mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-09-07 08:26:06 +00:00
merge sphinx doc into master
This commit is contained in:
huangsen.huang
jinli.yl
parent
430b4d8180
commit
28a3ec3dff
21 changed files with 213 additions and 677 deletions
|
|
@ -2,9 +2,7 @@ English | [**中文**](./README_ZH.md)
|
|||
|
||||
# MemoryScope
|
||||
|
||||
<p align="left">
|
||||
<img src="docs/images/logo_1.png" width="700px" alt="MemoryScope Logo">
|
||||
</p>
|
||||
|
||||
|
||||
Equip your LLM chatbot with a powerful and flexible long term memory system.
|
||||
|
||||
|
|
@ -33,9 +31,8 @@ to form and update *insights*. Then, memory re-consolidation is performed to ens
|
|||
among memory pieces are properly handled.
|
||||
|
||||
### Framework
|
||||
<p align="left">
|
||||
<img src="docs/images/framework.png" width="700px" alt="MemoryScope Framework">
|
||||
</p>
|
||||
|
||||
|
||||
|
||||
### Main Features
|
||||
|
||||
|
|
|
|||
14
README_ZH.md
14
README_ZH.md
|
|
@ -2,6 +2,7 @@
|
|||
|
||||
# MemoryScope
|
||||
|
||||
|
||||
<p align="left">
|
||||
<img src="docs/images/logo.png" width="700px" alt="MemoryScope Logo">
|
||||
</p>
|
||||
|
|
@ -28,12 +29,25 @@
|
|||
|
||||
## 什么是MemoryScope？
|
||||
|
||||
💾 记忆数据库:
|
||||
- MemoryScope 配备了一个 *ElasticSearch (ES)* 向量数据库，用于存储系统中记录的所有记忆片段。
|
||||
|
||||
🛠️ 系统操作:
|
||||
- 记忆检索：当用户输入对话，此操作返回语义相关的记忆片段。如果输入对话包含对时间的指涉，则同时返回相应时间中的记忆片段。
|
||||
- 记忆巩固：此操作接收一批用户的输入对话，并从对话中提取重要的用户信息，将其作为 *observation* 形式的记忆片段存储在记忆数据库中。
|
||||
- 反思与再巩固：每隔一段时间，此操作对新记录的 *observations* 进行反思，以形成和更新 *insight* 形式的记忆片段。然后执行记忆再巩固，
|
||||
以确保记忆片段之间的矛盾和重复得到妥善处理。
|
||||
|
||||
### 框架
|
||||
MemoryScope可以为LLM聊天机器人提供强大且灵活的长期记忆能力，并提供了构建长期记忆能力的框架。
|
||||
MemoryScope可以用于个人助理、情感陪伴等记忆场景，通过长期记忆能力来不断学习，记得用户的基础信息以及各种习惯和喜好，使得用户在使用LLM时逐渐感受到一种“默契”。
|
||||
<p align="left">
|
||||
<img src="docs/images/framework.png" width="700px" alt="MemoryScope Framework">
|
||||
</p>
|
||||
|
||||
|
||||
|
||||
### 主要特点
|
||||
### 长期记忆的框架：
|
||||
|
||||
💾 记忆数据库: MemoryScope配备了向量数据库(默认是*ElasticSearch*)，用于存储系统中记录的所有记忆片段。
|
||||
|
|
|
|||
|
|
@ -43,28 +43,13 @@
|
|||
3. Run `docker-compose up` to build and launch the memory-scope cli interface.
|
||||
|
||||
|
||||
## III. Install from PYPI [Linux only]
|
||||
## III. Install from PyPI [Linux]
|
||||
|
||||
1. Install from pypi:
|
||||
|
||||
```bash
|
||||
pip install memoryscope
|
||||
```
|
||||
|
||||
|
||||
2. test Chinese / Dashscope chat configuration:
|
||||
|
||||
```bash
|
||||
export DASHSCOPE_API_KEY="sk-0000000000"
|
||||
memoryscope --config_path=memoryscope/core/config/demo_config_zh.yaml
|
||||
```
|
||||
|
||||
3. test English / OpenAI chat configuration:
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY="sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
|
||||
python quick-start-demo.py --config_path=memoryscope/core/config/demo_config.yaml
|
||||
```
|
||||
```bash
|
||||
pip install memoryscope
|
||||
export DASHSCOPE_API_KEY="sk-0000000000"
|
||||
memoryscope --config_path=memoryscope/core/config/demo_config_zh.yaml
|
||||
```
|
||||
|
||||
|
||||
## IV. Install from source [Linux only]
|
||||
|
|
@ -78,7 +63,7 @@
|
|||
vim memoryscope/core/config/demo_config_zh.yaml
|
||||
```
|
||||
|
||||
2. Install
|
||||
2. Install
|
||||
```bash
|
||||
pip install -e .
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,7 +1,41 @@
|
|||
#!/bin/bash
|
||||
cd docs/sphinx_doc
|
||||
|
||||
|
||||
# remove build
|
||||
rm -rf build/html/*
|
||||
rm en/source/memoryscope*.rst
|
||||
rm zh_CN/source/memoryscope*.rst
|
||||
|
||||
|
||||
# copy related files
|
||||
cd ../../
|
||||
|
||||
cp README.md docs/sphinx_doc/en/source/README.md
|
||||
cp docs/installation.md docs/sphinx_doc/en/source/docs/installation.md
|
||||
cp -r docs/images docs/sphinx_doc/en/source/docs/images
|
||||
cp -r examples docs/sphinx_doc/en/source/examples
|
||||
|
||||
cp README_ZH.md docs/sphinx_doc/zh_CN/source/README.md
|
||||
cp docs/installation_ZH.md docs/sphinx_doc/zh_CN/source/docs/installation.md
|
||||
cp -r docs/images docs/sphinx_doc/zh_CN/source/docs/images
|
||||
cp -r examples docs/sphinx_doc/zh_CN/source/examples
|
||||
|
||||
|
||||
# build
|
||||
cd docs/sphinx_doc
|
||||
sphinx-apidoc -f -o en/source ../../memoryscope -t template -e
|
||||
sphinx-apidoc -f -o zh_CN/source ../../memoryscope -t template -e
|
||||
make clean all
|
||||
|
||||
# clear redundant files
|
||||
make clean all
|
||||
|
||||
rm en/source/README.md
|
||||
rm en/source/docs/installation.md
|
||||
rm -rf en/source/docs/images
|
||||
rm -rf en/source/examples
|
||||
|
||||
rm zh_CN/source/README.md
|
||||
rm zh_CN/source/docs/installation.md
|
||||
rm -rf zh_CN/source/docs/images
|
||||
rm -rf zh_CN/source/examples
|
||||
|
|
@ -39,11 +39,12 @@ extensions = [
|
|||
"sphinxcontrib.mermaid",
|
||||
"myst_parser",
|
||||
"sphinx.ext.autosectionlabel",
|
||||
'sphinxcontrib.autodoc_pydantic'
|
||||
"sphinxcontrib.autodoc_pydantic",
|
||||
"nbsphinx"
|
||||
]
|
||||
|
||||
autodoc_pydantic_model_show_json = True
|
||||
autodoc_pydantic_settings_show_json = True
|
||||
autodoc_pydantic_settings_show_json = True
|
||||
|
||||
# Prefix document path to section labels, otherwise autogenerated labels would
|
||||
# look like 'heading' rather than 'path/to/file:heading'
|
||||
|
|
@ -82,13 +83,16 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
|
|||
#
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
|
||||
# html_logo = "_static/logo.png"
|
||||
|
||||
# Add any paths that contain custom static files (such as style sheets) here,
|
||||
# relative to this directory. They are copied after the builtin static files,
|
||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||
html_static_path = ["_static"]
|
||||
|
||||
html_theme_options = {
|
||||
"navigation_depth": 10,
|
||||
# "logo_only": True,
|
||||
"navigation_depth": 4,
|
||||
}
|
||||
|
||||
source_suffix = {
|
||||
|
|
|
|||
|
|
@ -1,9 +1,5 @@
|
|||
.. _api:
|
||||
|
||||
=============
|
||||
API Reference
|
||||
=============
|
||||
|
||||
|
||||
MemoryScope API Documentation
|
||||
|
||||
|
|
@ -6,25 +6,48 @@
|
|||
:github_url: https://github.com/modelscope/memoryscope
|
||||
|
||||
MemoryScope Documentation
|
||||
======================================
|
||||
=========================
|
||||
|
||||
Welcome to MemoryScope Tutorial
|
||||
-------------------------------
|
||||
|
||||
.. include:: tutorial/main.md
|
||||
:parser: myst_parser.sphinx_
|
||||
.. image:: docs/images/logo_1.png
|
||||
:align: center
|
||||
|
||||
MemoryScope is a powerful and flexible long term memory system for LLM chatbots. It consists
|
||||
of a memory database and three customizable system operations, which can be flexibly combined to provide
|
||||
robust long term memory services for your LLM chatbot.
|
||||
|
||||
💾 Memory Database:
|
||||
^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
- MemoryScope comes with an *ElasticSearch (ES)* vector database to store all the
|
||||
memory pieces recorded in the system.
|
||||
|
||||
🛠️ System operations:
|
||||
^^^^^^^^^^^^^^^^^^^^^
|
||||
|
||||
- Memory Retrieval: Upon arrival of a user query, this operation returns the semantically related memory pieces
|
||||
and/or those from the corresponding time if the query involves reference to time.
|
||||
|
||||
- Memory Consolidation: This operation takes in a batch of user queries and returns important user information
|
||||
extracted from the queries as consolidated *observations* to be stored in the memory database.
|
||||
|
||||
- Reflection and Re-consolidation: At regular intervals, this operation performs reflection upon newly recorded *observations*
|
||||
to form and update *insights*. Then, memory re-consolidation is performed to ensure contradictions and repetitions
|
||||
among memory pieces are properly handled.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:hidden:
|
||||
:maxdepth: 2
|
||||
:caption: MemoryScope Tutorial
|
||||
|
||||
tutorial/101-memoryscope.md
|
||||
tutorial/102-installation.md
|
||||
tutorial/103-example.md
|
||||
About MemoryScope <README.md>
|
||||
🚀 Installation <docs/installation.md>
|
||||
Cli Client <examples/cli/README.md>
|
||||
Simple Usages <examples/api/simple_usages_en.ipynb>
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 6
|
||||
:caption: MemoryScope API Reference
|
||||
|
||||
memoryscope
|
||||
|
||||
API <docs/api.rst>
|
||||
|
|
|
|||
|
|
@ -1,116 +0,0 @@
|
|||
(101-memoryscope-en)=
|
||||
|
||||
# About AgentScope
|
||||
|
||||
In this tutorial, we will provide an overview of AgentScope by answering
|
||||
several questions, including what's AgentScope, what can AgentScope provide,
|
||||
and why we should choose AgentScope. Let's get started!
|
||||
|
||||
## What is AgentScope?
|
||||
|
||||
AgentScope is a developer-centric multi-agent platform, which enables
|
||||
developers to build their LLM-empowered multi-agent applications with less
|
||||
effort.
|
||||
|
||||
With the advance of large language models, developers are able to build
|
||||
diverse applications.
|
||||
In order to connect LLMs to data and services and solve complex tasks,
|
||||
AgentScope provides a series of development tools and components for ease of
|
||||
development.
|
||||
It features
|
||||
|
||||
- **usability**,
|
||||
- **robustness**,
|
||||
- **the support of multi-modal data**,
|
||||
- **distributed deployment**.
|
||||
|
||||
## Key Concepts
|
||||
|
||||
### Message
|
||||
|
||||
Message is a carrier of information (e.g. instructions, multi-modal
|
||||
data, and dialogue). In AgentScope, message is a Python dict subclass
|
||||
with `name` and `content` as necessary fields, and `url` as an optional
|
||||
field referring to additional resources.
|
||||
|
||||
### Agent
|
||||
|
||||
Agent is an autonomous entity capable of interacting with environment and
|
||||
agents, and taking actions to change the environment. In AgentScope, an
|
||||
agent takes message as input and generates corresponding response message.
|
||||
|
||||
### Service
|
||||
|
||||
Service refers to the functional APIs that enable agents to perform
|
||||
specific tasks. In AgentScope, services are categorized into model API
|
||||
services, which are channels to use the LLMs, and general API services,
|
||||
which provide a variety of tool functions.
|
||||
|
||||
### Workflow
|
||||
|
||||
Workflow represents ordered sequences of agent executions and message
|
||||
exchanges between agents, analogous to computational graphs in TensorFlow,
|
||||
but with the flexibility to accommodate non-DAG structures.
|
||||
|
||||
## Why AgentScope?
|
||||
|
||||
**Exceptional usability for developers.**
|
||||
AgentScope provides high usability for developers with flexible syntactic
|
||||
sugars, ready-to-use components, and pre-built examples.
|
||||
|
||||
**Robust fault tolerance for diverse models and APIs.**
|
||||
AgentScope ensures robust fault tolerance for diverse models, APIs, and
|
||||
allows developers to build customized fault-tolerant strategies.
|
||||
|
||||
**Extensive compatibility for multi-modal application.**
|
||||
AgentScope supports multi-modal data (e.g., files, images, audio and videos)
|
||||
in both dialog presentation, message transmission and data storage.
|
||||
|
||||
**Optimized efficiency for distributed multi-agent operations.** AgentScope
|
||||
introduces an actor-based distributed mechanism that enables centralized
|
||||
programming of complex distributed workflows, and automatic parallel
|
||||
optimization.
|
||||
|
||||
## How is AgentScope designed?
|
||||
|
||||
The architecture of AgentScope comprises three hierarchical layers. The
|
||||
layers provide supports for multi-agent applications from different levels,
|
||||
including elementary and advanced functionalities of a single agent
|
||||
(**utility layer**), resources and runtime management (**manager and wrapper
|
||||
layer**), and agent-level to workflow-level programming interfaces (**agent
|
||||
layer**). AgentScope introduces intuitive abstractions designed to fulfill
|
||||
the diverse functionalities inherent to each layer and simplify the
|
||||
complicated interlayer dependencies when building multi-agent systems.
|
||||
Furthermore, we offer programming interfaces and default mechanisms to
|
||||
strengthen the resilience of multi-agent systems against faults within
|
||||
different layers.
|
||||
|
||||
## AgentScope Code Structure
|
||||
|
||||
```bash
|
||||
AgentScope
|
||||
├── src
|
||||
│ ├── agentscope
|
||||
│ | ├── agents # Core components and implementations pertaining to agents.
|
||||
│ | ├── memory # Structures for agent memory.
|
||||
│ | ├── models # Interfaces for integrating diverse model APIs.
|
||||
│ | ├── pipelines # Fundamental components and implementations for running pipelines.
