Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
21 commits
Select commit Hold shift + click to select a range
fabd365
feat: implement lattes navigator tool and api ready for deployment
rubenszinho Dec 7, 2025
3258b50
fix: remove non-root user (was causing permission issues with playwri…
rubenszinho Dec 7, 2025
8854ff1
chore: add debug route to validate browser-use problem
rubenszinho Dec 7, 2025
eade592
fix: import ChatOpenAI from browser_use (not langchain_openai) remove…
rubenszinho Dec 7, 2025
c258255
chore: run first tests with current version and document it
rubenszinho Dec 7, 2025
4089015
feat: Optimize prompts
rubenszinho Dec 7, 2025
6a22ccd
chore: add raw json capture from agent response
rubenszinho Dec 7, 2025
dea82a6
chore: handle captcha lattes anti-bot protection
rubenszinho Dec 7, 2025
1183746
fix: improve project and advising status handling in lattes navigator…
rubenszinho Dec 7, 2025
a6785fc
chore: create a simple navigator testing demo for local validation
rubenszinho Dec 7, 2025
6feff41
refactor: enhance JSON extraction logic in Lattes navigator tool to c…
rubenszinho Dec 7, 2025
bc89a5a
update: update testing file to include latest changes to api. clarify…
rubenszinho Dec 7, 2025
4903023
refactor: update task instructions for Lattes CV extraction to dont n…
rubenszinho Dec 7, 2025
87f3b93
refactor: enhance Lattes CV extraction process with improved navigati…
rubenszinho Dec 7, 2025
8cce43a
refactor: update Lattes CV extraction task to follow natural navigati…
rubenszinho Dec 7, 2025
19d1a25
feat: include cloud browser to avoid captcha triggers
rubenszinho Dec 7, 2025
d62d341
refactor: streamline Lattes CV extraction instructions with clearer n…
rubenszinho Dec 7, 2025
ee3ef3c
fix: fix Lattes CV extraction process by removing unnecessary wait in…
rubenszinho Dec 7, 2025
ec33230
feat: enhance Lattes CV extraction by adding coauthor extraction, ded…
rubenszinho Dec 7, 2025
ed7e7b0
refactor: improve Lattes CV extraction by adding error handling for w…
rubenszinho Dec 8, 2025
ddb016d
feat: enhance Lattes CV extraction by implementing a structured appro…
rubenszinho Dec 8, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -1,3 +1,2 @@
.venv/
.webui_secret_key
datasets/
.webui_secret_key
1 change: 1 addition & 0 deletions .python-version
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
3.11.8
3 changes: 3 additions & 0 deletions agents4gov/.gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
.venv/
.webui_secret_key
datasets/
91 changes: 91 additions & 0 deletions agents4gov/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@

# Agents4Gov

**Laboratory of Computational Intelligence (LABIC – ICMC/USP)**


## Overview

**Agents4Gov** is a research and development project from **LABIC – Institute of Mathematics and Computer Sciences (ICMC/USP)** focused on building **LLM-based tools** to support and modernize **public sector services**.
The project emphasizes **local Large Language Models (LLMs)** for privacy, **data anonymization**, and the **development and evaluation of tools** for use in government and institutional environments.

---

## Installation

### 1. Install the Open WebUI Server

Agents4Gov is built on top of the **[Open WebUI](https://github.com/open-webui/open-webui)** framework, which serves as the base environment for loading and running tools.

Before starting, ensure you are using **Python 3.11** to avoid compatibility issues.

To install and run Open WebUI:

```bash
# Install Open WebUI
pip install open-webui

# Start the server
open-webui serve
```

After starting, the Open WebUI interface will be available at:
👉 **[http://localhost:8080](http://localhost:8080)**

---

### 2. Clone the Agents4Gov Repository

In the same environment, clone the Agents4Gov repository:

```bash
git clone https://github.com/icmc-usp/Agents4Gov.git
```

The `tools/` directory inside the repository contains all implemented tools.

---

### 3. Import Tools into Open WebUI

Once Open WebUI is running:

1. Access the **Tools** module in the Open WebUI interface.
2. Use the **Import Tool** option to add any of the tools from the `Agents4Gov/tools/` directory.
3. Each tool has its own documentation and configuration guide within its folder.

Example:

```bash
ls Agents4Gov/tools/
```

Each subdirectory corresponds to an individual tool that can be imported, executed, and evaluated directly within Open WebUI.

---

## Repository Structure

```
Agents4Gov/
├── tools/ # Implemented tools for public services
├── data/ # Example or anonymized datasets
├── docs/ # Documentation and evaluation reports
├── config/ # Model and system configuration files
└── README.md
```

---

## Objectives

* Develop and evaluate **LLM-based tools** focused on **public sector innovation**.
* Ensure **privacy-preserving** AI development using local LLMs and anonymized data.
* Provide a **modular and extensible** framework for integrating intelligent tools into public service environments.

---

## License

This project is licensed under the **MIT License**.
See the [LICENSE](LICENSE) file for details.
1 change: 1 addition & 0 deletions agents4gov/config/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@

1 change: 1 addition & 0 deletions agents4gov/data/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@

52 changes: 52 additions & 0 deletions agents4gov/docs/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
# Agents4Gov Documentation

Welcome to the Agents4Gov documentation. This directory contains guides and tutorials to help you work with the framework.

## Project Structure

Agents4Gov is built on top of **[Open WebUI](https://github.com/open-webui/open-webui)**, a framework for running LLM-based applications with tool integration.

```
Agents4Gov/
├── tools/ # Implemented tools for public services
├── data/ # Example or anonymized datasets
├── docs/ # Documentation and evaluation reports
├── config/ # Model and system configuration files
└── README.md # Main project documentation
```

### Key Directories

- **`tools/`** - Contains all tool implementations that can be imported into Open WebUI. Each tool is a Python class that provides specific functionality to agents.
- **`data/`** - Stores datasets used for testing and evaluation, with privacy-preserving anonymization.
- **`docs/`** - Documentation, tutorials, and research reports.
- **`config/`** - Configuration files for models and system settings.

## Available Documentation

- **[How to Create a Tool](how_to_create_tool.md)** - A comprehensive step-by-step guide for creating custom tools that can be used by agents. Learn about tool structure, parameter validation, error handling, and best practices. Reference implementation: `tools/open_alex_doi.py`

## External Resources

### Open WebUI Documentation

Agents4Gov tools are designed to run within Open WebUI. For understanding the underlying framework:

- **[Open WebUI GitHub](https://github.com/open-webui/open-webui)** - Main repository and source code
- **[Open WebUI Documentation](https://docs.openwebui.com/)** - Official documentation for installation, configuration, and usage
- **[Open WebUI Tools Guide](https://docs.openwebui.com/features/plugin/tools)** - Specific documentation on how tools work within Open WebUI

### Getting Started with Open WebUI

1. Install Open WebUI: `pip install open-webui`
2. Start the server: `open-webui serve`
3. Access the interface at [http://localhost:8080](http://localhost:8080)
4. Import Agents4Gov tools through the Tools module in the UI

## Contributing

When adding new documentation:
1. Create your markdown file in this `docs/` directory
2. Update this README.md with a link to your new document
3. Use clear, descriptive titles and include practical examples
4. Follow the structure and style of existing documentation
Loading