Metadata-Version: 2.4
Name: llama-index-tools-olostep
Version: 0.1.0
Summary: llama-index tools olostep integration
Project-URL: Homepage, https://www.olostep.com
Project-URL: Repository, https://github.com/olostep-api/llama-index-tools-olostep
Author: Olostep
License-Expression: MIT
Keywords: data extraction,olostep,web crawling,web scraping,web search
Requires-Python: <4.0,>=3.9
Requires-Dist: llama-index-core>=0.11.0
Requires-Dist: olostep
Description-Content-Type: text/markdown

# LlamaIndex Tools Integration: Olostep

[Olostep](https://www.olostep.com) is web scraping, crawling, and search
infrastructure built for AI agents. This tool gives a LlamaIndex agent live
web access — scrape any URL to clean markdown, run a web search, get an
AI-grounded answer with sources, and crawl a website.

To get started, get an API key from the
[Olostep dashboard](https://www.olostep.com/dashboard/api-keys).

## Installation

```bash
pip install llama-index-tools-olostep
```

## Usage

Here's an example usage of the `OlostepToolSpec`:

```python
from llama_index.tools.olostep import OlostepToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

olostep_tool = OlostepToolSpec(
    api_key="your-olostep-api-key",
)

agent = FunctionAgent(
    tools=olostep_tool.to_tool_list(),
    llm=OpenAI(model="gpt-4o"),
)

await agent.run("Scrape https://example.com and summarize the main heading")
```

## Available tools

- **`scrape`** — Scrape a single URL and return its content as clean markdown.
- **`search`** — Search the web for a query and return the ranked results.
- **`answer`** — Get an AI-grounded answer to a question, synthesized from live
  web sources with citations.
- **`crawl`** — Crawl a website starting from a URL and return the pages'
  content.

This tool has a more extensive example usage documented in a Jupyter notebook
[here](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-olostep/examples/olostep.ipynb).
