f\"Failed to get weather data, status code: {response.status_code}\")\n",
|
|
"source_type": "python",
|
|
"tags": [],
|
|
"tool_type": "custom",
|
|
"updated_at": "2025-03-28T01:11:04.575001+00:00",
|
|
"metadata_": {}
|
|
},
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.579856+00:00",
|
|
"description": "Add to archival memory. Make sure to phrase the memory contents such that it can be easily queried later.",
|
|
"json_schema": {
|
|
"name": "archival_memory_insert",
|
|
"description": "Add to archival memory. Make sure to phrase the memory contents such that it can be easily queried later.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"content": {
|
|
"type": "string",
|
|
"description": "Content to write to the memory. All unicode (including emojis) are supported."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": ["content", "request_heartbeat"]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "archival_memory_insert",
|
|
"return_char_limit": 1000000,
|
|
"source_code": null,
|
|
"source_type": "python",
|
|
"tags": ["letta_core"],
|
|
"tool_type": "letta_core",
|
|
"updated_at": "2025-03-28T01:11:04.579856+00:00",
|
|
"metadata_": {}
|
|
},
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.583369+00:00",
|
|
"description": "Search archival memory using semantic (embedding-based) search.",
|
|
"json_schema": {
|
|
"name": "archival_memory_search",
|
|
"description": "Search archival memory using semantic (embedding-based) search.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "String to search for."
|
|
},
|
|
"page": {
|
|
"type": "integer",
|
|
"description": "Allows you to page through results. Only use on a follow-up query. Defaults to 0 (first page)."
|
|
},
|
|
"start": {
|
|
"type": "integer",
|
|
"description": "Starting index for the search results. Defaults to 0."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": ["query", "request_heartbeat"]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "archival_memory_search",
|
|
"return_char_limit": 1000000,
|
|
"source_code": null,
|
|
"source_type": "python",
|
|
"tags": ["letta_core"],
|
|
"tool_type": "letta_core",
|
|
"updated_at": "2025-03-28T01:11:04.583369+00:00",
|
|
"metadata_": {}
|
|
},
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.586573+00:00",
|
|
"description": "Search prior conversation history using case-insensitive string matching.",
|
|
"json_schema": {
|
|
"name": "conversation_search",
|
|
"description": "Search prior conversation history using case-insensitive string matching.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "String to search for."
|
|
},
|
|
"page": {
|
|
"type": "integer",
|
|
"description": "Allows you to page through results. Only use on a follow-up query. Defaults to 0 (first page)."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": ["query", "request_heartbeat"]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "conversation_search",
|
|
"return_char_limit": 1000000,
|
|
"source_code": null,
|
|
"source_type": "python",
|
|
"tags": ["letta_core"],
|
|
"tool_type": "letta_core",
|
|
"updated_at": "2025-03-28T01:11:04.586573+00:00",
|
|
"metadata_": {}
|
|
},
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.589876+00:00",
|
|
"description": "Append to the contents of core memory.",
|
|
"json_schema": {
|
|
"name": "core_memory_append",
|
|
"description": "Append to the contents of core memory.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"label": {
|
|
"type": "string",
|
|
"description": "Section of the memory to be edited (persona or human)."
|
|
},
|
|
"content": {
|
|
"type": "string",
|
|
"description": "Content to write to the memory. All unicode (including emojis) are supported."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": ["label", "content", "request_heartbeat"]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "core_memory_append",
|
|
"return_char_limit": 1000000,
|
|
"source_code": null,
|
|
"source_type": "python",
|
|
"tags": ["letta_memory_core"],
|
|
"tool_type": "letta_memory_core",
|
|
"updated_at": "2025-03-28T01:11:04.589876+00:00",
|
|
"metadata_": {}
|
|
},
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.593153+00:00",
|
|
"description": "Replace the contents of core memory. To delete memories, use an empty string for new_content.",
|
|
"json_schema": {
|
|
"name": "core_memory_replace",
|
|
"description": "Replace the contents of core memory. To delete memories, use an empty string for new_content.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"label": {
|
|
"type": "string",
|
|
"description": "Section of the memory to be edited (persona or human)."
|
|
},
|
|
"old_content": {
|
|
"type": "string",
|
|
"description": "String to replace. Must be an exact match."
|
|
},
|
|
"new_content": {
|
|
"type": "string",
|
|
"description": "Content to write to the memory. All unicode (including emojis) are supported."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": [
|
|
"label",
|
|
"old_content",
|
|
"new_content",
|
|
"request_heartbeat"
|
|
]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "core_memory_replace",
|
|
"return_char_limit": 1000000,
|
|
"source_code": null,
|
|
"source_type": "python",
|
|
"tags": ["letta_memory_core"],
|
|
"tool_type": "letta_memory_core",
|
|
"updated_at": "2025-03-28T01:11:04.593153+00:00",
|
|
"metadata_": {}
|
|
},
|
|
{
|
|
"args_json_schema": null,
|
|
"created_at": "2025-03-28T01:11:04.596458+00:00",
|
|
"description": "Sends a message to the human user.",
|
|
"json_schema": {
|
|
"name": "send_message",
|
|
"description": "Sends a message to the human user.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"message": {
|
|
"type": "string",
|
|
"description": "Message contents. All unicode (including emojis) are supported."
|
|
},
|
|
"request_heartbeat": {
|
|
"type": "boolean",
|
|
"description": "Request an immediate heartbeat after function execution. Set to `True` if you want to send a follow-up message or run a follow-up function."
|
|
}
|
|
},
|
|
"required": ["message", "request_heartbeat"]
|
|
},
|
|
"type": null,
|
|
"required": []
|
|
},
|
|
"name": "send_message",
|
|
"return_char_limit": 1000000,
|
|
"source_code": null,
|
|
"source_type": "python",
|
|
"tags": ["letta_core"],
|
|
"tool_type": "letta_core",
|
|
"updated_at": "2025-03-28T01:11:04.596458+00:00",
|
|
"metadata_": {}
|
|
}
|
|
],
|
|
"updated_at": "2025-03-28T01:11:04.680766+00:00",
|
|
"version": "0.6.45"
|
|
}
|