mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-08-28 05:25:04 +00:00
docs: update documentation structure and content
This commit is contained in:
jinli.yl
parent
82d0adc86e
commit
c314a82039
6 changed files with 145 additions and 87 deletions
3
.gitignore
vendored
3
.gitignore
vendored
|
|
@ -28,4 +28,5 @@ cookbook/appworld/exp_result/*
|
|||
file_vector_store/*
|
||||
cookbook/appworld/file_vector_store/*
|
||||
/.venv/
|
||||
site/*
|
||||
site/*
|
||||
docs/_build/*
|
||||
|
|
@ -19,6 +19,9 @@ execute:
|
|||
parse:
|
||||
myst_enable_extensions:
|
||||
- colon_fence
|
||||
- deflist
|
||||
- attrs_inline
|
||||
- dollarmath
|
||||
|
||||
# Define the name of the latex output file for PDF builds
|
||||
latex:
|
||||
|
|
|
|||
|
|
@ -31,11 +31,6 @@ parts:
|
|||
- file: tool_memory/tool_summary_ops
|
||||
- file: tool_memory/tool_bench
|
||||
|
||||
- caption: SOP Memory
|
||||
maxdepth: 1
|
||||
chapters:
|
||||
- file: sop_memory/making_sop_memories
|
||||
|
||||
- caption: Extensions
|
||||
maxdepth: 1
|
||||
chapters:
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ kernelspec:
|
|||
|
||||
<div class="flex justify-center space-x-3">
|
||||
<a href="https://pypi.org/project/reme-ai/"><img src="https://img.shields.io/badge/python-3.12+-blue" alt="Python Version"></a>
|
||||
<a href="https://pypi.org/project/reme-ai/"><img src="https://img.shields.io/badge/pypi-v0.1-blue?logo=pypi" alt="PyPI Version"></a>
|
||||
<a href="https://pypi.org/project/reme-ai/"><img src="https://img.shields.io/badge/pypi-v0.1.10.3-blue?logo=pypi" alt="PyPI Version"></a>
|
||||
<a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-black" alt="License"></a>
|
||||
<a href="https://github.com/modelscope/ReMe"><img src="https://img.shields.io/github/stars/modelscope/ReMe?style=social" alt="GitHub Stars"></a>
|
||||
</div>
|
||||
|
|
@ -41,44 +41,45 @@ Personal memory helps "**understand user preferences**", task memory helps agent
|
|||
|
||||
ReMe integrates three complementary memory capabilities:
|
||||
|
||||
```{admonition} Task Memory/Experience
|
||||
:::{admonition} Task Memory/Experience
|
||||
:class: note
|
||||
|
||||
Procedural knowledge reused across agents
|
||||
Procedural knowledge reused across agents
|
||||
|
||||
- **Success Pattern Recognition**: Identify effective strategies and understand their underlying principles
|
||||
- **Failure Analysis Learning**: Learn from mistakes and avoid repeating the same issues
|
||||
- **Comparative Patterns**: Different sampling trajectories provide more valuable memories through comparison
|
||||
- **Validation Patterns**: Confirm the effectiveness of extracted memories through validation modules
|
||||
- **Success Pattern Recognition**: Identify effective strategies and understand their underlying principles
|
||||
- **Failure Analysis Learning**: Learn from mistakes and avoid repeating the same issues
|
||||
- **Comparative Patterns**: Different sampling trajectories provide more valuable memories through comparison
|
||||
- **Validation Patterns**: Confirm the effectiveness of extracted memories through validation modules
|
||||
|
||||
```
|
||||
:::
|
||||
|
||||
Learn more about how to use task memory from [task memory](task_memory/task_memory.md)
|
||||
|
||||
```{admonition} Personal Memory
|
||||
:::{admonition} Personal Memory
|
||||
:class: note
|
||||
|
||||
Contextualized memory for specific users
|
||||
|
||||
Contextualized memory for specific users
|
||||
- **Individual Preferences**: User habits, preferences, and interaction styles
|
||||
- **Contextual Adaptation**: Intelligent memory management based on time and context
|
||||
- **Progressive Learning**: Gradually build deep understanding through long-term interaction
|
||||
- **Time Awareness**: Time sensitivity in both retrieval and integration
|
||||
|
||||
|
||||
- **Individual Preferences**: User habits, preferences, and interaction styles
|
||||
- **Contextual Adaptation**: Intelligent memory management based on time and context
|
||||
- **Progressive Learning**: Gradually build deep understanding through long-term interaction
|
||||
- **Time Awareness**: Time sensitivity in both retrieval and integration
|
||||
|
||||
```
|
||||
:::
|
||||
|
||||
Learn more about how to use personal memory from [personal memory](personal_memory/personal_memory.md)
|
||||
|
||||
