From 7c15f486decac7fc5b3006ca320bba7d61dcb641 Mon Sep 17 00:00:00 2001 From: Vlada Dusek Date: Wed, 17 Jun 2026 11:30:53 +0200 Subject: [PATCH 1/6] docs: add AI agents guide --- README.md | 4 +- docs/01_introduction/index.mdx | 2 +- docs/01_introduction/quick-start.mdx | 1 + docs/03_guides/13_ai_agents.mdx | 173 +++++++++++++++++++++++++++ docs/03_guides/code/13_ai_agents.py | 50 ++++++++ 5 files changed, 227 insertions(+), 3 deletions(-) create mode 100644 docs/03_guides/13_ai_agents.mdx create mode 100644 docs/03_guides/code/13_ai_agents.py diff --git a/README.md b/README.md index b9c9ea55..b1c2f316 100644 --- a/README.md +++ b/README.md @@ -116,7 +116,7 @@ Almost any Python project can become an Actor, including projects for: - **Web scraping and crawling** — The SDK is fully compatible with [Crawlee](https://crawlee.dev/python), which makes Apify a natural place to deploy and scale your crawlers (see the [Crawlee guide](https://docs.apify.com/sdk/python/docs/guides/crawlee)). It also works with other popular scraping libraries, such as [Scrapy](https://docs.apify.com/sdk/python/docs/guides/scrapy), [Scrapling](https://docs.apify.com/sdk/python/docs/guides/scrapling), or [Crawl4AI](https://docs.apify.com/sdk/python/docs/guides/crawl4ai). - **Browser automation** — Drive a real browser with [Playwright](https://docs.apify.com/sdk/python/docs/guides/playwright) or [Selenium](https://docs.apify.com/sdk/python/docs/guides/selenium), or with higher-level tools such as [Browser Use](https://docs.apify.com/sdk/python/docs/guides/browser-use). - **Web servers and APIs** — Run a [web server](https://docs.apify.com/sdk/python/docs/guides/running-webserver) inside an Actor to serve HTTP requests, for example to expose your scraper as a live API. -- **AI agents** — Host agents built with your framework of choice. Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). +- **AI agents** — Host agents built with your framework of choice (see the [AI agents guide](https://docs.apify.com/sdk/python/docs/guides/ai-agents)). Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). - **MCP servers** — Deploy a Python MCP server as an Actor and make its tools available to any MCP client. See [MCP server](https://apify.com/templates/python-mcp-empty) and [MCP proxy](https://apify.com/templates/python-mcp-proxy) templates Whatever you build, the Apify SDK doesn't lock you into a particular framework. Bring the libraries you already use, and let Apify run your project in the cloud. @@ -199,7 +199,7 @@ The full SDK documentation lives at **[docs.apify.com/sdk/python](https://docs.a | [Overview](https://docs.apify.com/sdk/python/docs/overview) | What the SDK is, what Actors are, and how the pieces fit together. | | [Quick start](https://docs.apify.com/sdk/python/docs/quick-start) | Create, run, and deploy your first Python Actor. | | [Concepts](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle) | Actor lifecycle, input, storages, events, proxy management, interacting with other Actors, webhooks, accessing the Apify API, logging, configuration, and pay-per-event. | -| [Guides](https://docs.apify.com/sdk/python/docs/guides/beautifulsoup-httpx) | Integrations with BeautifulSoup, Parsel, Playwright, Selenium, Crawlee, Scrapy, Scrapling, Crawl4AI, and Browser Use, plus running a web server and using uv. | +| [Guides](https://docs.apify.com/sdk/python/docs/guides/beautifulsoup-httpx) | Integrations with BeautifulSoup, Parsel, Playwright, Selenium, Crawlee, Scrapy, Scrapling, Crawl4AI, and Browser Use, plus building AI agents, running a web server, and using uv. | | [Upgrading](https://docs.apify.com/sdk/python/docs/upgrading/upgrading-to-v4) | Migrating between major versions. | | [API reference](https://docs.apify.com/sdk/python/reference) | Generated reference for every class and method. | | [Changelog](https://docs.apify.com/sdk/python/docs/changelog) | Release history and breaking changes. | diff --git a/docs/01_introduction/index.mdx b/docs/01_introduction/index.mdx index 133c6a47..b4db08e8 100644 --- a/docs/01_introduction/index.mdx +++ b/docs/01_introduction/index.mdx @@ -41,7 +41,7 @@ Almost any Python project can become an Actor, including projects for: - **Web scraping and crawling** - The SDK is fully compatible with [Crawlee](https://crawlee.dev/python), which makes Apify a natural place to deploy and scale your crawlers (see the [Crawlee guide](./guides/crawlee)). It also works with other popular scraping libraries, such as [Scrapy](./guides/scrapy), [Scrapling](./guides/scrapling), or [Crawl4AI](./guides/crawl4ai). - **Browser automation** - Drive a real browser with [Playwright](./guides/playwright) or [Selenium](./guides/selenium), or with higher-level tools such as [Browser Use](./guides/browser-use). - **Web servers and APIs** - Run a [web server](./guides/running-webserver) inside an Actor to serve HTTP requests, for example to expose your scraper as a live API. -- **AI agents** - Host agents built with your framework of choice. Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). +- **AI agents** - Host agents built with your framework of choice (see the [AI agents guide](./guides/ai-agents)). Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). - **MCP servers** - Deploy a Python MCP server as an Actor and make its tools available to any MCP client. See the [MCP server](https://apify.com/templates/python-mcp-empty) and [MCP proxy](https://apify.com/templates/python-mcp-proxy) templates. Whatever you build, the Apify SDK doesn't lock you into a particular framework. Bring the libraries you already use, and let Apify run your project in the cloud. diff --git a/docs/01_introduction/quick-start.mdx b/docs/01_introduction/quick-start.mdx index 289659bf..19231b81 100644 --- a/docs/01_introduction/quick-start.mdx +++ b/docs/01_introduction/quick-start.mdx @@ -112,6 +112,7 @@ To see how you can integrate the Apify SDK with popular scraping libraries and f - [Adaptive scraping with Scrapling](./guides/scrapling) - [LLM-ready scraping with Crawl4AI](./guides/crawl4ai) - [Browser AI agents with Browser Use](./guides/browser-use) +- [Building AI agents](./guides/ai-agents) For other aspects of Actor development, explore these guides: diff --git a/docs/03_guides/13_ai_agents.mdx b/docs/03_guides/13_ai_agents.mdx new file mode 100644 index 00000000..f7c038e9 --- /dev/null +++ b/docs/03_guides/13_ai_agents.mdx @@ -0,0 +1,173 @@ +--- +id: ai-agents +title: Building AI agents +description: Host AI agents built with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents as Apify Actors. +--- + +import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock'; + +import AiAgentsExample from '!!raw-loader!roa-loader!./code/13_ai_agents.py'; + +In this guide, you'll learn how to host an AI agent as an Apify Actor, using the agent framework of your choice. + +## Introduction + +An AI agent is a program that uses a large language model (LLM) to decide what to do next. Instead of following a fixed script, it reasons about a task, calls tools to gather information or take actions, and loops until the task is done. The Python ecosystem offers several frameworks for building such agents, and the Apify SDK doesn't lock you into any of them. + +Apify Actors are a natural home for agents: + +- An agent is just a Python program, so wrapping it in `async with Actor:` is all it takes to run it on the platform. +- The platform scales runs, schedules them, and keeps logs, so you don't operate any infrastructure yourself. +- The [Apify Store](https://apify.com/store) gives your agent thousands of ready-made tools. Any Actor (a scraper, a browser automation, an API wrapper) can become a tool the agent calls. +- The [Apify OpenRouter proxy](https://apify.com/apify/openrouter) lets the agent talk to an LLM without managing a provider API key. +- Pay-per-event charging lets you monetize the agent and pass LLM costs on to its users. + +## Choosing a framework + +Apify maintains a ready-made Actor template for each of the popular agent frameworks. Each template is a complete, deployable Actor that you can use as a starting point. Pick the one that matches the framework you already use, or the style of agent you want to build: + +| Framework | Good for | Template | +|---|---|---| +| [PydanticAI](https://ai.pydantic.dev/) | Typed, Pydantic-native agents with tool calling | [`python-pydanticai`](https://apify.com/templates/python-pydanticai) | +| [CrewAI](https://www.crewai.com/) | Multi-agent "crews" that collaborate on a task | [`python-crewai`](https://apify.com/templates/python-crewai) | +| [LangGraph](https://www.langchain.com/langgraph) | Graph-based agents with explicit state and control flow | [`python-langgraph`](https://apify.com/templates/python-langgraph) | +| [LlamaIndex](https://www.llamaindex.ai/) | Retrieval-augmented agents over your own data | [`python-llamaindex-agent`](https://apify.com/templates/python-llamaindex-agent) | +| [Smolagents](https://github.com/huggingface/smolagents) | Lightweight code-writing agents from Hugging Face | [`python-smolagents`](https://apify.com/templates/python-smolagents) | + +All of these templates live in the [actor-templates repository](https://github.com/apify/actor-templates), and you can scaffold any of them with the [Apify CLI](https://docs.apify.com/cli), for example `apify create my-agent --template python-pydanticai`. + +## Example Actor + +The following Actor runs a [PydanticAI](https://ai.pydantic.dev/) agent for a single prompt and stores the answer in the default dataset. The prompt and model are configurable through the Actor input. + +A `build_agent` helper holds the PydanticAI-specific setup, while the `main` coroutine handles the [Actor](https://docs.apify.com/platform/actors) lifecycle, reads the input, runs the agent, and stores the result: + + + {AiAgentsExample} + + +Note that: + +- Keeping the agent setup in `build_agent` separates the framework-specific code from the Actor's orchestration logic. `main` only decides what to read from the input and what to store. +- The agent talks to its LLM through the Apify OpenRouter proxy, so the Actor needs no provider API key. See [Connecting to an LLM](#connecting-to-an-llm) below. +- `output_type=str` returns the answer as plain text. Pass a [Pydantic](./input-validation) model instead to get a validated object that maps onto a dataset row. + +## Connecting to an LLM + +Every agent needs an LLM, and there are two ways to provide one. + +The example above uses the [Apify OpenRouter proxy](https://apify.com/apify/openrouter), an OpenAI-compatible endpoint at `https://openrouter.apify.actor/api/v1` that fronts the full [OpenRouter](https://openrouter.ai) model catalog. The token usage is billed against the Apify account running the Actor, so no provider API key is required. The Actor authenticates with the proxy using the `APIFY_TOKEN` that the platform injects into every run. To switch models, change the `model` input to any [OpenRouter model slug](https://openrouter.ai/models), for example `openai/gpt-4o-mini`. + +Alternatively, you can call a provider such as OpenAI, Anthropic, or Google directly with your own API key. Keep the key out of the Actor input and source code. Read it from an environment variable, which on the platform you set as a [secret environment variable](https://docs.apify.com/platform/actors/development/programming-interface/environment-variables) and locally you export in your shell. + +## Using Apify Actors as tools + +An agent becomes useful once it can act on the world. On Apify, any of the thousands of Actors in the [Apify Store](https://apify.com/store) can become a tool: a scraper that fetches data, a browser automation that fills a form, or an API wrapper that posts a message. + +For LangChain-based frameworks, such as LangGraph and CrewAI, the [`langchain-apify`](https://github.com/apify/langchain-apify) package exposes any Actor as a tool with a single line: + +```python +from crewai_tools import ApifyActorsTool + +# Let the agent scrape Instagram profiles by calling the apify/instagram-scraper Actor. +tools = [ApifyActorsTool('apify/instagram-scraper')] +``` + +For any other framework, call the Actor directly through the Actor's preconfigured API client and read its dataset: + +```python +@tool +async def scrape_instagram(handle: str) -> list[dict]: + """Scrape recent posts from an Instagram profile.""" + run_input = {'directUrls': [f'https://www.instagram.com/{handle}/']} + run = await Actor.apify_client.actor('apify/instagram-scraper').call(run_input=run_input) + return (await Actor.apify_client.dataset(run['defaultDatasetId']).list_items()).items +``` + +For details on calling other Actors, see [Interacting with other Actors](../concepts/interacting-with-other-actors). + +## Other frameworks + +The same `async with Actor:` pattern wraps an agent built with any framework. The snippets below show how each one defines an agent. For a full, deployable Actor, start from the matching template. + +[**CrewAI**](https://apify.com/templates/python-crewai) assembles one or more role-playing agents into a crew that works through tasks: + +```python +from crewai import Agent, Crew, Task + +agent = Agent( + role='Social Media Analyst', + goal='Analyze Instagram profiles and summarize the findings.', + backstory='An expert at turning social media data into insights.', + tools=[ApifyActorsTool('apify/instagram-scraper')], + llm='gpt-4o-mini', +) +task = Task(description=query, expected_output='A short report.', agent=agent) +result = (await Crew(agents=[agent], tasks=[task]).kickoff_async()).raw +``` + +[**LangGraph**](https://apify.com/templates/python-langgraph) builds an agent as a graph with explicit state, which makes complex control flow easy to follow: + +```python +from langchain.agents import create_agent +from langchain_openai import ChatOpenAI + +agent = create_agent(ChatOpenAI(model='gpt-4o-mini'), tools=[scrape_instagram]) +result = await agent.ainvoke({'messages': [('user', query)]}) +``` + +[**LlamaIndex**](https://apify.com/templates/python-llamaindex-agent) shines at retrieval-augmented agents that reason over your own data: + +```python +from llama_index.core.agent import ReActAgent +from llama_index.core.tools import FunctionTool +from llama_index.llms.openai import OpenAI + +agent = ReActAgent( + tools=[FunctionTool.from_defaults(fn=scrape_instagram)], + llm=OpenAI(model='gpt-4o-mini'), +) +response = await agent.run(user_msg=query) +``` + +[**Smolagents**](https://apify.com/templates/python-smolagents) is a lightweight framework from Hugging Face whose agents write and run Python code to solve a task: + +```python +from smolagents import CodeAgent, OpenAIServerModel, WebSearchTool + +agent = CodeAgent(tools=[WebSearchTool()], model=OpenAIServerModel(model_id='gpt-4o-mini')) +result = agent.run(query) +``` + +## Running on the Apify platform + +Agents run on the standard [Apify Python base image](https://hub.docker.com/r/apify/actor-python), so no browser or extra system dependencies are needed. Add `apify` and your framework to `requirements.txt`, for example: + +```text +apify +pydantic-ai +``` + +To monetize the agent, use [pay-per-event charging](../concepts/pay-per-event). You define events such as `task-completed` in the Actor's monetization settings and trigger them from the code: + +```python +await Actor.charge('task-completed') +``` + +This lets you charge users directly from the Actor and cover the cost of execution and LLM tokens. It pairs naturally with the Apify OpenRouter proxy, which already bills the LLM usage to the account running the Actor. + +## Conclusion + +In this guide, you learned how to host an AI agent as an Apify Actor. You can now run an agent built with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents, connect it to an LLM through the Apify OpenRouter proxy, give it Apify Actors as tools, and monetize it with pay-per-event. To get started, see the [Actor templates](https://apify.com/templates/categories/python). If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy building! + +## Additional resources + +- [Apify templates: PydanticAI](https://apify.com/templates/python-pydanticai) +- [Apify templates: CrewAI](https://apify.com/templates/python-crewai) +- [Apify templates: LangGraph](https://apify.com/templates/python-langgraph) +- [Apify templates: LlamaIndex](https://apify.com/templates/python-llamaindex-agent) +- [Apify templates: Smolagents](https://apify.com/templates/python-smolagents) +- [Apify: actor-templates repository](https://github.com/apify/actor-templates) +- [Apify: OpenRouter proxy](https://apify.com/apify/openrouter) +- [Apify: langchain-apify integration](https://github.com/apify/langchain-apify) +- [Apify blog: What are AI agents](https://blog.apify.com/what-are-ai-agents/) diff --git a/docs/03_guides/code/13_ai_agents.py b/docs/03_guides/code/13_ai_agents.py new file mode 100644 index 00000000..fa00494f --- /dev/null +++ b/docs/03_guides/code/13_ai_agents.py @@ -0,0 +1,50 @@ +import asyncio +import os + +from pydantic_ai import Agent +from pydantic_ai.models.openai import OpenAIChatModel +from pydantic_ai.providers.openai import OpenAIProvider + +from apify import Actor + +# The agent reaches its LLM through the Apify OpenRouter proxy, an +# OpenAI-compatible endpoint billed against the run's Apify account. It +# authenticates with the `APIFY_TOKEN` that the platform injects into every run, +# so no separate provider API key (such as `OPENAI_API_KEY`) is needed. +OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' + +DEFAULT_PROMPT = 'In two sentences, explain what an Apify Actor is.' + + +def build_agent(model_name: str) -> Agent[None, str]: + """Build a PydanticAI agent that routes LLM calls through Apify OpenRouter.""" + provider = OpenAIProvider( + base_url=OPENROUTER_BASE_URL, + api_key=os.environ['APIFY_TOKEN'], + ) + return Agent( + OpenAIChatModel(model_name, provider=provider), + output_type=str, + system_prompt='You are a concise, helpful research assistant.', + ) + + +async def main() -> None: + async with Actor: + # Read the Actor input. + actor_input = await Actor.get_input() or {} + prompt = actor_input.get('prompt', DEFAULT_PROMPT) + model_name = actor_input.get('model', 'openai/gpt-4o-mini') + + # Build the agent and run it for a single prompt. + Actor.log.info(f'Running the agent (model={model_name}) for: {prompt}') + agent = build_agent(model_name) + result = await agent.run(user_prompt=prompt) + + # Store the agent's answer in the default dataset. + Actor.log.info(f'The agent responded:\n{result.output}') + await Actor.push_data({'prompt': prompt, 'response': result.output}) + + +if __name__ == '__main__': + asyncio.run(main()) From 034a077eb3a85f24b9a0e70d6b9c4789334653e1 Mon Sep 17 00:00:00 2001 From: Vlada Dusek Date: Wed, 17 Jun 2026 14:03:24 +0200 Subject: [PATCH 2/6] docs: split AI agents guide into per-framework sections --- docs/03_guides/13_ai_agents.mdx | 148 +++++++++++++-------------- docs/03_guides/code/13_ai_agents.py | 50 --------- docs/03_guides/code/13_crewai.py | 34 ++++++ docs/03_guides/code/13_langgraph.py | 33 ++++++ docs/03_guides/code/13_llamaindex.py | 40 ++++++++ docs/03_guides/code/13_pydanticai.py | 36 +++++++ docs/03_guides/code/13_smolagents.py | 32 ++++++ 7 files changed, 246 insertions(+), 127 deletions(-) delete mode 100644 docs/03_guides/code/13_ai_agents.py create mode 100644 docs/03_guides/code/13_crewai.py create mode 100644 docs/03_guides/code/13_langgraph.py create mode 100644 docs/03_guides/code/13_llamaindex.py create mode 100644 docs/03_guides/code/13_pydanticai.py create mode 100644 docs/03_guides/code/13_smolagents.py diff --git a/docs/03_guides/13_ai_agents.mdx b/docs/03_guides/13_ai_agents.mdx index f7c038e9..3c0c8a06 100644 --- a/docs/03_guides/13_ai_agents.mdx +++ b/docs/03_guides/13_ai_agents.mdx @@ -6,7 +6,11 @@ description: Host AI agents built with PydanticAI, CrewAI, LangGraph, LlamaIndex import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock'; -import AiAgentsExample from '!!raw-loader!roa-loader!./code/13_ai_agents.py'; +import PydanticaiExample from '!!raw-loader!roa-loader!./code/13_pydanticai.py'; +import CrewaiExample from '!!raw-loader!roa-loader!./code/13_crewai.py'; +import LanggraphExample from '!!raw-loader!roa-loader!./code/13_langgraph.py'; +import LlamaindexExample from '!!raw-loader!roa-loader!./code/13_llamaindex.py'; +import SmolagentsExample from '!!raw-loader!roa-loader!./code/13_smolagents.py'; In this guide, you'll learn how to host an AI agent as an Apify Actor, using the agent framework of your choice. @@ -28,37 +32,80 @@ Apify maintains a ready-made Actor template for each of the popular agent framew | Framework | Good for | Template | |---|---|---| -| [PydanticAI](https://ai.pydantic.dev/) | Typed, Pydantic-native agents with tool calling | [`python-pydanticai`](https://apify.com/templates/python-pydanticai) | -| [CrewAI](https://www.crewai.com/) | Multi-agent "crews" that collaborate on a task | [`python-crewai`](https://apify.com/templates/python-crewai) | -| [LangGraph](https://www.langchain.com/langgraph) | Graph-based agents with explicit state and control flow | [`python-langgraph`](https://apify.com/templates/python-langgraph) | -| [LlamaIndex](https://www.llamaindex.ai/) | Retrieval-augmented agents over your own data | [`python-llamaindex-agent`](https://apify.com/templates/python-llamaindex-agent) | -| [Smolagents](https://github.com/huggingface/smolagents) | Lightweight code-writing agents from Hugging Face | [`python-smolagents`](https://apify.com/templates/python-smolagents) | +| [PydanticAI](#pydanticai) | Typed, Pydantic-native agents with tool calling | [`python-pydanticai`](https://apify.com/templates/python-pydanticai) | +| [CrewAI](#crewai) | Multi-agent "crews" that collaborate on a task | [`python-crewai`](https://apify.com/templates/python-crewai) | +| [LangGraph](#langgraph) | Graph-based agents with explicit state and control flow | [`python-langgraph`](https://apify.com/templates/python-langgraph) | +| [LlamaIndex](#llamaindex) | Retrieval-augmented agents over your own data | [`python-llamaindex-agent`](https://apify.com/templates/python-llamaindex-agent) | +| [Smolagents](#smolagents) | Lightweight code-writing agents from Hugging Face | [`python-smolagents`](https://apify.com/templates/python-smolagents) | All of these templates live in the [actor-templates repository](https://github.com/apify/actor-templates), and you can scaffold any of them with the [Apify CLI](https://docs.apify.com/cli), for example `apify create my-agent --template python-pydanticai`. -## Example Actor +## Connecting to an LLM + +Every agent needs an LLM, and there are two ways to provide one. + +The first is the [Apify OpenRouter proxy](https://apify.com/apify/openrouter), an OpenAI-compatible endpoint at `https://openrouter.apify.actor/api/v1` that fronts the full [OpenRouter](https://openrouter.ai) model catalog. The token usage is billed against the Apify account running the Actor, so no provider API key is required. The Actor authenticates with the proxy using the `APIFY_TOKEN` that the platform injects into every run. Any framework with an OpenAI-compatible client can point its base URL at the proxy, which is what most examples below do. To switch models, change the `model` input to any [OpenRouter model slug](https://openrouter.ai/models), for example `openai/gpt-4o-mini`. -The following Actor runs a [PydanticAI](https://ai.pydantic.dev/) agent for a single prompt and stores the answer in the default dataset. The prompt and model are configurable through the Actor input. +The second is to call a provider such as OpenAI directly with your own API key, which the CrewAI example below does through LiteLLM. Keep the key out of the Actor input and source code. Read it from an environment variable, which on the platform you set as a [secret environment variable](https://docs.apify.com/platform/actors/development/programming-interface/environment-variables) and locally you export in your shell. -A `build_agent` helper holds the PydanticAI-specific setup, while the `main` coroutine handles the [Actor](https://docs.apify.com/platform/actors) lifecycle, reads the input, runs the agent, and stores the result: +Each section below shows a complete, single-file Actor for one framework. They all read the input, run the agent, and store the result in the default dataset. + +## PydanticAI + +[PydanticAI](https://ai.pydantic.dev/) is an agent framework from the team behind Pydantic. It is strongly typed and integrates naturally with the [Pydantic models](./input-validation) the Apify SDK already uses. The following Actor runs an agent for a single prompt: - {AiAgentsExample} + {PydanticaiExample} + + +Set `output_type` to a Pydantic model instead of `str` to get a validated object back, which maps directly onto a dataset row. + +## CrewAI + +[CrewAI](https://www.crewai.com/) models a problem as a "crew" of role-playing agents that work through tasks. The following Actor defines a single analyst agent and one task: + + + {CrewaiExample} Note that: -- Keeping the agent setup in `build_agent` separates the framework-specific code from the Actor's orchestration logic. `main` only decides what to read from the input and what to store. -- The agent talks to its LLM through the Apify OpenRouter proxy, so the Actor needs no provider API key. See [Connecting to an LLM](#connecting-to-an-llm) below. -- `output_type=str` returns the answer as plain text. Pass a [Pydantic](./input-validation) model instead to get a validated object that maps onto a dataset row. +- `kickoff_async` runs the crew without blocking the Actor's event loop. +- CrewAI calls the LLM through [LiteLLM](https://docs.litellm.ai/), so this example reads `OPENAI_API_KEY`. To route it through the Apify OpenRouter proxy instead, configure a custom `LLM` (see the [CrewAI LLM docs](https://docs.crewai.com/concepts/llms)). +- On a fresh container, crewAI shows a one-time trace-consent prompt. The template sets `CREWAI_TESTING=true` to suppress it; do the same in your Dockerfile. -## Connecting to an LLM +## LangGraph -Every agent needs an LLM, and there are two ways to provide one. +[LangGraph](https://www.langchain.com/langgraph) builds an agent as a graph with explicit state, which makes complex, multi-step control flow easy to follow. It builds on [LangChain](https://www.langchain.com/), so any LangChain chat model and tool works. The following Actor runs a single-turn agent: + + + {LanggraphExample} + + +The example passes an empty `tools` list for brevity. Add LangChain tools to give the agent abilities, and read the final answer from the last message in the returned state. + +## LlamaIndex + +[LlamaIndex](https://www.llamaindex.ai/) is built for retrieval-augmented agents that reason over your own data. The following Actor runs a `ReActAgent` with a single tool: + + + {LlamaindexExample} + + +Note that: + +- `OpenAILike` is the LlamaIndex LLM class for OpenAI-compatible endpoints such as the Apify OpenRouter proxy. It needs the `llama-index-llms-openai-like` package. +- The agent decides on its own when to call the `word_count` tool. Add `FunctionTool`s of your own to extend it. -The example above uses the [Apify OpenRouter proxy](https://apify.com/apify/openrouter), an OpenAI-compatible endpoint at `https://openrouter.apify.actor/api/v1` that fronts the full [OpenRouter](https://openrouter.ai) model catalog. The token usage is billed against the Apify account running the Actor, so no provider API key is required. The Actor authenticates with the proxy using the `APIFY_TOKEN` that the platform injects into every run. To switch models, change the `model` input to any [OpenRouter model slug](https://openrouter.ai/models), for example `openai/gpt-4o-mini`. +## Smolagents -Alternatively, you can call a provider such as OpenAI, Anthropic, or Google directly with your own API key. Keep the key out of the Actor input and source code. Read it from an environment variable, which on the platform you set as a [secret environment variable](https://docs.apify.com/platform/actors/development/programming-interface/environment-variables) and locally you export in your shell. +[Smolagents](https://github.com/huggingface/smolagents) is a lightweight framework from Hugging Face whose agents write and run Python code to solve a task. The following Actor runs a `CodeAgent`: + + + {SmolagentsExample} + + +A `CodeAgent` executes the Python code it generates, so run it in the isolated Actor container rather than on your own machine. Pass tools such as `WebSearchTool` in the `tools` list to let it gather information. ## Using Apify Actors as tools @@ -76,7 +123,6 @@ tools = [ApifyActorsTool('apify/instagram-scraper')] For any other framework, call the Actor directly through the Actor's preconfigured API client and read its dataset: ```python -@tool async def scrape_instagram(handle: str) -> list[dict]: """Scrape recent posts from an Instagram profile.""" run_input = {'directUrls': [f'https://www.instagram.com/{handle}/']} @@ -86,67 +132,15 @@ async def scrape_instagram(handle: str) -> list[dict]: For details on calling other Actors, see [Interacting with other Actors](../concepts/interacting-with-other-actors). -## Other frameworks - -The same `async with Actor:` pattern wraps an agent built with any framework. The snippets below show how each one defines an agent. For a full, deployable Actor, start from the matching template. - -[**CrewAI**](https://apify.com/templates/python-crewai) assembles one or more role-playing agents into a crew that works through tasks: - -```python -from crewai import Agent, Crew, Task - -agent = Agent( - role='Social Media Analyst', - goal='Analyze Instagram profiles and summarize the findings.', - backstory='An expert at turning social media data into insights.', - tools=[ApifyActorsTool('apify/instagram-scraper')], - llm='gpt-4o-mini', -) -task = Task(description=query, expected_output='A short report.', agent=agent) -result = (await Crew(agents=[agent], tasks=[task]).kickoff_async()).raw -``` - -[**LangGraph**](https://apify.com/templates/python-langgraph) builds an agent as a graph with explicit state, which makes complex control flow easy to follow: - -```python -from langchain.agents import create_agent -from langchain_openai import ChatOpenAI - -agent = create_agent(ChatOpenAI(model='gpt-4o-mini'), tools=[scrape_instagram]) -result = await agent.ainvoke({'messages': [('user', query)]}) -``` - -[**LlamaIndex**](https://apify.com/templates/python-llamaindex-agent) shines at retrieval-augmented agents that reason over your own data: - -```python -from llama_index.core.agent import ReActAgent -from llama_index.core.tools import FunctionTool -from llama_index.llms.openai import OpenAI - -agent = ReActAgent( - tools=[FunctionTool.from_defaults(fn=scrape_instagram)], - llm=OpenAI(model='gpt-4o-mini'), -) -response = await agent.run(user_msg=query) -``` - -[**Smolagents**](https://apify.com/templates/python-smolagents) is a lightweight framework from Hugging Face whose agents write and run Python code to solve a task: - -```python -from smolagents import CodeAgent, OpenAIServerModel, WebSearchTool - -agent = CodeAgent(tools=[WebSearchTool()], model=OpenAIServerModel(model_id='gpt-4o-mini')) -result = agent.run(query) -``` - ## Running on the Apify platform -Agents run on the standard [Apify Python base image](https://hub.docker.com/r/apify/actor-python), so no browser or extra system dependencies are needed. Add `apify` and your framework to `requirements.txt`, for example: +Agents run on the standard [Apify Python base image](https://hub.docker.com/r/apify/actor-python), so no browser or extra system dependencies are needed. Add `apify` and your framework's packages to `requirements.txt`: -```text -apify -pydantic-ai -``` +- PydanticAI: `pydantic-ai` +- CrewAI: `crewai` (or `crewai[tools]` for `ApifyActorsTool`) +- LangGraph: `langchain`, `langchain-openai`, `langgraph` +- LlamaIndex: `llama-index`, `llama-index-llms-openai-like` +- Smolagents: `smolagents[openai]` To monetize the agent, use [pay-per-event charging](../concepts/pay-per-event). You define events such as `task-completed` in the Actor's monetization settings and trigger them from the code: @@ -158,7 +152,7 @@ This lets you charge users directly from the Actor and cover the cost of executi ## Conclusion -In this guide, you learned how to host an AI agent as an Apify Actor. You can now run an agent built with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents, connect