Skip to content

Commit b8ecc28

Browse files
ohlavaMQ37jirispilkadirkbrnd
authored
Add better Apify integration docs with more examples (#183)
This edit is connected with an updated version of the actual implementation in the Agno main repository [PR#2566](agno-agi/agno#2566). Later we will follow with adding Agno implementation into the Apify docs as well. --------- Co-authored-by: Jakub Kopecký <[email protected]> Co-authored-by: Jiří Spilka <[email protected]> Co-authored-by: Dirk Brand <[email protected]>
1 parent 3349ade commit b8ecc28

File tree

1 file changed

+131
-22
lines changed

1 file changed

+131
-22
lines changed

‎tools/toolkits/others/apify.mdx

Lines changed: 131 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -2,48 +2,157 @@
22
title: Apify
33
---
44

5-
**ApifyTools** enable an Agent to access the Apify API and run actors.
5+
This guide demonstrates how to integrate and use [Apify](https://apify.com/actors) Actors within the Agno framework to enhance your AI agents with web scraping, crawling, data extraction, and web automation capabilities.
6+
7+
## What is Apify?
8+
9+
[Apify](https://apify.com/) is a platform that provides:
10+
- Data collection services for AI Agents, specializing in extracting data from social media, search engines, online maps, e-commerce sites, travel portals, or general websites
11+
- A marketplace of ready-to-use Actors (specialized tools) for various data tasks
12+
- Infrastructure to run and monetize our own AI Agents
613

714
## Prerequisites
815

9-
The following example requires the `apify-client` library and an API token which can be obtained from [Apify](https://apify.com/).
16+
1. Sign up for an [Apify account](https://console.apify.com/sign-up)
17+
2. Obtain your Apify API token (can be obtained from [Apify](https://docs.apify.com/platform/integrations/api))
18+
3. Install the required packages:
1019

11-
```shell
12-
pip install -U apify-client
20+
```bash
21+
pip install agno apify-client
1322
```
1423

15-
```shell
16-
export MY_APIFY_TOKEN=***
24+
## Basic Usage
25+
26+
The Agno framework makes it easy to integrate Apify Actors into your agents. Here's a simple example:
27+
28+
```python
29+
from agno.agent import Agent
30+
from agno.tools.apify import ApifyTools
31+
32+
# Create an agent with ApifyTools
33+
agent = Agent(
34+
tools=[
35+
ApifyTools(
36+
actors=["apify/rag-web-browser"], # Specify which Apify Actors to use, use multiple ones if needed
37+
apify_api_token="your_apify_api_key" # Or set the APIFY_API_TOKEN environment variable
38+
)
39+
],
40+
show_tool_calls=True,
41+
markdown=True
42+
)
43+
44+
# Use the agent to get website content
45+
agent.print_response("What information can you find on https://docs.agno.com/introduction ?", markdown=True)
1746
```
1847

19-
## Example
48+
## Available Apify Tools
49+
50+
You can easily integrate any Apify Actor as a tool. Here are some examples:
51+
52+
### 1. RAG Web Browser
2053

21-
The following agent will use Apify to crawl the webpage: https://docs.agno.com/introduction and summarize it.
54+
The [RAG Web Browser](https://apify.com/apify/rag-web-browser) Actor is specifically designed for AI and LLM applications. It searches the web for a query or processes a URL, then cleans and formats the content for your agent. This tool is enabled by default.
2255

23-
```python cookbook/tools/apify_tools.py
56+
```python
2457
from agno.agent import Agent
2558
from agno.tools.apify import ApifyTools
2659

