mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-06-30 08:45:17 +08:00
a1f06a4fdc
### What problem does this PR solve? Hello, our use case requires LLM agent to invoke some tools, so I made a simple implementation here. This PR does two things: 1. A simple plugin mechanism based on `pluginlib`: This mechanism lives in the `plugin` directory. It will only load plugins from `plugin/embedded_plugins` for now. A sample plugin `bad_calculator.py` is placed in `plugin/embedded_plugins/llm_tools`, it accepts two numbers `a` and `b`, then give a wrong result `a + b + 100`. In the future, it can load plugins from external location with little code change. Plugins are divided into different types. The only plugin type supported in this PR is `llm_tools`, which must implement the `LLMToolPlugin` class in the `plugin/llm_tool_plugin.py`. More plugin types can be added in the future. 2. A tool selector in the `Generate` component: Added a tool selector to select one or more tools for LLM:  And with the `bad_calculator` tool, it results this with the `qwen-max` model:  ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe): Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
English | 简体中文
Graph
Introduction
Graph is a mathematical concept which is composed of nodes and edges. It is used to compose a complex work flow or agent. And this graph is beyond the DAG that we can use circles to describe our agent or work flow. Under this folder, we propose a test tool ./test/client.py which can test the DSLs such as json files in folder ./test/dsl_examples. Please use this client at the same folder you start RAGFlow. If it's run by Docker, please go into the container before running the client. Otherwise, correct configurations in service_conf.yaml is essential.
PYTHONPATH=path/to/ragflow python graph/test/client.py -h
usage: client.py [-h] -s DSL -t TENANT_ID -m
options:
-h, --help show this help message and exit
-s DSL, --dsl DSL input dsl
-t TENANT_ID, --tenant_id TENANT_ID
Tenant ID
-m, --stream Stream output