```{admonition} Tool Memory
|
||||
:::{admonition} Tool Memory
|
||||
:class: note
|
||||
|
||||
Data-driven tool selection and usage optimization
|
||||
Data-driven tool selection and usage optimization
|
||||
|
||||
- **Historical Performance Tracking**: Success rates, execution times, and token costs from real usage
|
||||
- **LLM-as-Judge Evaluation**: Qualitative insights on why tools succeed or fail
|
||||
- **Parameter Optimization**: Learn optimal parameter configurations from successful calls
|
||||
- **Dynamic Guidelines**: Transform static tool descriptions into living, learned manuals
|
||||
- **Historical Performance Tracking**: Success rates, execution times, and token costs from real usage
|
||||
- **LLM-as-Judge Evaluation**: Qualitative insights on why tools succeed or fail
|
||||
- **Parameter Optimization**: Learn optimal parameter configurations from successful calls
|
||||
- **Dynamic Guidelines**: Transform static tool descriptions into living, learned manuals
|
||||
|
||||
```
|
||||
:::
|
||||
|
||||
Learn more about how to use tool memory from [tool memory](tool_memory/tool_memory.md)
|
||||
|
||||
|
|
|
|||
|
|
@ -42,6 +42,27 @@ reme \
|
|||
|
||||
`````{tab-set}
|
||||
|
||||
````{tab-item} python(http)
|
||||
```{code-block}
|
||||
import requests
|
||||
|
||||
# Experience Summarizer: Learn from execution trajectories
|
||||
response = requests.post("http://localhost:8002/summary_task_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"trajectories": [
|
||||
{"messages": [{"role": "user", "content": "Help me create a project plan"}], "score": 1.0}
|
||||
]
|
||||
})
|
||||
|
||||
# Retriever: Get relevant memories
|
||||
response = requests.post("http://localhost:8002/retrieve_task_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"query": "How to efficiently manage project progress?",
|
||||
"top_k": 1
|
||||
})
|
||||
```
|
||||
````
|
||||
|
||||
````{tab-item} python(import)
|
||||
```{code-block}
|
||||
import asyncio
|
||||
|
|
@ -82,27 +103,6 @@ if __name__ == "__main__":
|
|||
```
|
||||
````
|
||||
|
||||
````{tab-item} python(http)
|
||||
```{code-block}
|
||||
import requests
|
||||
|
||||
# Experience Summarizer: Learn from execution trajectories
|
||||
response = requests.post("http://localhost:8002/summary_task_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"trajectories": [
|
||||
{"messages": [{"role": "user", "content": "Help me create a project plan"}], "score": 1.0}
|
||||
]
|
||||
})
|
||||
|
||||
# Retriever: Get relevant memories
|
||||
response = requests.post("http://localhost:8002/retrieve_task_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"query": "How to efficiently manage project progress?",
|
||||
"top_k": 1
|
||||
})
|
||||
```
|
||||
````
|
||||
|
||||
````{tab-item} curl
|
||||
```bash
|
||||
# Experience Summarizer: Learn from execution trajectories
|
||||
|
|
@ -164,11 +164,37 @@ fetch("http://localhost:8002/retrieve_task_memory", {
|
|||
|
||||
#### Personal Memory Management
|
||||
|
||||
<summary> import version</summary>
|
||||
`````{tab-set}
|
||||
|
||||
````{tab-item} Python(import)
|
||||
```{code-cell}
|
||||
````{tab-item} python(http)
|
||||
```{code-block}
|
||||
import requests
|
||||
|
||||
# Memory Integration: Learn from user interactions
|
||||
response = requests.post("http://localhost:8002/summary_personal_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"trajectories": [
|
||||
{"messages":
|
||||
[
|
||||
{"role": "user", "content": "I like to drink coffee while working in the morning"},
|
||||
{"role": "assistant",
|
||||
"content": "I understand, you prefer to start your workday with coffee to stay energized"}
|
||||
]
|
||||
}
|
||||
]
|
||||
})
|
||||
|
||||
# Memory Retrieval: Get personal memory fragments
|
||||
response = requests.post("http://localhost:8002/retrieve_personal_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"query": "What are the user's work habits?",
|
||||
"top_k": 5
|
||||
})
|
||||
```
|
||||
````
|
||||
|
||||
````{tab-item} python(import)
|
||||
```{code-block}
|
||||
import asyncio
|
||||
from reme_ai import ReMeApp
|
||||
|
||||
|
|
@ -208,32 +234,7 @@ if __name__ == "__main__":
|
|||
```
|
||||
````
|
||||
|
||||
|
||||
```{code-cell}
|
||||
# Memory Integration: Learn from user interactions
|
||||