27-
agent = Agent(tools=[ApifyTools()], show_tool_calls=True)
28-
agent.print_response("Tell me about https://docs.agno.com/introduction", markdown=True)
60+
agent = Agent(
61+
tools=[
62+
ApifyTools(actors=["apify/rag-web-browser"])
63+
],
64+
show_tool_calls=True,
65+
markdown=True
66+
)
67+
68+
# Search for information and process the results
69+
agent.print_response("What are the latest developments in large language models?", markdown=True)
2970
```
3071

31-
## Toolkit Params
72+
### 2. Website Content Crawler
3273

33-
| Parameter | Type | Default | Description |
34-
| ------------------------- | ------ | ------- | --------------------------------------------------------------------------------- |
35-
| `api_key` | `str` | - | API key for authentication purposes. |
36-
| `website_content_crawler` | `bool` | `True` | Enables the functionality to crawl a website using website-content-crawler actor. |
37-
| `web_scraper` | `bool` | `False` | Enables the functionality to crawl a website using web_scraper actor. |
74+
This tool uses Apify's [Website Content Crawler](https://apify.com/apify/website-content-crawler) Actor to extract text content from websites, making it perfect for RAG applications.
3875

39-
## Toolkit Functions
76+
```python
77+
from agno.agent import Agent
78+
from agno.tools.apify import ApifyTools
4079

41-
| Function | Description |
42-
| ------------------------- | ------------------------------------------------------------- |
43-
| `website_content_crawler` | Crawls a website using Apify's website-content-crawler actor. |
44-
| `web_scrapper` | Scrapes a website using Apify's web-scraper actor. |
80+
agent = Agent(
81+
tools=[
82+
ApifyTools(actors=["apify/website-content-crawler"])
83+
],
84+
markdown=True
85+
)
86+
87+
# Ask the agent to process web content
88+
agent.print_response("Summarize the content from https://docs.agno.com/introduction", markdown=True)
89+
```
90+
91+
### 3. Google Places Crawler
92+
93+
The [Google Places Crawler](https://apify.com/compass/crawler-google-places) extracts data about businesses from Google Maps and Google Places.
94+
95+
```python
96+
from agno.agent import Agent
97+
from agno.tools.apify import ApifyTools
98+
99+
agent = Agent(
100+
tools=[
101+
ApifyTools(actors=["compass/crawler-google-places"])
102+
],
103+
show_tool_calls=True
104+
)
105+
106+
# Find business information in a specific location
107+
agent.print_response("What are the top-rated restaurants in San Francisco?", markdown=True)
108+
agent.print_response("Find coffee shops in Prague", markdown=True)
109+
```
110+
111+
## Example Scenarios
112+
113+
### RAG Web Browser + Google Places Crawler
114+
This example combines web search with local business data to provide comprehensive information about a topic:
115+
116+
```python
117+
from agno.agent import Agent
118+
from agno.tools.apify import ApifyTools
119+
120+
agent = Agent(
121+
tools=[
122+
ApifyTools(actors=[
123+
"apify/rag-web-browser",
124+
"compass/crawler-google-places"
125+
])
126+
],
127+
show_tool_calls=True
128+
)
129+
130+
# Get general information and local businesses
131+
agent.print_response(
132+
"""
133+
I'm traveling to Tokyo next month.
134+
1. Research the best time to visit and major attractions
135+
2. Find one good rated sushi restaurants near Shinjuku
136+
Compile a comprehensive travel guide with this information.
137+
""",
138+
markdown=True
139+
)
140+
```
141+
142+
## Toolkit Params
143+
144+
| Parameter | Type | Default | Description |
145+
| ---------------------------- | ------------------- | ------- | ------------------------------------------------------------------ |
146+
| `apify_api_token` | `str` | `None` | Apify API token (or set via APIFY_API_TOKEN environment variable) |
147+
| `actors` | `str` or `List[str]`| `None` | Single Actor ID or list of Actor IDs to register |
45148

46149
## Developer Resources
47150

48151
- View [Tools](https://github.com/agno-agi/agno/blob/main/libs/agno/agno/tools/apify.py)
49152
- View [Cookbook](https://github.com/agno-agi/agno/blob/main/cookbook/tools/apify_tools.py)
153+
154+
## Resources
155+
156+
- [Apify Actor Documentation](https://docs.apify.com/Actors)
157+
- [Apify Store - Browse available Actors](https://apify.com/store)
158+
- [How to build and monetize an AI agent on Apify](https://blog.apify.com/how-to-build-an-ai-agent/)

0 commit comments

Comments
 (0)