|
||||
│ | ├── rpc # Rpc module for agent distributed deployment.
|
||||
│ | ├── service # Services offering functions independent of memory and state.
|
||||
| | ├── web # WebUI used to show dialogs.
|
||||
│ | ├── utils # Auxiliary utilities and helper functions.
|
||||
│ | ├── message.py # Definitions and implementations of messaging between agents.
|
||||
│ | ├── prompt.py # Prompt engineering module for model input.
|
||||
│ | ├── ... ..
|
||||
│ | ├── ... ..
|
||||
├── scripts # Scripts for launching local Model API
|
||||
├── examples # Pre-built examples of different applications.
|
||||
├── docs # Documentation tool for API reference.
|
||||
├── tests # Unittest modules for continuous integration.
|
||||
├── LICENSE # The official licensing agreement for AgentScope usage.
|
||||
└── setup.py # Setup script for installing.
|
||||
├── ... ..
|
||||
└── ... ..
|
||||
```
|
||||
|
||||
[[Return to the top]](#101-memoryscope-en)
|
||||
|
|
@ -1,68 +0,0 @@
|
|||
(102-installation-en)=
|
||||
|
||||
# Installation
|
||||
|
||||
To install AgentScope, you need to have Python 3.9 or higher installed. We recommend setting up a new virtual environment specifically for AgentScope:
|
||||
|
||||
## Create a Virtual Environment
|
||||
|
||||
### Using Conda
|
||||
|
||||
If you're using Conda as your package and environment management tool, you can create a new virtual environment with Python 3.9 using the following commands:
|
||||
|
||||
```bash
|
||||
# Create a new virtual environment named 'agentscope' with Python 3.9
|
||||
conda create -n agentscope python=3.9
|
||||
|
||||
# Activate the virtual environment
|
||||
conda activate agentscope
|
||||
```
|
||||
|
||||
### Using Virtualenv
|
||||
|
||||
Alternatively, if you prefer `virtualenv`, you can install it first (if it's not already installed) and then create a new virtual environment as shown:
|
||||
|
||||
```bash
|
||||
# Install virtualenv if it is not already installed
|
||||
pip install virtualenv
|
||||
|
||||
# Create a new virtual environment named 'agentscope' with Python 3.9
|
||||
virtualenv agentscope --python=python3.9
|
||||
|
||||
# Activate the virtual environment
|
||||
source agentscope/bin/activate # On Windows use `agentscope\Scripts\activate`
|
||||
```
|
||||
|
||||
## Installing AgentScope
|
||||
|
||||
### Install with Pip
|
||||
|
||||
If you prefer to install AgentScope from Pypi, you can do so easily using `pip`:
|
||||
|
||||
```bash
|
||||
# For centralized multi-agent applications
|
||||
pip install agentscope --pre
|
||||
# For distributed multi-agent applications
|
||||
pip install agentscope[distribute] --pre # On Mac use `pip install agentscope\[distribute\] --pre`
|
||||
```
|
||||
|
||||
### Install from Source
|
||||
|
||||
For users who prefer to install AgentScope directly from the source code, follow these steps to clone the repository and install the platform in editable mode:
|
||||
|
||||
**_Note: This project is under active development, it's recommended to install AgentScope from source._**
|
||||
|
||||
```bash
|
||||
# Pull the source code from Github
|
||||
git clone https://github.com/modelscope/agentscope.git
|
||||
cd agentscope
|
||||
|
||||
# For centralized multi-agent applications
|
||||
pip install -e .
|
||||
# For distributed multi-agent applications
|
||||
pip install -e .[distribute] # On Mac use `pip install -e .\[distribute\]`
|
||||
```
|
||||
|
||||
**Note**: The `[distribute]` option installs additional dependencies required for distributed applications. Remember to activate your virtual environment before running these commands.
|
||||
|
||||
[[Return to the top]](#102-installation-en)
|
||||
|
|
@ -1,108 +0,0 @@
|
|||
(103-start-en)=
|
||||
|
||||
# Quick Start
|
||||
|
||||
AgentScope is designed with a flexible communication mechanism.
|
||||
In this tutorial, we will introduce the basic usage of AgentScope via a
|
||||
simple standalone conversation between two agents (e.g. user and assistant
|
||||
agents).
|
||||
|
||||
## Step1: Prepare Model
|
||||
|
||||
AgentScope decouples the deployment and invocation of models to better build multi-agent applications.
|
||||
|
||||
In terms of model deployment, users can use third-party model services such
|
||||
as OpenAI API, Google Gemini API, HuggingFace/ModelScope Inference API, or
|
||||
quickly deploy local open-source model services through the [scripts](https://github.com/modelscope/agentscope/blob/main/scripts/README.md) in
|
||||
the repository.
|
||||
|
||||
While for model invocation, users should prepare a model configuration to specify the model service. Taking OpenAI Chat API as an example, the model configuration is like this:
|
||||
|
||||
```python
|
||||
model_config = {
|
||||
"config_name": "{config_name}", # A unique name for the model config.
|
||||
"model_type": "openai_chat", # Choose from "openai_chat", "openai_dall_e", or "openai_embedding".
|
||||
|
||||
"model_name": "{model_name}", # The model identifier used in the OpenAI API, such as "gpt-3.5-turbo", "gpt-4", or "text-embedding-ada-002".
|
||||
"api_key": "xxx", # Your OpenAI API key. If unset, the environment variable OPENAI_API_KEY is used.
|
||||
"organization": "xxx", # Your OpenAI organization ID. If unset, the environment variable OPENAI_ORGANIZATION is used.
|
||||
}
|
||||
```
|
||||
|
||||
More details about model invocation, deployment and open-source models please refer to [Model](203-model-en) section.
|
||||
|
||||
After preparing the model configuration, you can register your configuration by calling the `init` method of AgentScope. Additionally, you can load multiple model configurations at once.
|
||||
|
||||
```python
|
||||
import agentscope
|
||||
|
||||
# init once by passing a list of config dict
|
||||
openai_cfg_dict = {
|
||||
# ...
|
||||
}
|
||||
modelscope_cfg_dict = {
|
||||
# ...
|
||||
}
|
||||
agentscope.init(model_configs=[openai_cfg_dict, modelscope_cfg_dict])
|
||||
```
|
||||
|
||||
## Step2: Create Agents
|
||||
|
||||
Creating agents is straightforward in AgentScope. After initializing AgentScope with your model configurations (Step 1 above), you can then define each agent with its corresponding role and specific model.
|
||||
|
||||
```python
|
||||
import agentscope
|
||||
from agentscope.agents import DialogAgent, UserAgent
|
||||
|
||||
# read model configs
|
||||
agentscope.init(model_configs="./openai_model_configs.json")
|
||||
|
||||
# Create a dialog agent and a user agent
|
||||
dialogAgent = DialogAgent(name="assistant", model_config_name="gpt-4", sys_prompt="You are a helpful ai assistant")
|
||||
userAgent = UserAgent()
|
||||
```
|
||||
|
||||
**NOTE**: Please refer to [Customizing Your Own Agent](201-agent-en) for all available agents.
|
||||
|
||||
## Step3: Agent Conversation
|
||||
|
||||
"Message" is the primary means of communication between agents in AgentScope. They are Python dictionaries comprising essential fields like the actual `content` of this message and the sender's `name`. Optionally, a message can include a `url` to either a local file (image, video or audio) or website.
|
||||
|
||||
```python
|
||||
from agentscope.message import Msg
|
||||
|
||||
# Example of a simple text message from Alice
|
||||
message_from_alice = Msg("Alice", "Hi!")
|
||||
|
||||
# Example of a message from Bob with an attached image
|
||||
message_from_bob = Msg("Bob", "What about this picture I took?", url="/path/to/picture.jpg")
|
||||
```
|
||||
|
||||
To start a conversation between two agents, such as `dialog_agent` and `user_agent`, you can use the following loop. The conversation continues until the user inputs `"exit"` which terminates the interaction.
|
||||
|
||||
```python
|
||||
x = None
|
||||
while True:
|
||||
x = dialogAgent(x)
|
||||
x = userAgent(x)
|
||||
|
||||
# Terminate the conversation if the user types "exit"
|
||||
if x.content == "exit":
|
||||
print("Exiting the conversation.")
|
||||
break
|
||||
```
|
||||
|
||||
For a more advanced approach, AgentScope offers the option of using pipelines to manage the flow of messages between agents. The `sequentialpipeline` stands for sequential speech, where each agent receive message from last agent and generate its response accordingly.
|
||||
|
||||
```python
|
||||
from agentscope.pipelines.functional import sequentialpipeline
|
||||
|
||||
# Execute the conversation loop within a pipeline structure
|
||||
x = None
|
||||
while x is None or x.content != "exit":
|
||||
x = sequentialpipeline([dialog_agent, user_agent])
|
||||
```
|
||||
|
||||
For more details about how to utilize pipelines for complex agent interactions, please refer to [Pipeline and MsgHub](202-pipeline-en).
|
||||
|
||||
[[Return to the top]](#103-start-en)
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
# Welcome to MemoryScope Tutorial
|
||||
|
||||
MemoryScope is an innovative multi-agent platform designed to empower developers to build multi-agent applications with ease, reliability, and high performance. It features three high-level capabilities:
|
||||
|
||||
- **Easy-to-Use**: Programming in pure Python with various prebuilt components for immediate use, suitable for developers or users with different levels of customization requirements.
|
||||
|
||||
- **High Robustness**: Supporting customized fault-tolerance controls and retry mechanisms to enhance application stability.
|
||||
|
||||
- **Actor-Based Distribution**: Enabling developers to build distributed multi-agent applications in a centralized programming manner for streamlined development.
|
||||
|
||||
## Tutorial Navigator
|
||||
|
||||
- [About MemoryScope](101-memoryscope.md)
|
||||
- [Installation](102-installation.md)
|
||||
- [Quick Start](103-example.md)
|
||||
|
|
@ -9,4 +9,5 @@ sphinx-autobuild
|
|||
sphinx_rtd_theme
|
||||
sphinxcontrib-mermaid
|
||||
myst-parser
|
||||
autodoc_pydantic
|
||||
autodoc_pydantic
|
||||
nbsphinx
|
||||
|
|
@ -39,11 +39,12 @@ extensions = [
|
|||
"sphinxcontrib.mermaid",
|
||||
"myst_parser",
|
||||
"sphinx.ext.autosectionlabel",
|
||||
'sphinxcontrib.autodoc_pydantic'
|
||||
"sphinxcontrib.autodoc_pydantic",
|
||||
"nbsphinx"
|
||||
]
|
||||
|
||||
autodoc_pydantic_model_show_json = True
|
||||
autodoc_pydantic_settings_show_json = True
|
||||
autodoc_pydantic_settings_show_json = True
|
||||
|
||||
# Prefix document path to section labels, otherwise autogenerated labels would
|
||||
# look like 'heading' rather than 'path/to/file:heading'
|
||||
|
|
@ -82,12 +83,15 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
|
|||
#
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
|
||||
# html_logo = "_static/logo.png"
|
||||
|
||||
# Add any paths that contain custom static files (such as style sheets) here,
|
||||
# relative to this directory. They are copied after the builtin static files,
|
||||
# so a file named "default.css" will overwrite the builtin "default.css".
|
||||
html_static_path = ["_static"]
|
||||
|
||||
html_theme_options = {
|
||||
# "logo_only": True,
|
||||
"navigation_depth": 4,
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -6,24 +6,44 @@
|
|||
:github_url: https://github.com/modelscope/memoryscope
|
||||
|
||||
MemoryScope 文档
|
||||
======================================
|
||||
=========================
|
||||
|
||||
欢迎浏览MemoryScope相关文档
|
||||
-------------------------------
|
||||
|
||||
.. include:: tutorial/main.md
|
||||
:parser: myst_parser.sphinx_
|
||||
.. image:: ./docs/images/logo_1.png
|
||||
:align: center
|
||||
|
||||
MemoryScope 是一个为LLM聊天机器人服务的强大且灵活的长期记忆系统。它由一个记忆数据库和三个可定制的系统操作组成，这些操作可以灵活组合，
|
||||
为您的LLM聊天机器人提供强大的长期记忆服务。
|
||||
|
||||
💾 记忆数据库:
|
||||
^^^^^^^^^^^^^
|
||||
|
||||
- MemoryScope 配备了一个 *ElasticSearch (ES)* 向量数据库，用于存储系统中记录的所有记忆片段。
|
||||
|
||||
🛠️ 系统操作:
|
||||
^^^^^^^^^^^^
|
||||
|
||||
- 记忆检索：当用户输入对话，此操作返回语义相关的记忆片段。如果输入对话包含对时间的指涉，则同时返回相应时间中的记忆片段。
|
||||
-
|
||||
- 记忆巩固：此操作接收一批用户的输入对话，并从对话中提取重要的用户信息，将其作为 *observation* 形式的记忆片段存储在记忆数据库中。
|
||||
-
|
||||
- 反思与再巩固：每隔一段时间，此操作对新记录的 *observations* 进行反思，以形成和更新 *insight* 形式的记忆片段。然后执行记忆再巩固，
|
||||
以确保记忆片段之间的矛盾和重复得到妥善处理。
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:hidden:
|
||||
:caption: MemoryScope Tutorial
|
||||
:maxdepth: 2
|
||||
:caption: MemoryScope 教程
|
||||
|
||||
tutorial/101-memoryscope.md
|
||||
tutorial/102-installation.md
|
||||
tutorial/103-example.md
|
||||
关于MemoryScope <README.md>
|
||||
🚀 安装 <docs/installation.md>
|
||||
命令行 <examples/cli/README.md>
|
||||
简例 <examples/api/simple_usages_cn.ipynb>
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 4
|
||||
:caption: MemoryScope API 文档
|
||||
:maxdepth: 6
|
||||
:caption: MemoryScope 接口
|
||||
|
||||
API <docs/api.rst>
|
||||
|
||||
api
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
(101-memoryscope-cn)=
|
||||
|
||||
# 关于memoryscope
|
||||
|
||||
TODO: 添加中文文档
|
||||
|
||||
[[Return to the top]](#101-memoryscope-cn)
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
(102-installation-cn)=
|
||||
|
||||
# 安装memoryscope
|
||||
|
||||
TODO: 添加中文文档
|
||||
|
||||
[[Return to the top]](#102-installation-cn)
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
(103-start-cn)=
|
||||
|
||||
# 如何使用
|
||||
TODO: 添加中文
|
||||
|
||||
[[Return to the top]](#103-start-cn)
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
# 欢迎来到 MemoryScope 教程
|
||||
|
||||
AgentScope是一款全新的Multi-Agent框架，专为应用开发者打造，旨在提供高易用、高可靠的编程体验！
|
||||
|
||||
- **高易用**：AgentScope支持纯Python编程，提供多种语法工具实现灵活的应用流程编排，内置丰富的API服务（Service）以及应用样例，供开发者直接使用。
|
||||
|
||||
- **高鲁棒**：确保开发便捷性和编程效率的同时，针对不同能力的大模型，AgentScope提供了全面的重试机制、定制化的容错控制和面向Agent的异常处理，以确保应用的稳定、高效运行；
|
||||
|
||||
- **基于Actor的分布式机制**：AgentScope设计了一种新的基于Actor的分布式机制，实现了复杂分布式工作流的集中式编程和自动并行优化，即用户可以使用中心化编程的方式完成分布式应用的流程编排，同时能够零代价将本地应用迁移到分布式的运行环境中。
|
||||
|
||||
## 教程大纲
|
||||
|
||||
- [关于AgentScope](101-memoryscope.md)
|
||||
- [安装](102-installation.md)
|
||||
- [快速开始](103-example.md)
|
||||
|
|
@ -2,9 +2,7 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# chat 和 service 接口的示例用法\n",
|
||||
"这个笔记本展示了 MemoryScope 的 **chat** 和 **service** 接口的简单用法，以及它的主要功能。\n",
|
||||
|
|
@ -14,9 +12,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 初始化一个 MemoryScope 实例\n",
|
||||
"首先，我们需要指定一个配置并初始化一个 MemoryScope 实例。\n",
|
||||
|
|
@ -26,14 +22,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:42:19.303078Z",
|
||||
