AIbase
EN
Home
All Categories
AI search
Level Navi Agent Search
Level-Navi Agent-Search
L
Level Navi Agent Search
AI searchResearch tools#Large Language Model#Web Search#Dataset#Zero-shot Learning#Few-shot LearningStandard PicksOpen Source
Overview :
Level-Navi Agent is an open-source general-purpose web search agent framework that can decompose complex problems and progressively search for information on the internet until it answers user questions. By providing the Web24 dataset, covering five major fields: finance, games, sports, movies, and events, it provides a benchmark for evaluating model performance on search tasks. The framework supports zero-shot and few-shot learning, providing an important reference for the application of large language models in the field of Chinese web search agents.
Target Users :
Level-Navi Agent is suitable for researchers and developers to evaluate and develop large language models for Chinese web search tasks. It provides a standardized evaluation tool for the model's search capabilities, helping to optimize model performance.
Total Visits： 492.1M
Top Region： US(19.34%)
Website Views ： 52.7K
Use Cases
Using the Level-Navi Agent framework, researchers can quickly evaluate the performance of different large language models on Chinese web search tasks.
Developers can use this framework to develop personalized web search agents to improve search efficiency.
Combined with the Web24 dataset, models can be trained and optimized for search tasks in areas such as finance, games, and sports.
Features
Supports zero-shot and few-shot learning, adapting to different model needs.
Provides the Web24 dataset, covering five major fields: finance, games, sports, movies, and events.
Compatible with multiple large language models, allowing for flexible deployment.
Progressive search capability, accurately understanding complex problems.
Open-source framework, easy for developers to extend and customize.
How to Use
1. Clone the project: Obtain the code via `git clone https://github.com/chuanruihu/Level-Navi-Agent-Search.git`.
2. Create a Python virtual environment: Create an environment using `conda create --name ai_search python=3.11`.
3. Install dependencies: After entering the project directory, run `pip install -r requirements.txt` to install dependencies.
4. Configure the search engine API: Set the Bing API Key in the configuration file.
5. Start testing: Run the example code `python terminal.py` to perform a test.
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase