Skip to main content

MemNetAI Python SDK - MemNetAI长记忆服务平台的Python接口

Project description

MemNet AI Python SDK

MemNet AI Python SDK 提供了与MemNet AI API交互的Python接口,包括基础请求客户端和增强功能。

功能特性

  • 基础API请求客户端
  • 记忆管理功能
  • 思考功能
  • 梦境功能
  • 常识功能
  • 增强版客户端(带LLM集成)

安装

pip install memnetai-python-sdk

快速开始

基础客户端使用

from memnetai import MemNetAIClient, Message

# 初始化客户端
client = MemNetAIClient(
    base_url="https://api.memnetai.com",
    api_key="your_api_key"
)

messages = [
    Message(role="user", content="什么是人工智能?", character="用户")
]

# 1. 记忆
response = client.memories(
    memory_agent_name="default",
    messages=messages
)
print("回忆结果:", response)

# 2. 回忆
response = client.recall(
    memory_agent_name="default",
    query="什么是人工智能?",
)
print("回忆结果:", response)

# 3. 思考功能
response = client.think(
    memory_agent_name="default",
)
print("思考结果:", response)

# 4. 梦境功能
response = client.dream(
    memory_agent_name="default",
)
print("梦境结果:", response)

# 5. 常识功能
response = client.common_sense(
    common_sense_database_id="default",
    common_sense_text="科学",
)
print("常识结果:", response)

增强版客户端使用

from memnetai import MemNetAIClientPlus, OpenAIConfig


def test_memnetaiclientplus():
    # 配置OpenAI参数
    openai_config = OpenAIConfig(
        memnetai_base_url="https://api.memnetai.com",
        memnetai_api_key="your_memnet_api_key",
        memory_agent_name="default",
        base_url="https://api.openai.com/v1",
        api_key="your_openai_api_key",
        model_name="gpt-3.5-turbo",
    )

    # 初始化增强版客户端
    client_plus = MemNetAIClientPlus(config=openai_config)

    # 智能对话(自动记忆和回忆)
    try:
        while True:
            if not client_plus.input():  # 用户输入了退出命令
                break
            response = client_plus.chat()
            print(f"AI回复: {response}")
    except KeyboardInterrupt:
        print("\n正在关闭程序...")
    finally:
        client_plus.close()


if __name__ == "__main__":
    test_memnetaiclientplus()

API 文档

基础客户端 API

记忆管理

  • recall(): 根据查询检索记忆
  • memories_create(): 创建新记忆
  • memories_detail(): 获取记忆详情
  • memories_progress(): 获取记忆处理进度
  • memories_all(): 获取所有记忆
  • memories_delete(): 删除记忆

思考功能

  • think(): 触发AI思考过程
  • think_detail(): 获取思考详情
  • think_all(): 获取所有思考任务
  • think_delete(): 删除思考任务

梦境功能

  • dream(): 创建梦境任务
  • dream_detail(): 获取梦境详情
  • dream_all(): 获取所有梦境任务
  • dream_delete(): 删除梦境任务

常识功能

  • common_sense(): 查询常识数据库
  • common_sense_detail(): 获取常识详情
  • common_sense_progress(): 获取常识处理进度
  • common_sense_all(): 获取所有常识任务
  • common_sense_delete(): 删除常识任务

增强版客户端 API

智能对话

  • chat(): 智能对话(自动记忆和回忆)
  • input(): 用户输入(触发对话)
  • close(): 关闭客户端连接

配置参数

  • OpenAIConfig: OpenAI配置参数,包含模型、温度、最大令牌等

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

memnetai_python_sdk-1.0.1.tar.gz (18.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

memnetai_python_sdk-1.0.1-py3-none-any.whl (34.0 kB view details)

Uploaded Python 3

File details

Details for the file memnetai_python_sdk-1.0.1.tar.gz.

File metadata

  • Download URL: memnetai_python_sdk-1.0.1.tar.gz
  • Upload date:
  • Size: 18.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for memnetai_python_sdk-1.0.1.tar.gz
Algorithm Hash digest
SHA256 f96d24500869029a8e2b25b29c1d9491feca4cc7a2a0fcb7706daab78cfbd7c3
MD5 199634d2c2d6eb9bf2df823b26379a12
BLAKE2b-256 e314f1c4607a4d5fe5a8b4ea071f93433376f31b0035646192a23e89a51123d5

See more details on using hashes here.

File details

Details for the file memnetai_python_sdk-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for memnetai_python_sdk-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a4acdfea9e41d59b8bbe5d4ba452002750dcb01457ab63eb3d4b2745c147f9d4
MD5 7d9b9557b812d850f9e70751205558d1
BLAKE2b-256 8724c5f663c9e29049e1c578fa0adf5e3a0103180c8133e98c363abf6e240c1a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page