"start_time": "2024-08-02T14:42:17.332785Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import sys\n",
|
||||
|
|
@ -59,9 +49,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 聊天（不含记忆）\n",
|
||||
"MemoryScope 配有默认的 chat 接口，因此开始聊天非常容易，就像使用任何大型语言模型聊天机器人一样。"
|
||||
|
|
@ -69,14 +57,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:42:24.843842Z",
|
||||
"start_time": "2024-08-02T14:42:19.304038Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -96,9 +78,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"你可以选择进行含有或不含有多轮对话上下文的聊天。然而，由于尚未调用**记忆巩固**功能，系统中还没有任何记忆片段。"
|
||||
|
|
@ -106,14 +86,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:42:33.777924Z",
|
||||
"start_time": "2024-08-02T14:42:24.845133Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -136,9 +110,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## **记忆巩固**\n",
|
||||
"现在，我们再聊多几句，然后尝试**记忆巩固**功能。"
|
||||
|
|
@ -146,14 +118,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:42:52.517936Z",
|
||||
"start_time": "2024-08-02T14:42:33.780200Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -183,14 +149,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:43:14.475175Z",
|
||||
"start_time": "2024-08-02T14:42:52.518868Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -212,9 +172,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"**记忆巩固**从用户的7条聊天消息中提取了3条 *observations* ，其余无效的信息被过滤掉了。\n",
|
||||
|
|
@ -224,14 +182,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:43:57.226685Z",
|
||||
"start_time": "2024-08-02T14:43:14.475977Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -283,14 +235,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:44:26.290389Z",
|
||||
"start_time": "2024-08-02T14:43:57.227597Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -309,9 +255,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"我们可以看到，**记忆巩固**成功过滤掉了虚假内容，并展示了良好的时间敏感性。\n",
|
||||
|
|
@ -321,14 +265,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:44:57.748723Z",
|
||||
"start_time": "2024-08-02T14:44:26.292543Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -370,14 +308,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:45:38.454853Z",
|
||||
"start_time": "2024-08-02T14:44:57.750558Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -401,9 +333,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## **反思与再巩固**\n",
|
||||
"现在，我们在系统中已经积累了足够多的新的 *observations* ，因此我们可以调用**反思与再巩固**功能，让我们看看会得到什么。"
|
||||
|
|
@ -411,14 +341,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:45:52.599528Z",
|
||||
"start_time": "2024-08-02T14:45:38.455556Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -447,9 +371,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 低用户时延（RT）\n",
|
||||
"\n",
|
||||
|
|
@ -459,9 +381,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import time\n",
|
||||
|
|
@ -483,14 +403,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:46:08.814486Z",
|
||||
"start_time": "2024-08-02T14:45:52.601688Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -540,9 +454,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"我们可以看到，从 MemoryScope 检索记忆片段不会增加聊天的响应时间。"
|
||||
|
|
@ -550,24 +462,13 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 更多用法\n",
|
||||
"我们建议读者参考[进阶自定义用法](./examples/api/advanced_customization_cn.ipynb)来对MemoryScope系统进行各种自定义设置。您还可以通过自定义**workflow**和对应的**worker**来创建或定制满足您特定需求的**operation**。\n",
|
||||
"\n",
|
||||
"此外，您还可以尝试使用[在命令行与MemoryScope聊天机器人交互](./examples/cli/dash_cli_cn1.sh)。我们在这里实现了始终在后台异步运行**记忆巩固**和**反思与再巩固**这两个操作，从而使得它们不会增加聊天的响应时间。"
|
||||
"此外，您还可以尝试使用[在命令行与MemoryScope聊天机器人交互](../cli/README.md)。我们在这里实现了始终在后台异步运行**记忆巩固**和**反思与再巩固**这两个操作，从而使得它们不会增加聊天的响应时间。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
@ -585,8 +486,7 @@
|
|||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython2",
|
||||
"version": "2.7.6"
|
||||
"pygments_lexer": "ipython2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
|
|
|||
|
|
@ -2,9 +2,7 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Example usages of **chat** and **service** interfaces\n",
|
||||
"This notebook shows simple usages of MemoryScope's **chat** and **service** interfaces, along with its main features.\n",
|
||||
|
|
@ -14,9 +12,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Initiate a MemoryScope instance\n",
|
||||
"First, we need to specify a configuration and initiate a MemoryScope instance.\n",
|
||||
|
|
@ -25,14 +21,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:34:30.387354Z",
|
||||
"start_time": "2024-08-02T14:34:28.512658Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import sys\n",
|
||||
|
|
@ -58,9 +48,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Chat without memory\n",
|
||||
"MemoryScope comes with a default **chat** interface, so it's very easy to start chatting, just as what you'll do with any LLM chatbot."