it to an LLM through the Apify OpenRouter proxy, give it Apify Actors as tools, and monetize it with pay-per-event. To get started, see the [Actor templates](https://apify.com/templates/categories/python). If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy building! +In this guide, you learned how to host an AI agent as an Apify Actor. You can now build an agent with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents, connect it to an LLM through the Apify OpenRouter proxy, give it Apify Actors as tools, and monetize it with pay-per-event. To get started, see the [Actor templates](https://apify.com/templates/categories/python). If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy building! ## Additional resources diff --git a/docs/03_guides/code/13_ai_agents.py b/docs/03_guides/code/13_ai_agents.py deleted file mode 100644 index fa00494f..00000000 --- a/docs/03_guides/code/13_ai_agents.py +++ /dev/null @@ -1,50 +0,0 @@ -import asyncio -import os - -from pydantic_ai import Agent -from pydantic_ai.models.openai import OpenAIChatModel -from pydantic_ai.providers.openai import OpenAIProvider - -from apify import Actor - -# The agent reaches its LLM through the Apify OpenRouter proxy, an -# OpenAI-compatible endpoint billed against the run's Apify account. It -# authenticates with the `APIFY_TOKEN` that the platform injects into every run, -# so no separate provider API key (such as `OPENAI_API_KEY`) is needed. -OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' - -DEFAULT_PROMPT = 'In two sentences, explain what an Apify Actor is.' - - -def build_agent(model_name: str) -> Agent[None, str]: - """Build a PydanticAI agent that routes LLM calls through Apify OpenRouter.""" - provider = OpenAIProvider( - base_url=OPENROUTER_BASE_URL, - api_key=os.environ['APIFY_TOKEN'], - ) - return Agent( - OpenAIChatModel(model_name, provider=provider), - output_type=str, - system_prompt='You are a concise, helpful research assistant.', - ) - - -async def main() -> None: - async with Actor: - # Read the Actor input. - actor_input = await Actor.get_input() or {} - prompt = actor_input.get('prompt', DEFAULT_PROMPT) - model_name = actor_input.get('model', 'openai/gpt-4o-mini') - - # Build the agent and run it for a single prompt. - Actor.log.info(f'Running the agent (model={model_name}) for: {prompt}') - agent = build_agent(model_name) - result = await agent.run(user_prompt=prompt) - - # Store the agent's answer in the default dataset. - Actor.log.info(f'The agent responded:\n{result.output}') - await Actor.push_data({'prompt': prompt, 'response': result.output}) - - -if __name__ == '__main__': - asyncio.run(main()) diff --git a/docs/03_guides/code/13_crewai.py b/docs/03_guides/code/13_crewai.py new file mode 100644 index 00000000..04949b84 --- /dev/null +++ b/docs/03_guides/code/13_crewai.py @@ -0,0 +1,34 @@ +import asyncio + +from crewai import Agent, Crew, Task + +from apify import Actor + + +async def main() -> None: + async with Actor: + actor_input = await Actor.get_input() or {} + topic = actor_input.get('topic', 'the Apify platform') + model = actor_input.get('model', 'gpt-4o-mini') + + # CrewAI calls the LLM through LiteLLM, which reads OPENAI_API_KEY. + analyst = Agent( + role='Research Analyst', + goal=f'Write a short, accurate summary about {topic}.', + backstory='An analyst who turns a topic into a concise brief.', + llm=model, + ) + task = Task( + description=f'Write a three-sentence summary about {topic}.', + expected_output='A three-sentence summary.', + agent=analyst, + ) + + # `kickoff_async` keeps the Actor's event loop responsive. + result = await Crew(agents=[analyst], tasks=[task]).kickoff_async() + Actor.log.info(f'Crew result:\n{result.raw}') + await Actor.push_data({'topic': topic, 'summary': result.raw}) + + +if __name__ == '__main__': + asyncio.run(main()) diff --git a/docs/03_guides/code/13_langgraph.py b/docs/03_guides/code/13_langgraph.py new file mode 100644 index 00000000..64d4ec0b --- /dev/null +++ b/docs/03_guides/code/13_langgraph.py @@ -0,0 +1,33 @@ +import asyncio +import os + +from langchain.agents import create_agent +from langchain_openai import ChatOpenAI + +from apify import Actor + +OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' + + +async def main() -> None: + async with Actor: + actor_input = await Actor.get_input() or {} + query = actor_input.get('query', 'What is an Apify Actor?') + model = actor_input.get('model', 'openai/gpt-4o-mini') + + # Route the LLM through the Apify OpenRouter proxy (no provider key needed). + llm = ChatOpenAI( + model=model, + base_url=OPENROUTER_BASE_URL, + api_key=os.environ['APIFY_TOKEN'], + ) + agent = create_agent(llm, tools=[]) + + result = await agent.ainvoke({'messages': [('user', query)]}) + answer = result['messages'][-1].content + Actor.log.info(f'Agent answer:\n{answer}') + await Actor.push_data({'query': query, 'answer': answer}) + + +if __name__ == '__main__': + asyncio.run(main()) diff --git a/docs/03_guides/code/13_llamaindex.py b/docs/03_guides/code/13_llamaindex.py new file mode 100644 index 00000000..ed75901b --- /dev/null +++ b/docs/03_guides/code/13_llamaindex.py @@ -0,0 +1,40 @@ +import asyncio +import os + +from llama_index.core.agent import ReActAgent +from llama_index.core.tools import FunctionTool +from llama_index.llms.openai_like import OpenAILike + +from apify import Actor + +OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' + + +def word_count(text: str) -> int: + """Return the number of words in the given text.""" + return len(text.split()) + + +async def main() -> None: + async with Actor: + actor_input = await Actor.get_input() or {} + query = actor_input.get('query', 'How many words are in "Apify runs Actors"?') + model = actor_input.get('model', 'openai/gpt-4o-mini') + + # Route the LLM through the Apify OpenRouter proxy (no provider key needed). + # `OpenAILike` is the LlamaIndex class for OpenAI-compatible endpoints. + llm = OpenAILike( + model=model, + api_base=OPENROUTER_BASE_URL, + api_key=os.environ['APIFY_TOKEN'], + is_chat_model=True, + ) + agent = ReActAgent(tools=[FunctionTool.from_defaults(fn=word_count)], llm=llm) + + response = await agent.run(user_msg=query) + Actor.log.info(f'Agent answer:\n{response}') + await Actor.push_data({'query': query, 'answer': str(response)}) + + +if __name__ == '__main__': + asyncio.run(main()) diff --git a/docs/03_guides/code/13_pydanticai.py b/docs/03_guides/code/13_pydanticai.py new file mode 100644 index 00000000..415edfcd --- /dev/null +++ b/docs/03_guides/code/13_pydanticai.py @@ -0,0 +1,36 @@ +import asyncio +import os + +from pydantic_ai import Agent +from pydantic_ai.models.openai import OpenAIChatModel +from pydantic_ai.providers.openai import OpenAIProvider + +from apify import Actor + +OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' + + +async def main() -> None: + async with Actor: + actor_input = await Actor.get_input() or {} + prompt = actor_input.get('prompt', 'Explain Apify Actors in two sentences.') + model = actor_input.get('model', 'openai/gpt-4o-mini') + + # Route the LLM through the Apify OpenRouter proxy (no provider key needed). + provider = OpenAIProvider( + base_url=OPENROUTER_BASE_URL, + api_key=os.environ['APIFY_TOKEN'], + ) + agent = Agent( + OpenAIChatModel(model, provider=provider), + output_type=str, + system_prompt='You are a concise, helpful assistant.', + ) + + result = await agent.run(user_prompt=prompt) + Actor.log.info(f'Agent response:\n{result.output}') + await Actor.push_data({'prompt': prompt, 'response': result.output}) + + +if __name__ == '__main__': + asyncio.run(main()) diff --git a/docs/03_guides/code/13_smolagents.py b/docs/03_guides/code/13_smolagents.py new file mode 100644 index 00000000..19dc0e00 --- /dev/null +++ b/docs/03_guides/code/13_smolagents.py @@ -0,0 +1,32 @@ +import asyncio +import os + +from smolagents import CodeAgent, OpenAIServerModel + +from apify import Actor + +OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' + + +async def main() -> None: + async with Actor: + actor_input = await Actor.get_input() or {} + task = actor_input.get('task', 'Compute the 12th Fibonacci number.') + model = actor_input.get('model', 'openai/gpt-4o-mini') + + # Route the LLM through the Apify OpenRouter proxy (no provider key needed). + llm = OpenAIServerModel( + model_id=model, + api_base=OPENROUTER_BASE_URL, + api_key=os.environ['APIFY_TOKEN'], + ) + # A `CodeAgent` writes and runs Python code to solve the task. + agent = CodeAgent(tools=[], model=llm) + + result = agent.run(task) + Actor.log.info(f'Agent result:\n{result}') + await Actor.push_data({'task': task, 'result': str(result)}) + + +if __name__ == '__main__': + asyncio.run(main()) From 622a72003da64fec5b42a90e76943ca4b9e1b3b6 Mon Sep 17 00:00:00 2001 From: Vlada Dusek Date: Fri, 3 Jul 2026 13:30:24 +0200 Subject: [PATCH 3/6] docs: align AI agents guide examples with their Actor templates --- docs/03_guides/13_ai_agents.mdx | 32 +++++++++++++++++----------- docs/03_guides/code/13_crewai.py | 27 +++++++++++++++++------ docs/03_guides/code/13_langgraph.py | 12 +++++++++-- docs/03_guides/code/13_pydanticai.py | 23 ++++++++++++++------ docs/03_guides/code/13_smolagents.py | 15 +++++++------ 5 files changed, 74 insertions(+), 35 deletions(-) diff --git a/docs/03_guides/13_ai_agents.mdx b/docs/03_guides/13_ai_agents.mdx index 3c0c8a06..570e8224 100644 --- a/docs/03_guides/13_ai_agents.mdx +++ b/docs/03_guides/13_ai_agents.mdx @@ -4,10 +4,11 @@ title: Building AI agents description: Host AI agents built with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents as Apify Actors. --- +import CodeBlock from '@theme/CodeBlock'; import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock'; import PydanticaiExample from '!!raw-loader!roa-loader!./code/13_pydanticai.py'; -import CrewaiExample from '!!raw-loader!roa-loader!./code/13_crewai.py'; +import CrewaiExample from '!!raw-loader!./code/13_crewai.py'; import LanggraphExample from '!!raw-loader!roa-loader!./code/13_langgraph.py'; import LlamaindexExample from '!!raw-loader!roa-loader!./code/13_llamaindex.py'; import SmolagentsExample from '!!raw-loader!roa-loader!./code/13_smolagents.py'; @@ -52,37 +53,39 @@ Each section below shows a complete, single-file Actor for one framework. They a ## PydanticAI -[PydanticAI](https://ai.pydantic.dev/) is an agent framework from the team behind Pydantic. It is strongly typed and integrates naturally with the [Pydantic models](./input-validation) the Apify SDK already uses. The following Actor runs an agent for a single prompt: +[PydanticAI](https://ai.pydantic.dev/) is an agent framework from the team behind Pydantic. It's strongly typed and integrates naturally with the [Pydantic models](./input-validation) the Apify SDK already uses. The following Actor generates a joke and returns it as a typed object: {PydanticaiExample} -Set `output_type` to a Pydantic model instead of `str` to get a validated object back, which maps directly onto a dataset row. +The `output_type=Joke` argument makes the agent return a validated `Joke` instance, which maps directly onto a dataset row. Set `output_type=str` instead to get plain text back. ## CrewAI -[CrewAI](https://www.crewai.com/) models a problem as a "crew" of role-playing agents that work through tasks. The following Actor defines a single analyst agent and one task: +[CrewAI](https://www.crewai.com/) models a problem as a "crew" of role-playing agents that work through tasks. The following Actor defines a single analyst agent that uses an Apify Actor as a tool to answer a query: - +{/* Not runnable from the docs: CrewAI reads the LLM key from OPENAI_API_KEY, which the shared example runner doesn't provide. */} + {CrewaiExample} - + Note that: - `kickoff_async` runs the crew without blocking the Actor's event loop. +- `ApifyActorsTool('apify/instagram-scraper')` gives the agent the [Instagram Scraper](https://apify.com/apify/instagram-scraper) as a tool. It comes from the `crewai[tools]` package and reads its token from `APIFY_API_TOKEN`, which the example sets from the platform's `APIFY_TOKEN`. - CrewAI calls the LLM through [LiteLLM](https://docs.litellm.ai/), so this example reads `OPENAI_API_KEY`. To route it through the Apify OpenRouter proxy instead, configure a custom `LLM` (see the [CrewAI LLM docs](https://docs.crewai.com/concepts/llms)). -- On a fresh container, crewAI shows a one-time trace-consent prompt. The template sets `CREWAI_TESTING=true` to suppress it; do the same in your Dockerfile. +- On a fresh container, CrewAI shows a one-time trace-consent prompt. The template sets `CREWAI_TESTING=true` to suppress it. Do the same in your Dockerfile. ## LangGraph -[LangGraph](https://www.langchain.com/langgraph) builds an agent as a graph with explicit state, which makes complex, multi-step control flow easy to follow. It builds on [LangChain](https://www.langchain.com/), so any LangChain chat model and tool works. The following Actor runs a single-turn agent: +[LangGraph](https://www.langchain.com/langgraph) builds an agent as a graph with explicit state, which makes complex, multi-step control flow easy to follow. It builds on [LangChain](https://www.langchain.com/), so any LangChain chat model and tool works. The following Actor runs an agent with a single tool: {LanggraphExample} -The example passes an empty `tools` list for brevity. Add LangChain tools to give the agent abilities, and read the final answer from the last message in the returned state. +The agent decides on its own when to call the `sum_numbers` tool, and the answer is read from the last message in the returned state. Add more LangChain tools to extend it, including Apify Actors (see [Using Apify Actors as tools](#using-apify-actors-as-tools)). ## LlamaIndex @@ -96,6 +99,7 @@ Note that: - `OpenAILike` is the LlamaIndex LLM class for OpenAI-compatible endpoints such as the Apify OpenRouter proxy. It needs the `llama-index-llms-openai-like` package. - The agent decides on its own when to call the `word_count` tool. Add `FunctionTool`s of your own to extend it. +- To reason over your own data, wrap an Apify Actor in a `FunctionTool` (see [Using Apify Actors as tools](#using-apify-actors-as-tools)), as the [LlamaIndex template](https://apify.com/templates/python-llamaindex-agent) does with a contact-details scraper. ## Smolagents @@ -105,21 +109,23 @@ Note that: {SmolagentsExample} -A `CodeAgent` executes the Python code it generates, so run it in the isolated Actor container rather than on your own machine. Pass tools such as `WebSearchTool` in the `tools` list to let it gather information. +This agent uses `WebSearchTool` to fetch the latest news, then writes and runs Python code to summarize it. Because a `CodeAgent` executes the code it generates, run it in the isolated Actor container rather than on your own machine. ## Using Apify Actors as tools An agent becomes useful once it can act on the world. On Apify, any of the thousands of Actors in the [Apify Store](https://apify.com/store) can become a tool: a scraper that fetches data, a browser automation that fills a form, or an API wrapper that posts a message. -For LangChain-based frameworks, such as LangGraph and CrewAI, the [`langchain-apify`](https://github.com/apify/langchain-apify) package exposes any Actor as a tool with a single line: +Some frameworks ship a ready-made wrapper for this. For LangGraph and other [LangChain](https://www.langchain.com/)-based agents, the [`langchain-apify`](https://github.com/apify/langchain-apify) package exposes any Actor as a tool with a single line: ```python -from crewai_tools import ApifyActorsTool +from langchain_apify import ApifyActorsTool # Let the agent scrape Instagram profiles by calling the apify/instagram-scraper Actor. tools = [ApifyActorsTool('apify/instagram-scraper')] ``` +CrewAI ships the same tool as `crewai_tools.ApifyActorsTool`, as the [CrewAI example](#crewai) above shows. + For any other framework, call the Actor directly through the Actor's preconfigured API client and read its dataset: ```python @@ -137,7 +143,7 @@ For details on calling other Actors, see [Interacting with other Actors](../conc Agents run on the standard [Apify Python base image](https://hub.docker.com/r/apify/actor-python), so no browser or extra system dependencies are needed. Add `apify` and your framework's packages to `requirements.txt`: - PydanticAI: `pydantic-ai` -- CrewAI: `crewai` (or `crewai[tools]` for `ApifyActorsTool`) +- CrewAI: `crewai[tools]` (the `tools` extra provides `ApifyActorsTool`) - LangGraph: `langchain`, `langchain-openai`, `langgraph` - LlamaIndex: `llama-index`, `llama-index-llms-openai-like` - Smolagents: `smolagents[openai]` diff --git a/docs/03_guides/code/13_crewai.py b/docs/03_guides/code/13_crewai.py index 04949b84..546f9813 100644 --- a/docs/03_guides/code/13_crewai.py +++ b/docs/03_guides/code/13_crewai.py @@ -1,33 +1,46 @@ import asyncio +import os from crewai import Agent, Crew, Task +from crewai_tools import ApifyActorsTool from apify import Actor +# On a fresh container, CrewAI shows a one-time trace-consent prompt that blocks on +# stdin. `CREWAI_TESTING=true` is the only flag that suppresses it. +os.environ.setdefault('CREWAI_TESTING', 'true') + async def main() -> None: async with Actor: actor_input = await Actor.get_input() or {} - topic = actor_input.get('topic', 'the Apify platform') + query = actor_input.get( + 'query', 'Summarize the latest posts on the @openai Instagram profile.' + ) model = actor_input.get('model', 'gpt-4o-mini') # CrewAI calls the LLM through LiteLLM, which reads OPENAI_API_KEY. + # `ApifyActorsTool` reads APIFY_API_TOKEN. The platform injects APIFY_TOKEN. + os.environ.setdefault('APIFY_API_TOKEN', os.environ['APIFY_TOKEN']) + + # The agent can run any Apify Actor as a tool, here the Instagram scraper. analyst = Agent( - role='Research Analyst', - goal=f'Write a short, accurate summary about {topic}.', - backstory='An analyst who turns a topic into a concise brief.', + role='Social Media Analyst', + goal='Analyze social media profiles and summarize the findings.', + backstory='An analyst who turns raw social media data into concise insights.', + tools=[ApifyActorsTool('apify/instagram-scraper')], llm=model, ) task = Task( - description=f'Write a three-sentence summary about {topic}.', - expected_output='A three-sentence summary.', + description=query, + expected_output='A short, readable summary that answers the query.', agent=analyst, ) # `kickoff_async` keeps the Actor's event loop responsive. result = await Crew(agents=[analyst], tasks=[task]).kickoff_async() Actor.log.info(f'Crew result:\n{result.raw}') - await Actor.push_data({'topic': topic, 'summary': result.raw}) + await Actor.push_data({'query': query, 'summary': result.raw}) if __name__ == '__main__': diff --git a/docs/03_guides/code/13_langgraph.py b/docs/03_guides/code/13_langgraph.py index 64d4ec0b..0d990daa 100644 --- a/docs/03_guides/code/13_langgraph.py +++ b/docs/03_guides/code/13_langgraph.py @@ -2,6 +2,7 @@ import os from langchain.agents import create_agent +from langchain_core.tools import tool from langchain_openai import ChatOpenAI from apify import Actor @@ -9,10 +10,16 @@ OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' +@tool +def sum_numbers(numbers: list[int]) -> int: + """Return the sum of a list of numbers.""" + return sum(numbers) + + async def main() -> None: async with Actor: actor_input = await Actor.get_input() or {} - query = actor_input.get('query', 'What is an Apify Actor?') + query = actor_input.get('query', 'What is the sum of 128, 64, and 32?') model = actor_input.get('model', 'openai/gpt-4o-mini') # Route the LLM through the Apify OpenRouter proxy (no provider key needed). @@ -21,7 +28,8 @@ async def main() -> None: base_url=OPENROUTER_BASE_URL, api_key=os.environ['APIFY_TOKEN'], ) - agent = create_agent(llm, tools=[]) + # The agent decides on its own when to call the `sum_numbers` tool. + agent = create_agent(llm, tools=[sum_numbers]) result = await agent.ainvoke({'messages': [('user', query)]}) answer = result['messages'][-1].content diff --git a/docs/03_guides/code/13_pydanticai.py b/docs/03_guides/code/13_pydanticai.py index 415edfcd..083da4b5 100644 --- a/docs/03_guides/code/13_pydanticai.py +++ b/docs/03_guides/code/13_pydanticai.py @@ -1,6 +1,7 @@ import asyncio import os +from pydantic import BaseModel from pydantic_ai import Agent from pydantic_ai.models.openai import OpenAIChatModel from pydantic_ai.providers.openai import OpenAIProvider @@ -10,10 +11,17 @@ OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' +class Joke(BaseModel): + """The agent's typed output: a joke split into its setup and punchline.""" + + setup: str + punchline: str + + async def main() -> None: async with Actor: actor_input = await Actor.get_input() or {} - prompt = actor_input.get('prompt', 'Explain Apify Actors in two sentences.') + topic = actor_input.get('topic', 'bad weather') model = actor_input.get('model', 'openai/gpt-4o-mini') # Route the LLM through the Apify OpenRouter proxy (no provider key needed). @@ -21,15 +29,18 @@ async def main() -> None: base_url=OPENROUTER_BASE_URL, api_key=os.environ['APIFY_TOKEN'], ) + # `output_type=Joke` makes the agent return a validated `Joke` instance. agent = Agent( OpenAIChatModel(model, provider=provider), - output_type=str, - system_prompt='You are a concise, helpful assistant.', + output_type=Joke, + system_prompt='You are a witty comedian. Write a single short joke.', ) - result = await agent.run(user_prompt=prompt) - Actor.log.info(f'Agent response:\n{result.output}') - await Actor.push_data({'prompt': prompt, 'response': result.output}) + joke = (await agent.run(user_prompt=f'Tell me a joke about {topic}.')).output + Actor.log.info(f'Joke:\n{joke.setup}\n{joke.punchline}') + await Actor.push_data( + {'topic': topic, 'setup': joke.setup, 'punchline': joke.punchline} + ) if __name__ == '__main__': diff --git a/docs/03_guides/code/13_smolagents.py b/docs/03_guides/code/13_smolagents.py index 19dc0e00..f5d29d31 100644 --- a/docs/03_guides/code/13_smolagents.py +++ b/docs/03_guides/code/13_smolagents.py @@ -1,7 +1,7 @@ import asyncio import os -from smolagents import CodeAgent, OpenAIServerModel +from smolagents import CodeAgent, OpenAIServerModel, WebSearchTool from apify import Actor @@ -11,7 +11,7 @@ async def main() -> None: async with Actor: actor_input = await Actor.get_input() or {} - task = actor_input.get('task', 'Compute the 12th Fibonacci number.') + topic = actor_input.get('topic', 'open source AI') model = actor_input.get('model', 'openai/gpt-4o-mini') # Route the LLM through the Apify OpenRouter proxy (no provider key needed). @@ -20,12 +20,13 @@ async def main() -> None: api_base=OPENROUTER_BASE_URL, api_key=os.environ['APIFY_TOKEN'], ) - # A `CodeAgent` writes and runs Python code to solve the task. - agent = CodeAgent(tools=[], model=llm) + # A `CodeAgent` writes and runs Python code to solve the task. Here it uses + # `WebSearchTool` to gather the latest news before summarizing it. + agent = CodeAgent(tools=[WebSearchTool()], model=llm) - result = agent.run(task) - Actor.log.info(f'Agent result:\n{result}') - await Actor.push_data({'task': task, 'result': str(result)}) + result = agent.run(f'Find and summarize the latest news about {topic}.') + Actor.log.info(f'Summary:\n{result}') + await Actor.push_data({'topic': topic, 'summary': str(result)}) if __name__ == '__main__': From 817d0e0be8a188ef732145470d3651076d09b880 Mon Sep 17 00:00:00 2001 From: Vlada Dusek Date: Fri, 3 Jul 2026 17:04:06 +0200 Subject: [PATCH 4/6] docs: refine AI agents guide and renumber to 14 --- docs/01_introduction/quick-start.mdx | 2 +- .../{13_ai_agents.mdx => 14_ai_agents.mdx} | 107 ++++++++++++------ .../code/{13_crewai.py => 14_crewai.py} | 0 .../code/{13_langgraph.py => 14_langgraph.py} | 0 .../{13_llamaindex.py => 14_llamaindex.py} | 0 .../{13_pydanticai.py => 14_pydanticai.py} | 0 .../{13_smolagents.py => 14_smolagents.py} | 0 7 files changed, 72 insertions(+), 37 deletions(-) rename docs/03_guides/{13_ai_agents.mdx => 14_ai_agents.mdx} (75%) rename docs/03_guides/code/{13_crewai.py => 14_crewai.py} (100%) rename docs/03_guides/code/{13_langgraph.py => 14_langgraph.py} (100%) rename docs/03_guides/code/{13_llamaindex.py => 14_llamaindex.py} (100%) rename docs/03_guides/code/{13_pydanticai.py => 14_pydanticai.py} (100%) rename docs/03_guides/code/{13_smolagents.py => 14_smolagents.py} (100%) diff --git a/docs/01_introduction/quick-start.mdx b/docs/01_introduction/quick-start.mdx index 19231b81..9bb53038 100644 --- a/docs/01_introduction/quick-start.mdx +++ b/docs/01_introduction/quick-start.mdx @@ -112,7 +112,7 @@ To see how you can integrate the Apify SDK with popular scraping libraries and f - [Adaptive scraping with Scrapling](./guides/scrapling) - [LLM-ready scraping with Crawl4AI](./guides/crawl4ai) - [Browser AI agents with Browser Use](./guides/browser-use) -- [Building AI agents](./guides/ai-agents) +- [Hosting AI agents](./guides/ai-agents) For other aspects of Actor development, explore these guides: diff --git a/docs/03_guides/13_ai_agents.mdx b/docs/03_guides/14_ai_agents.mdx similarity index 75% rename from docs/03_guides/13_ai_agents.mdx rename to docs/03_guides/14_ai_agents.mdx index 570e8224..5c2a3bfb 100644 --- a/docs/03_guides/13_ai_agents.mdx +++ b/docs/03_guides/14_ai_agents.mdx @@ -1,17 +1,17 @@ --- id: ai-agents -title: Building AI agents -description: Host AI agents built with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents as Apify Actors. +title: Hosting AI agents +description: Host AI agents built with LangGraph, CrewAI, PydanticAI, LlamaIndex, or Smolagents as Apify Actors. --- import CodeBlock from '@theme/CodeBlock'; import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock'; -import PydanticaiExample from '!!raw-loader!roa-loader!./code/13_pydanticai.py'; -import CrewaiExample from '!!raw-loader!./code/13_crewai.py'; -import LanggraphExample from '!!raw-loader!roa-loader!./code/13_langgraph.py'; -import LlamaindexExample from '!!raw-loader!roa-loader!./code/13_llamaindex.py'; -import SmolagentsExample from '!!raw-loader!roa-loader!./code/13_smolagents.py'; +import LanggraphExample from '!!raw-loader!roa-loader!./code/14_langgraph.py'; +import CrewaiExample from '!!raw-loader!./code/14_crewai.py'; +import PydanticaiExample from '!!raw-loader!roa-loader!./code/14_pydanticai.py'; +import LlamaindexExample from '!!raw-loader!roa-loader!./code/14_llamaindex.py'; +import SmolagentsExample from '!!raw-loader!roa-loader!./code/14_smolagents.py'; In this guide, you'll learn how to host an AI agent as an Apify Actor, using the agent framework of your choice. @@ -32,10 +32,10 @@ Apify Actors are a natural home for agents: Apify maintains a ready-made Actor template for each of the popular agent frameworks. Each template is a complete, deployable Actor that you can use as a starting point. Pick the one that matches the framework you already use, or the style of agent you want to build: | Framework | Good for | Template | -|---|---|---| -| [PydanticAI](#pydanticai) | Typed, Pydantic-native agents with tool calling | [`python-pydanticai`](https://apify.com/templates/python-pydanticai) | -| [CrewAI](#crewai) | Multi-agent "crews" that collaborate on a task | [`python-crewai`](https://apify.com/templates/python-crewai) | +| --- | --- | --- | | [LangGraph](#langgraph) | Graph-based agents with explicit state and control flow | [`python-langgraph`](https://apify.com/templates/python-langgraph) | +| [CrewAI](#crewai) | Multi-agent "crews" that collaborate on a task | [`python-crewai`](https://apify.com/templates/python-crewai) | +| [PydanticAI](#pydanticai) | Typed, Pydantic-native agents with tool calling | [`python-pydanticai`](https://apify.com/templates/python-pydanticai) | | [LlamaIndex](#llamaindex) | Retrieval-augmented agents over your own data | [`python-llamaindex-agent`](https://apify.com/templates/python-llamaindex-agent) | | [Smolagents](#smolagents) | Lightweight code-writing agents from Hugging Face | [`python-smolagents`](https://apify.com/templates/python-smolagents) | @@ -51,21 +51,37 @@ The second is to call a provider such as OpenAI directly with your own API key, Each section below shows a complete, single-file Actor for one framework. They all read the input, run the agent, and store the result in the default dataset. -## PydanticAI +## LangGraph + +[LangGraph](https://www.langchain.com/langgraph) builds an agent as a graph with explicit state, which makes complex, multi-step control flow easy to follow. It builds on [LangChain](https://www.langchain.com/), so any LangChain chat model and tool works. To install it, use: + +```bash +pip install langchain langchain-openai langgraph +``` -[PydanticAI](https://ai.pydantic.dev/) is an agent framework from the team behind Pydantic. It's strongly typed and integrates naturally with the [Pydantic models](./input-validation) the Apify SDK already uses. The following Actor generates a joke and returns it as a typed object: +The following Actor runs an agent with a single tool: - {PydanticaiExample} + {LanggraphExample} -The `output_type=Joke` argument makes the agent return a validated `Joke` instance, which maps directly onto a dataset row. Set `output_type=str` instead to get plain text back. +Note that: + +- `ChatOpenAI` points its `base_url` at the Apify OpenRouter proxy, so any LangChain chat model works without a provider key. +- The agent decides on its own when to call the `sum_numbers` tool, and the answer is read from the last message in the returned state. +- Add more LangChain tools to extend it, including Apify Actors (see [Using Apify Actors as tools](#using-apify-actors-as-tools)). ## CrewAI -[CrewAI](https://www.crewai.com/) models a problem as a "crew" of role-playing agents that work through tasks. The following Actor defines a single analyst agent that uses an Apify Actor as a tool to answer a query: +[CrewAI](https://www.crewai.com/) models a problem as a "crew" of role-playing agents that work through tasks. To install it, use: -{/* Not runnable from the docs: CrewAI reads the LLM key from OPENAI_API_KEY, which the shared example runner doesn't provide. */} +```bash +pip install "crewai[tools]" +``` + +The following Actor defines a single analyst agent that uses an Apify Actor as a tool to answer a query: + +{/*Not runnable from the docs: CrewAI reads the LLM key from OPENAI_API_KEY, which the shared example runner doesn't provide.*/} {CrewaiExample} @@ -77,19 +93,34 @@ Note that: - CrewAI calls the LLM through [LiteLLM](https://docs.litellm.ai/), so this example reads `OPENAI_API_KEY`. To route it through the Apify OpenRouter proxy instead, configure a custom `LLM` (see the [CrewAI LLM docs](https://docs.crewai.com/concepts/llms)). - On a fresh container, CrewAI shows a one-time trace-consent prompt. The template sets `CREWAI_TESTING=true` to suppress it. Do the same in your Dockerfile. -## LangGraph +## PydanticAI + +[PydanticAI](https://ai.pydantic.dev/) is an agent framework from the team behind Pydantic. It's strongly typed and integrates naturally with the [Pydantic models](./input-validation) the Apify SDK already uses. To install it, use: -[LangGraph](https://www.langchain.com/langgraph) builds an agent as a graph with explicit state, which makes complex, multi-step control flow easy to follow. It builds on [LangChain](https://www.langchain.com/), so any LangChain chat model and tool works. The following Actor runs an agent with a single tool: +```bash +pip install pydantic-ai +``` + +The following Actor generates a joke and returns it as a typed object: - {LanggraphExample} + {PydanticaiExample} -The agent decides on its own when to call the `sum_numbers` tool, and the answer is read from the last message in the returned state. Add more LangChain tools to extend it, including Apify Actors (see [Using Apify Actors as tools](#using-apify-actors-as-tools)). +Note that: + +- The agent reaches the LLM through the Apify OpenRouter proxy via `OpenAIChatModel` and a custom `OpenAIProvider`, so no provider API key is needed. +- `output_type=Joke` makes the agent return a validated `Joke` instance, which maps directly onto a dataset row. Set `output_type=str` instead to get plain text back. ## LlamaIndex -[LlamaIndex](https://www.llamaindex.ai/) is built for retrieval-augmented agents that reason over your own data. The following Actor runs a `ReActAgent` with a single tool: +[LlamaIndex](https://www.llamaindex.ai/) is built for retrieval-augmented agents that reason over your own data. To install it, use: + +```bash +pip install llama-index llama-index-llms-openai-like +``` + +The following Actor runs a `ReActAgent` with a single tool: {LlamaindexExample} @@ -103,13 +134,23 @@ Note that: ## Smolagents -[Smolagents](https://github.com/huggingface/smolagents) is a lightweight framework from Hugging Face whose agents write and run Python code to solve a task. The following Actor runs a `CodeAgent`: +[Smolagents](https://github.com/huggingface/smolagents) is a lightweight framework from Hugging Face whose agents write and run Python code to solve a task. To install it, use: + +```bash +pip install "smolagents[openai]" +``` + +The following Actor runs a `CodeAgent`: {SmolagentsExample} -This agent uses `WebSearchTool` to fetch the latest news, then writes and runs Python code to summarize it. Because a `CodeAgent` executes the code it generates, run it in the isolated Actor container rather than on your own machine. +Note that: + +- `OpenAIServerModel` points `api_base` at the Apify OpenRouter proxy, so no provider API key is needed. +- The agent uses `WebSearchTool` to fetch the latest news, then writes and runs Python code to summarize it. +- Because a `CodeAgent` executes the code it generates, run it in the isolated Actor container rather than on your own machine. ## Using Apify Actors as tools @@ -140,13 +181,7 @@ For details on calling other Actors, see [Interacting with other Actors](../conc ## Running on the Apify platform -Agents run on the standard [Apify Python base image](https://hub.docker.com/r/apify/actor-python), so no browser or extra system dependencies are needed. Add `apify` and your framework's packages to `requirements.txt`: - -- PydanticAI: `pydantic-ai` -- CrewAI: `crewai[tools]` (the `tools` extra provides `ApifyActorsTool`) -- LangGraph: `langchain`, `langchain-openai`, `langgraph` -- LlamaIndex: `llama-index`, `llama-index-llms-openai-like` -- Smolagents: `smolagents[openai]` +Agents run on the standard [Apify Python base image](https://hub.docker.com/r/apify/actor-python), so no browser or extra system dependencies are needed. Add `apify` and the packages shown in your framework's section above to `requirements.txt`, then deploy the Actor as usual. To monetize the agent, use [pay-per-event charging](../concepts/pay-per-event). You define events such as `task-completed` in the Actor's monetization settings and trigger them from the code: @@ -158,15 +193,15 @@ This lets you charge users directly from the Actor and cover the cost of executi ## Conclusion -In this guide, you learned how to host an AI agent as an Apify Actor. You can now build an agent with PydanticAI, CrewAI, LangGraph, LlamaIndex, or Smolagents, connect it to an LLM through the Apify OpenRouter proxy, give it Apify Actors as tools, and monetize it with pay-per-event. To get started, see the [Actor templates](https://apify.com/templates/categories/python). If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy building! +In this guide, you learned how to host an AI agent as an Apify Actor. You can now build an agent with LangGraph, CrewAI, PydanticAI, LlamaIndex, or Smolagents, connect it to an LLM through the Apify OpenRouter proxy, give it Apify Actors as tools, and monetize it with pay-per-event. To get started, see the [Actor templates](https://apify.com/templates/categories/python). If you have questions or need assistance, feel free to reach out on our [GitHub](https://github.com/apify/apify-sdk-python) or join our [Discord community](https://discord.com/invite/jyEM2PRvMU). Happy building! ## Additional resources -- [Apify templates: PydanticAI](https://apify.com/templates/python-pydanticai) -- [Apify templates: CrewAI](https://apify.com/templates/python-crewai) -- [Apify templates: LangGraph](https://apify.com/templates/python-langgraph) -- [Apify templates: LlamaIndex](https://apify.com/templates/python-llamaindex-agent) -- [Apify templates: Smolagents](https://apify.com/templates/python-smolagents) +- [Apify: LangGraph template](https://apify.com/templates/python-langgraph) +- [Apify: CrewAI template](https://apify.com/templates/python-crewai) +- [Apify: PydanticAI template](https://apify.com/templates/python-pydanticai) +- [Apify: LlamaIndex template](https://apify.com/templates/python-llamaindex-agent) +- [Apify: Smolagents template](https://apify.com/templates/python-smolagents) - [Apify: actor-templates repository](https://github.com/apify/actor-templates) - [Apify: OpenRouter proxy](https://apify.com/apify/openrouter) - [Apify: langchain-apify integration](https://github.com/apify/langchain-apify) diff --git a/docs/03_guides/code/13_crewai.py b/docs/03_guides/code/14_crewai.py similarity index 100% rename from docs/03_guides/code/13_crewai.py rename to docs/03_guides/code/14_crewai.py diff --git a/docs/03_guides/code/13_langgraph.py b/docs/03_guides/code/14_langgraph.py similarity index 100% rename from docs/03_guides/code/13_langgraph.py rename to docs/03_guides/code/14_langgraph.py diff --git a/docs/03_guides/code/13_llamaindex.py b/docs/03_guides/code/14_llamaindex.py similarity index 100% rename from docs/03_guides/code/13_llamaindex.py rename to docs/03_guides/code/14_llamaindex.py diff --git a/docs/03_guides/code/13_pydanticai.py b/docs/03_guides/code/14_pydanticai.py similarity index 100% rename from docs/03_guides/code/13_pydanticai.py rename to docs/03_guides/code/14_pydanticai.py diff --git a/docs/03_guides/code/13_smolagents.py b/docs/03_guides/code/14_smolagents.py similarity index 100% rename from docs/03_guides/code/13_smolagents.py rename to docs/03_guides/code/14_smolagents.py From 24096337a3b16c09ae89a7183c57252642880d32 Mon Sep 17 00:00:00 2001 From: Vlada Dusek Date: Fri, 3 Jul 2026 17:23:39 +0200 Subject: [PATCH 5/6] docs: route the CrewAI agent example through the OpenRouter proxy --- docs/03_guides/14_ai_agents.mdx | 24 ++++++++--------- docs/03_guides/code/14_crewai.py | 45 ++++++++++++++++++++------------ 2 files changed, 39 insertions(+), 30 deletions(-) diff --git a/docs/03_guides/14_ai_agents.mdx b/docs/03_guides/14_ai_agents.mdx index 5c2a3bfb..e055dec3 100644 --- a/docs/03_guides/14_ai_agents.mdx +++ b/docs/03_guides/14_ai_agents.mdx @@ -4,11 +4,10 @@ title: Hosting AI agents description: Host AI agents built with LangGraph, CrewAI, PydanticAI, LlamaIndex, or Smolagents as Apify Actors. --- -import CodeBlock from '@theme/CodeBlock'; import RunnableCodeBlock from '@site/src/components/RunnableCodeBlock'; import LanggraphExample from '!!raw-loader!roa-loader!./code/14_langgraph.py'; -import CrewaiExample from '!!raw-loader!./code/14_crewai.py'; +import CrewaiExample from '!!raw-loader!roa-loader!./code/14_crewai.py'; import PydanticaiExample from '!!raw-loader!roa-loader!./code/14_pydanticai.py'; import LlamaindexExample from '!!raw-loader!roa-loader!./code/14_llamaindex.py'; import SmolagentsExample from '!!raw-loader!roa-loader!./code/14_smolagents.py'; @@ -37,7 +36,7 @@ Apify maintains a ready-made Actor template for each of the popular agent framew | [CrewAI](#crewai) | Multi-agent "crews" that collaborate on a task | [`python-crewai`](https://apify.com/templates/python-crewai) | | [PydanticAI](#pydanticai) | Typed, Pydantic-native agents with tool calling | [`python-pydanticai`](https://apify.com/templates/python-pydanticai) | | [LlamaIndex](#llamaindex) | Retrieval-augmented agents over your own data | [`python-llamaindex-agent`](https://apify.com/templates/python-llamaindex-agent) | -| [Smolagents](#smolagents) | Lightweight code-writing agents from Hugging Face | [`python-smolagents`](https://apify.com/templates/python-smolagents) | +| [Smolagents](#smolagents) | Lightweight code-writing agents | [`python-smolagents`](https://apify.com/templates/python-smolagents) | All of these templates live in the [actor-templates repository](https://github.com/apify/actor-templates), and you can scaffold any of them with the [Apify CLI](https://docs.apify.com/cli), for example `apify create my-agent --template python-pydanticai`. @@ -45,9 +44,9 @@ All of these templates live in the [actor-templates repository](https://github.c Every agent needs an LLM, and there are two ways to provide one. -The first is the [Apify OpenRouter proxy](https://apify.com/apify/openrouter), an OpenAI-compatible endpoint at `https://openrouter.apify.actor/api/v1` that fronts the full [OpenRouter](https://openrouter.ai) model catalog. The token usage is billed against the Apify account running the Actor, so no provider API key is required. The Actor authenticates with the proxy using the `APIFY_TOKEN` that the platform injects into every run. Any framework with an OpenAI-compatible client can point its base URL at the proxy, which is what most examples below do. To switch models, change the `model` input to any [OpenRouter model slug](https://openrouter.ai/models), for example `openai/gpt-4o-mini`. +The first is the [Apify OpenRouter proxy](https://apify.com/apify/openrouter), an OpenAI-compatible endpoint at `https://openrouter.apify.actor/api/v1` that fronts the full [OpenRouter](https://openrouter.ai) model catalog. The token usage is billed against the Apify account running the Actor, so no provider API key is required. The Actor authenticates with the proxy using the `APIFY_TOKEN` that the platform injects into every run. Any framework with an OpenAI-compatible client can point its base URL at the proxy, which is what every example below does. To switch models, change the `model` input to any [OpenRouter model slug](https://openrouter.ai/models), for example `openai/gpt-4o-mini`. -The second is to call a provider such as OpenAI directly with your own API key, which the CrewAI example below does through LiteLLM. Keep the key out of the Actor input and source code. Read it from an environment variable, which on the platform you set as a [secret environment variable](https://docs.apify.com/platform/actors/development/programming-interface/environment-variables) and locally you export in your shell. +The second is to call a provider such as OpenAI directly with your own API key. Keep the key out of the Actor input and source code. Read it from an environment variable, which on the platform you set as a [secret environment variable](https://docs.apify.com/platform/actors/development/programming-interface/environment-variables) and locally you export in your shell. Each section below shows a complete, single-file Actor for one framework. They all read the input, run the agent, and store the result in the default dataset. @@ -76,21 +75,20 @@ Note that: [CrewAI](https://www.crewai.com/) models a problem as a "crew" of role-playing agents that work through tasks. To install it, use: ```bash -pip install "crewai[tools]" +pip install crewai ``` -The following Actor defines a single analyst agent that uses an Apify Actor as a tool to answer a query: +The following Actor defines a single analyst agent with one tool: -{/*Not runnable from the docs: CrewAI reads the LLM key from OPENAI_API_KEY, which the shared example runner doesn't provide.*/} - + {CrewaiExample} - + Note that: +- CrewAI's `LLM` points its `base_url` at the Apify OpenRouter proxy. The `openai/` model prefix selects its OpenAI-compatible client, so no provider key is needed. - `kickoff_async` runs the crew without blocking the Actor's event loop. -- `ApifyActorsTool('apify/instagram-scraper')` gives the agent the [Instagram Scraper](https://apify.com/apify/instagram-scraper) as a tool. It comes from the `crewai[tools]` package and reads its token from `APIFY_API_TOKEN`, which the example sets from the platform's `APIFY_TOKEN`. -- CrewAI calls the LLM through [LiteLLM](https://docs.litellm.ai/), so this example reads `OPENAI_API_KEY`. To route it through the Apify OpenRouter proxy instead, configure a custom `LLM` (see the [CrewAI LLM docs](https://docs.crewai.com/concepts/llms)). +- The agent decides on its own when to call the `average` tool. Add more tools to extend it, including Apify Actors (see [Using Apify Actors as tools](#using-apify-actors-as-tools)). - On a fresh container, CrewAI shows a one-time trace-consent prompt. The template sets `CREWAI_TESTING=true` to suppress it. Do the same in your Dockerfile. ## PydanticAI @@ -165,7 +163,7 @@ from langchain_apify import ApifyActorsTool tools = [ApifyActorsTool('apify/instagram-scraper')] ``` -CrewAI ships the same tool as `crewai_tools.ApifyActorsTool`, as the [CrewAI example](#crewai) above shows. +CrewAI ships the same tool as `crewai_tools.ApifyActorsTool` in its `crewai[tools]` package. For any other framework, call the Actor directly through the Actor's preconfigured API client and read its dataset: diff --git a/docs/03_guides/code/14_crewai.py b/docs/03_guides/code/14_crewai.py index 546f9813..7fc02162 100644 --- a/docs/03_guides/code/14_crewai.py +++ b/docs/03_guides/code/14_crewai.py @@ -1,46 +1,57 @@ import asyncio import os -from crewai import Agent, Crew, Task -from crewai_tools import ApifyActorsTool +from crewai import LLM, Agent, Crew, Task +from crewai.tools import tool from apify import Actor +OPENROUTER_BASE_URL = 'https://openrouter.apify.actor/api/v1' + # On a fresh container, CrewAI shows a one-time trace-consent prompt that blocks on # stdin. `CREWAI_TESTING=true` is the only flag that suppresses it. os.environ.setdefault('CREWAI_TESTING', 'true') +@tool('Average') +def average(numbers: list[float]) -> float: + """Return the arithmetic mean of a list of numbers.""" + return sum(numbers) / len(numbers) + + async def main() -> None: async with Actor: actor_input = await Actor.get_input() or {} - query = actor_input.get( - 'query', 'Summarize the latest posts on the @openai Instagram profile.' + query = actor_input.get('query', 'What is the average of 12, 18, and 30?') + model = actor_input.get('model', 'openai/gpt-4o-mini') + + # Route the LLM through the Apify OpenRouter proxy (no provider key needed). + # The `openai/` prefix selects CrewAI's OpenAI-compatible client. The rest + # is the OpenRouter model slug sent to the proxy. + llm = LLM( + model=f'openai/{model}', + base_url=OPENROUTER_BASE_URL, + api_key=os.environ['APIFY_TOKEN'], ) - model = actor_input.get('model', 'gpt-4o-mini') - - # CrewAI calls the LLM through LiteLLM, which reads OPENAI_API_KEY. - # `ApifyActorsTool` reads APIFY_API_TOKEN. The platform injects APIFY_TOKEN. - os.environ.setdefault('APIFY_API_TOKEN', os.environ['APIFY_TOKEN']) - # The agent can run any Apify Actor as a tool, here the Instagram scraper. + # A one-agent crew: an analyst that answers using the `average` tool. analyst = Agent( - role='Social Media Analyst', - goal='Analyze social media profiles and summarize the findings.', - backstory='An analyst who turns raw social media data into concise insights.', - tools=[ApifyActorsTool('apify/instagram-scraper')], - llm=model, + role='Data Analyst', + goal='Answer numeric questions accurately.', + backstory='An analyst who turns raw numbers into clear answers.', + tools=[average], + llm=llm, ) task = Task( description=query, - expected_output='A short, readable summary that answers the query.', + expected_output='A short, readable answer to the query.', agent=analyst, ) # `kickoff_async` keeps the Actor's event loop responsive. result = await Crew(agents=[analyst], tasks=[task]).kickoff_async() Actor.log.info(f'Crew result:\n{result.raw}') - await Actor.push_data({'query': query, 'summary': result.raw}) + await Actor.push_data({'query': query, 'answer': result.raw}) if __name__ == '__main__': From 2fa02f9ca200c73e2fe7284efb73aaf2404cf731 Mon Sep 17 00:00:00 2001 From: Vlada Dusek Date: Fri, 3 Jul 2026 17:28:20 +0200 Subject: [PATCH 6/6] docs: align AI agent template order in README and introduction with the guide --- README.md | 4 ++-- docs/01_introduction/index.mdx | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index b1c2f316..bb29d002 100644 --- a/README.md +++ b/README.md @@ -116,7 +116,7 @@ Almost any Python project can become an Actor, including projects for: - **Web scraping and crawling** — The SDK is fully compatible with [Crawlee](https://crawlee.dev/python), which makes Apify a natural place to deploy and scale your crawlers (see the [Crawlee guide](https://docs.apify.com/sdk/python/docs/guides/crawlee)). It also works with other popular scraping libraries, such as [Scrapy](https://docs.apify.com/sdk/python/docs/guides/scrapy), [Scrapling](https://docs.apify.com/sdk/python/docs/guides/scrapling), or [Crawl4AI](https://docs.apify.com/sdk/python/docs/guides/crawl4ai). - **Browser automation** — Drive a real browser with [Playwright](https://docs.apify.com/sdk/python/docs/guides/playwright) or [Selenium](https://docs.apify.com/sdk/python/docs/guides/selenium), or with higher-level tools such as [Browser Use](https://docs.apify.com/sdk/python/docs/guides/browser-use). - **Web servers and APIs** — Run a [web server](https://docs.apify.com/sdk/python/docs/guides/running-webserver) inside an Actor to serve HTTP requests, for example to expose your scraper as a live API. -- **AI agents** — Host agents built with your framework of choice (see the [AI agents guide](https://docs.apify.com/sdk/python/docs/guides/ai-agents)). Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). +- **AI agents** — Host agents built with your framework of choice (see the [AI agents guide](https://docs.apify.com/sdk/python/docs/guides/ai-agents)). Ready-made Actor templates cover [LangGraph](https://apify.com/templates/python-langgraph), [CrewAI](https://apify.com/templates/python-crewai), [PydanticAI](https://apify.com/templates/python-pydanticai), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). - **MCP servers** — Deploy a Python MCP server as an Actor and make its tools available to any MCP client. See [MCP server](https://apify.com/templates/python-mcp-empty) and [MCP proxy](https://apify.com/templates/python-mcp-proxy) templates Whatever you build, the Apify SDK doesn't lock you into a particular framework. Bring the libraries you already use, and let Apify run your project in the cloud. @@ -199,7 +199,7 @@ The full SDK documentation lives at **[docs.apify.com/sdk/python](https://docs.a | [Overview](https://docs.apify.com/sdk/python/docs/overview) | What the SDK is, what Actors are, and how the pieces fit together. | | [Quick start](https://docs.apify.com/sdk/python/docs/quick-start) | Create, run, and deploy your first Python Actor. | | [Concepts](https://docs.apify.com/sdk/python/docs/concepts/actor-lifecycle) | Actor lifecycle, input, storages, events, proxy management, interacting with other Actors, webhooks, accessing the Apify API, logging, configuration, and pay-per-event. | -| [Guides](https://docs.apify.com/sdk/python/docs/guides/beautifulsoup-httpx) | Integrations with BeautifulSoup, Parsel, Playwright, Selenium, Crawlee, Scrapy, Scrapling, Crawl4AI, and Browser Use, plus building AI agents, running a web server, and using uv. | +| [Guides](https://docs.apify.com/sdk/python/docs/guides/beautifulsoup-httpx) | Integrations with BeautifulSoup, Parsel, Playwright, Selenium, Crawlee, Scrapy, Scrapling, Crawl4AI, and Browser Use, plus hosting AI agents, running a web server, and using uv. | | [Upgrading](https://docs.apify.com/sdk/python/docs/upgrading/upgrading-to-v4) | Migrating between major versions. | | [API reference](https://docs.apify.com/sdk/python/reference) | Generated reference for every class and method. | | [Changelog](https://docs.apify.com/sdk/python/docs/changelog) | Release history and breaking changes. | diff --git a/docs/01_introduction/index.mdx b/docs/01_introduction/index.mdx index b4db08e8..60eae5e2 100644 --- a/docs/01_introduction/index.mdx +++ b/docs/01_introduction/index.mdx @@ -41,7 +41,7 @@ Almost any Python project can become an Actor, including projects for: - **Web scraping and crawling** - The SDK is fully compatible with [Crawlee](https://crawlee.dev/python), which makes Apify a natural place to deploy and scale your crawlers (see the [Crawlee guide](./guides/crawlee)). It also works with other popular scraping libraries, such as [Scrapy](./guides/scrapy), [Scrapling](./guides/scrapling), or [Crawl4AI](./guides/crawl4ai). - **Browser automation** - Drive a real browser with [Playwright](./guides/playwright) or [Selenium](./guides/selenium), or with higher-level tools such as [Browser Use](./guides/browser-use). - **Web servers and APIs** - Run a [web server](./guides/running-webserver) inside an Actor to serve HTTP requests, for example to expose your scraper as a live API. -- **AI agents** - Host agents built with your framework of choice (see the [AI agents guide](./guides/ai-agents)). Ready-made Actor templates cover [PydanticAI](https://apify.com/templates/python-pydanticai), [CrewAI](https://apify.com/templates/python-crewai), [LangGraph](https://apify.com/templates/python-langgraph), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). +- **AI agents** - Host agents built with your framework of choice (see the [AI agents guide](./guides/ai-agents)). Ready-made Actor templates cover [LangGraph](https://apify.com/templates/python-langgraph), [CrewAI](https://apify.com/templates/python-crewai), [PydanticAI](https://apify.com/templates/python-pydanticai), [LlamaIndex](https://apify.com/templates/python-llamaindex-agent), and [Smolagents](https://apify.com/templates/python-smolagents). - **MCP servers** - Deploy a Python MCP server as an Actor and make its tools available to any MCP client. See the [MCP server](https://apify.com/templates/python-mcp-empty) and [MCP proxy](https://apify.com/templates/python-mcp-proxy) templates. Whatever you build, the Apify SDK doesn't lock you into a particular framework. Bring the libraries you already use, and let Apify run your project in the cloud.