response = requests.post("http://localhost:8002/summary_personal_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"trajectories": [
|
||||
{"messages":
|
||||
[
|
||||
{"role": "user", "content": "I like to drink coffee while working in the morning"},
|
||||
{"role": "assistant",
|
||||
"content": "I understand, you prefer to start your workday with coffee to stay energized"}
|
||||
]
|
||||
}
|
||||
]
|
||||
})
|
||||
|
||||
# Memory Retrieval: Get personal memory fragments
|
||||
response = requests.post("http://localhost:8002/retrieve_personal_memory", json={
|
||||
"workspace_id": "task_workspace",
|
||||
"query": "What are the user's work habits?",
|
||||
"top_k": 5
|
||||
})
|
||||
```
|
||||
|
||||
````{dropdown} curl version
|
||||
|
||||
````{tab-item} curl
|
||||
```bash
|
||||
# Memory Integration: Learn from user interactions
|
||||
curl -X POST http://localhost:8002/summary_personal_memory \
|
||||
|
|
@ -259,8 +260,7 @@ curl -X POST http://localhost:8002/retrieve_personal_memory \
|
|||
```
|
||||
````
|
||||
|
||||
````{dropdown} Node.js version
|
||||
|
||||
````{tab-item} Node.js
|
||||
```{code-block} javascript
|
||||
// Memory Integration: Learn from user interactions
|
||||
fetch("http://localhost:8002/summary_personal_memory", {
|
||||
|
|
@ -297,11 +297,15 @@ fetch("http://localhost:8002/retrieve_personal_memory", {
|
|||
.then(data => console.log(data));
|
||||
```
|
||||
````
|
||||
`````
|
||||
|
||||
|
||||
#### Tool Memory Management
|
||||
|
||||
```{code-cell}
|
||||
`````{tab-set}
|
||||
|
||||
````{tab-item} python(http)
|
||||
```{code-block}
|
||||
import requests
|
||||
|
||||
# Record tool execution results
|
||||
|
|
@ -332,10 +336,59 @@ response = requests.post("http://localhost:8002/retrieve_tool_memory", json={
|
|||
"tool_names": "web_search"
|
||||
})
|
||||
```
|
||||
````
|
||||
|
||||
````{tab-item} python(import)
|
||||
```{code-block}
|
||||
import asyncio
|
||||
from reme_ai import ReMeApp
|
||||
|
||||
````{dropdown} curl version
|
||||
async def main():
|
||||
async with ReMeApp(
|
||||
"llm.default.model_name=qwen3-30b-a3b-thinking-2507",
|
||||
"embedding_model.default.model_name=text-embedding-v4",
|
||||
"vector_store.default.backend=memory"
|
||||
) as app:
|
||||
# Record tool execution results
|
||||
result = await app.async_execute(
|
||||
name="add_tool_call_result",
|
||||
workspace_id="tool_workspace",
|
||||
tool_call_results=[
|
||||
{
|
||||
"create_time": "2025-10-21 10:30:00",
|
||||
"tool_name": "web_search",
|
||||
"input": {"query": "Python asyncio tutorial", "max_results": 10},
|
||||
"output": "Found 10 relevant results...",
|
||||
"token_cost": 150,
|
||||
"success": True,
|
||||
"time_cost": 2.3
|
||||
}
|
||||
]
|
||||
)
|
||||
print(result)
|
||||
|
||||
# Generate usage guidelines from history
|
||||
result = await app.async_execute(
|
||||
name="summary_tool_memory",
|
||||
workspace_id="tool_workspace",
|
||||
tool_names="web_search"
|
||||
)
|
||||
print(result)
|
||||
|
||||
# Retrieve tool guidelines before use
|
||||
result = await app.async_execute(
|
||||
name="retrieve_tool_memory",
|
||||
workspace_id="tool_workspace",
|
||||
tool_names="web_search"
|
||||
)
|
||||
print(result)
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
```
|
||||
````
|
||||
|
||||
````{tab-item} curl
|
||||
```bash
|
||||
# Record tool execution results
|
||||
curl -X POST http://localhost:8002/add_tool_call_result \
|
||||
|
|
@ -373,8 +426,7 @@ curl -X POST http://localhost:8002/retrieve_tool_memory \
|
|||
```
|
||||
````
|
||||
|
||||
````{dropdown} Node.js version
|
||||
|
||||
````{tab-item} Node.js
|
||||
```{code-block} javascript
|
||||
// Record tool execution results
|
||||
fetch("http://localhost:8002/add_tool_call_result", {
|
||||
|
|
@ -428,4 +480,5 @@ fetch("http://localhost:8002/retrieve_tool_memory", {
|
|||
.then(response => response.json())
|
||||
.then(data => console.log(data));
|
||||
```
|
||||
````
|
||||
````
|
||||
`````
|
||||
|
|
@ -27,6 +27,11 @@ dependencies = [
|
|||
"flowllm[reme]>=0.1.11.3",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
dev = ["jupyter-book", "ghp-import", "myst-nb", "sphinxcontrib-bibtex", "furo", "sphinxcontrib-mermaid"]
|
||||
|
||||
all = ["reme_ai[dev]"]
|
||||
|
||||
[tool.setuptools.packages.find]
|
||||
where = ["."]
|
||||
include = ["reme_ai*"]
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue