> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aisearchapi.io/llms.txt
> Use this file to discover all available pages before exploring further.

# CrewAI

This is a **CrewAI integration** for the **AI Search API**.\
It connects your CrewAI agents with **context-aware search**, **multi-message prompts**, and **intelligent answers with citations**.

👉 Get started now:

* [Sign Up](https://app.aisearchapi.io/join)
* [Log In](https://app.aisearchapi.io/login)
* [Dashboard](https://app.aisearchapi.io/dashboard)

***

# Features

* 🔍 **Prompt + Context Search** – Send a query with structured context
* 💬 **Multi-Message Context** – Handle several user messages in one query
* 📚 **Source Citations** – Responses include references when available
* ⚡ **CrewAI Integration** – Works with Agent, Task, Crew right away
* 🖥️ **Local LLM Support** – Use Ollama for reasoning + Search API for live info
* 🛡️ **Error Handling** – Clear exceptions for invalid models or roles

***

# Installation

```bash theme={null}
pip install crewai-aisearchapi
```

***

# Quick Start (with Ollama + CrewAI)

```python theme={null}
from crewai import Agent, Task, Crew, Process, LLM
from crewai_aisearchapi import AISearchTool

llm = LLM(
    model="ollama/llama3.2:3b",
    base_url="http://localhost:11434",
    temperature=0.2,
)

tool = AISearchTool(api_key="your-api-key")

agent = Agent(
    role="Researcher",
    goal="Answer questions with context and sources.",
    backstory="Careful and concise.",
    tools=[tool],
    llm=llm,
    verbose=True,
)

task = Task(
    description="Answer: '{question}'. Keep it short.",
    expected_output="2–4 sentences.",
    agent=agent,
    markdown=True,
)

crew = Crew(agents=[agent], tasks=[task], process=Process.sequential, verbose=True)

if __name__ == "__main__":
    print(crew.kickoff(inputs={"question": "What is RLHF in AI?"}))
```

***

# Contextual Prompts

Add multiple context messages for better answers:

```python theme={null}
result = tool.run({
    "prompt": "Explain how RLHF improves AI safety.",
    "context": [
        {"role": "user", "content": "Keep it simple, I'm new to ML."},
        {"role": "user", "content": "Add one practical example."}
    ],
    "response_type": "markdown"
})
```

***

# Configuration Options

```python theme={null}
from crewai_aisearchapi import AISearchTool, AISearchToolConfig

config = AISearchToolConfig(
    default_response_type="markdown",
    include_sources=True,
    timeout=30,
    verbose=True
)

tool = AISearchTool(api_key="your-api-key", config=config)
```

***

# Handling Responses

The tool returns:

* **Answer** (AI response)
* **Sources** (when available)
* **Response time**

Example:

```text theme={null}
Reinforcement Learning with Human Feedback (RLHF) helps align AI models with human intent...

**Sources:**
- [1] https://example.com/rlhf-overview
- [2] https://research.example.org/rlhf

*Response time: 120ms*
```

***

# Environment Variables

```bash theme={null}
export AISEARCH_API_KEY="your-api-key"
```

In Python:

```python theme={null}
import os
from crewai_aisearchapi import AISearchTool

tool = AISearchTool(api_key=os.getenv("AISEARCH_API_KEY"))
```

***

# Troubleshooting

| Problem                | Fix                                              |
| ---------------------- | ------------------------------------------------ |
| **model not found**    | Run `ollama pull llama3.2:3b`                    |
| **context role error** | Ensure all context messages use `"role": "user"` |
| **API key error**      | Check `AISEARCH_API_KEY` is set correctly        |

***

# Resources

* [AI Search API Homepage](https://aisearchapi.io)
* [Docs](https://docs.aisearchapi.io)
* [Dashboard](https://app.aisearchapi.io/dashboard)
* [GitHub Issues](https://github.com/aisearchapi/aisearchapi-py/issues)

***

# License

[MIT License](https://github.com/aisearchapi/aisearchapi-crew-ai/blob/main/LICENSE)

***