Skip to content
Merged
Changes from all commits
Commits
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
28 changes: 17 additions & 11 deletions docs/tools/tool/agentql.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -4,22 +4,23 @@ description: Precise web data extraction for agents
icon: browser
---

AgentQL Web Loader is a tool that Scrape a url with a given AgentQL query or a natural language description of the data you want to scrape.
AgentQL Web Loader is a tool that scrapes a URL with a given AgentQL query or a Natural Language description of the data you want to scrape.
Create your own AgentQL API key [here](https://dev.agentql.com).

## Description
AgentQL Web Loader is powered by AgentQL, an AI-powered query language for scraping web sites and automating workflows.
If you want to extract data in a precise format, use AgentQL natural language queries under the `query` field to pinpoint data on any web page, including authenticated and dynamically generated content.

AgentQL Web Loader is powered by AgentQL, an AI-powered query language for scraping web sites and automating workflows.
If you want to extract data in a precise format, use [AgentQL query language](https://docs.agentql.com/agentql-query) under the `query` field to pinpoint data on any web page, including authenticated and dynamically generated content.
Users can define structured data output and apply transforms within queries.
You could also directly describe the data you want to extract under the `prompt` field to let AgentQL Web Loader automatically generate the format and data.
You could also directly describe the data you want to extract under the `prompt` field to let AgentQL Web Loader automatically generate the format and data.

## Installation

```bash
agentstack tools add agentql
```

Set the environment variable
Set the environment variable in your project's `.env` file.

```env
AGENTQL_API_KEY=...
Expand All @@ -29,10 +30,15 @@ AGENTQL_API_KEY=...

The following parameters can be used to customize the `AgentQL Web Loader`'s behavior:

| Argument | Type | Description |
|:---------------|:---------|:-------------------------------------------------------------------------------------------------------------------------------------|
| **url** | `string` | Url of the website to scrape from. |
| **query** | `string` | _Optional_. AgentQL query to scrape the url. Please visit [AgentQL Query Language Introduction](https://docs.agentql.com/agentql-query) for more information. |
| **prompt** | `string` | _Optional_. Natural language description of the data you want to scrape. Either `query` or `prompt` is required. |
| Argument | Type | Description |
| :--------- | :------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **url** | `string` | URL of the website to scrape from. |
| **query** | `string` | _Optional_. AgentQL query to scrape the URL. Please visit [AgentQL Query Language Introduction](https://docs.agentql.com/agentql-query) for more information. |
| **prompt** | `string` | _Optional_. Natural Language description of the data you want to scrape. Either `query` or `prompt` is required. |

If you want to hack our tool, feel free to do so by modifying `src/tools/agentql_tool.py` and reference our documentation for [AgentQL REST API](https://docs.agentql.com/rest-api/api-reference).

## Examples

If you want to hack our tool, feel free to do so by modifying `src/tools/agentql_tool.py` and reference our documentation for [AgentQL REST API](https://docs.agentql.com/rest-api/api-reference).
- [Research Assistant](https://github.com/AgentOps-AI/AgentStack/tree/main/examples/research_assistant)
- [Sentiment Analyzer](https://github.com/AgentOps-AI/AgentStack/tree/main/examples/sentiment_analyser)
Loading