|
||||
|
|
@ -68,14 +56,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:34:35.313590Z",
|
||||
"start_time": "2024-08-02T14:34:30.388733Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -95,9 +77,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"You can choose to chat with or without multi-round conversation contexts. However, since **Memory Consolidation** has not been called, there's no memory pieces in the system yet."
|
||||
|
|
@ -105,14 +85,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:34:42.621918Z",
|
||||
"start_time": "2024-08-02T14:34:35.315441Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -135,9 +109,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Memory Consolidation\n",
|
||||
"Now, we do a bit more chatting and then try out **Memory Consolidation**."
|
||||
|
|
@ -145,14 +117,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:35:07.399702Z",
|
||||
"start_time": "2024-08-02T14:34:42.622804Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -182,14 +148,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:35:42.560772Z",
|
||||
"start_time": "2024-08-02T14:35:07.401224Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -211,9 +171,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"**Memory Consolidation** extracted 3 *observations* out of the 7 chat messages from the user, with the uninformative ones being filtered out.\n",
|
||||
|
|
@ -223,14 +181,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:36:30.548435Z",
|
||||
"start_time": "2024-08-02T14:35:42.559854Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -294,14 +246,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:37:04.220392Z",
|
||||
"start_time": "2024-08-02T14:36:30.549719Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -322,9 +268,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"We can see **Memory Consolidation** successfully filtered out fictitious contents, and shows good time sensitivity.\n",
|
||||
|
|
@ -334,14 +278,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:37:25.239829Z",
|
||||
"start_time": "2024-08-02T14:37:04.221032Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -383,14 +321,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:38:05.369583Z",
|
||||
"start_time": "2024-08-02T14:37:25.241674Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -413,9 +345,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Reflection and Re-Consolidation\n",
|
||||
"Now, we have accumulated enough new *observations* in the system, so we can call **Reflection and Re-Consolidation**, let's see what will it get."
|
||||
|
|
@ -423,14 +353,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:38:27.126860Z",
|
||||
"start_time": "2024-08-02T14:38:05.370326Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -463,9 +387,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Low response-time (RT) for the user\n",
|
||||
"Finally, we test the RT of MemoryScope system for the user. Specifically, we test the difference of RT when responding with and without retrieving memory pieces from the system."
|
||||
|
|
@ -474,9 +396,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import time\n",
|
||||
|
|
@ -498,14 +418,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-08-02T14:38:46.158169Z",
|
||||
"start_time": "2024-08-02T14:38:27.128634Z"
|
||||
},
|
||||
"collapsed": false
|
||||
},
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
|
|
@ -557,9 +471,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"----\n",
|
||||
"We can see responding with retrieving memory pieces from MemoryScope does not increase RT."
|
||||
|
|
@ -567,25 +479,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## More Examples\n",
|
||||
"We direct the reader to [Advanced Customization](./examples/api/advanced_customization_en.ipynb) for guidance on customizing the various settings of the MemoryScope system. It is also possible to create or customize your own MemoryScope **operations** by specifying a **workflow** and the corresponding **workers** that best meet your specific needs.\n",
|
||||
"\n",
|
||||
"Additionally, you can also try out the [CLI with a MemoryScope Chatbot](./examples/cli/dash_cli_cn1.sh). We have implemented the chatbot so that the **Memory Consolidation** and **Reflection and Re-Consolidation** operations are always run asynchronously in the backend, ensuring that they do not incur any response time for the user.\n",
|
||||
"Additionally, you can also try out the [CLI with a MemoryScope Chatbot](../cli/README.md). We have implemented the chatbot so that the **Memory Consolidation** and **Reflection and Re-Consolidation** operations are always run asynchronously in the backend, ensuring that they do not incur any response time for the user.\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
@ -603,8 +504,7 @@
|
|||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython2",
|
||||
"version": "2.7.6"
|
||||
"pygments_lexer": "ipython2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue