### Install dappier-go SDK

Source: https://docs.dappier.com/integrations/go-sdk

Instructions for installing the dappier-go SDK using go get. This is the first step to integrate Dappier's capabilities into your Go applications.

```bash
go get github.com/DappierAI/dappier-go
```

--------------------------------

### Google ADK + Dappier Starter App Setup

Source: https://docs.dappier.com/integrations/google-adk-integration

Provides instructions for setting up and running a starter application that integrates Google ADK with Dappier SDK. This guide focuses on forking the project on Replit and preparing for API key configuration.

```APIDOC
Getting Started: Build the Google ADK + Dappier Starter App

Step 1: Fork the Starter App on Replit
  1. Open the project in your browser: 👉 [Google ADK + Dappier Starter App](https://replit.com/@dappier/Google-ADK-Dappier-Starter-App?v=1)
  2. Click "Fork" at the top-right to create your own copy.
  3. Replit will automatically set up the project environment and open the code editor.

Once forked, you are ready to configure your API keys. Proceed to Step 2 for API key setup.
```

--------------------------------

### Dappier RAG API Call Example

Source: https://docs.dappier.com/quickstart

Demonstrates how to fetch data from a Dappier RAG model using Python and cURL. This involves setting up authentication with an API key and sending a query to a specific endpoint. The response contains the AI-generated output based on the provided query and the RAG model's data.

```python
import requests

def fetch_dappier_data(query):
    api_key = "<YOUR_DAPPIER_API_KEY>" # Replace with your actual Dappier API key
    endpoint = "https://api.dappier.com/app/aimodel/am_01j06ytn18ejftedz6dyhz2b15"
    headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
    body = {"query": query}
    response = requests.post(endpoint, headers=headers, json=body)
    return response.json()

# Example usage
results = fetch_dappier_data("Plan me an itinerary for a 3 day trip to Puerto Rico")
print(results)
```

```bash
curl -L 'https://api.dappier.com/app/aimodel/am_01j06ytn18ejftedz6dyhz2b15' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer <YOUR_DAPPIER_API_KEY>' \
-d "{
    \"query\": \"Plan me an itinerary for a 3 day trip to Puerto Rico\"
}"
```

--------------------------------

### Install Dappier and LlamaIndex Packages

Source: https://docs.dappier.com/cookbook/recipes/llama-index-stock-analyzer

Installs the necessary Python packages for Dappier, LlamaIndex, and OpenAI integration. This command-line instruction ensures all dependencies are met before proceeding with the setup.

```bash
pip install llama-index llama-index-tools-dappier openai
```

--------------------------------

### Claude Desktop Configuration for Dappier MCP

Source: https://docs.dappier.com/integrations/claude-dappier-mcp-server-integration

This JSON configuration enables Claude for Desktop to automatically start the Dappier MCP Server upon application launch. It specifies the command to run and environment variables, including the Dappier API key.

```json
{
  "mcpServers": {
    "dappier": {
      "command": "uvx",
      "args": ["dappier-mcp"],
      "env": {
        "DAPPIER_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
```

--------------------------------

### Install Dependencies

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-travel-assistant

Installs the necessary Python packages for the project, including openai-agents, dappier, colorama, and nest-asyncio, which are essential for building the AI assistant.

```bash
!pip install openai-agents dappier colorama nest-asyncio
```

--------------------------------

### Install Dependencies

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-stock-analyser

Installs necessary Python packages for building the AI-powered stock analyzer, including OpenAI Agents SDK, Dappier, colorama, and nest-asyncio.

```bash
!pip install openai-agents dappier colorama nest-asyncio
```

--------------------------------

### Install Dappier Python SDK

Source: https://docs.dappier.com/integrations/python-sdk

Installs the Dappier Python SDK using pip. This is the first step to integrate Dappier's capabilities into your project.

```bash
pip install dappier
```

--------------------------------

### Install dappier-mcp Package

Source: https://docs.dappier.com/cookbook/recipes/dappier-mcp-claude-integration

Installs the dappier-mcp Python package using the UV package manager. This command fetches and installs the necessary library for Dappier MCP integration.

```bash
uv pip install dappier-mcp
```

--------------------------------

### Create AI Agent with Dappier Tools (Python)

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-travel-assistant

This example demonstrates how to create an AI agent using a Python framework. The agent is configured with a name, specific instructions for query analysis, and a list of tools, including Dappier's real-time search and AI recommendations functions. The agent's instructions guide it to choose between these tools based on the user's query context.

```Python
# Assuming Agent class and dappier_real_time_search, dappier_ai_recommendations are defined elsewhere
# from your_agent_framework import Agent
# from your_dappier_tools import dappier_real_time_search, dappier_ai_recommendations

agent = Agent(
    name="Dappier Assistant",
    instructions="""
    You analyze the user's query and determine whether to use real-time search or AI recommendations.
    If the query involves stocks, finance, or current events, use `dappier_real_time_search`.
    If the query is about recommendations (e.g., news, lifestyle, sports, pets), use `dappier_ai_recommendations`.
    You MUST provide `ai_model_id` or `data_model_id` as necessary.
    Format responses in structured Markdown.
    """,
    tools=[dappier_real_time_search, dappier_ai_recommendations],
)

```

--------------------------------

### Install OpenAI Agents SDK

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-travel-assistant

Installs the OpenAI Agents SDK using pip, a necessary dependency for building AI agents.

```bash
pip install openai-agents
```

--------------------------------

### Install MCP-Use and LangChain Dependencies

Source: https://docs.dappier.com/integrations/mcp-use-integration

Installs the necessary Python libraries for using the MCP-Use client and integrating with LangChain, such as OpenAI or Anthropic LLM providers.

```bash
pip install mcp-use langchain-openai  # or langchain-anthropic
```

--------------------------------

### Install OpenAI Agents SDK

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-news-letter

Installs the OpenAI Agents SDK using pip, a standard package installer for Python, to enable agent functionality.

```bash
pip install openai-agents
```

--------------------------------

### Install Required Packages

Source: https://docs.dappier.com/cookbook/recipes/open-ai-function-calling-stock-analyst

Installs the necessary Python packages, 'openai' and 'dappier', required for the stock market analysis functionality.

```bash
!pip install openai dappier
```

--------------------------------

### Install Project Dependencies

Source: https://docs.dappier.com/cookbook/recipes/google-adk-dynamic-travel-planner

Installs the necessary Python packages for the project, including the Google ADK and Dappier SDKs, using pip.

```bash
pip install google-adk dappier
```

--------------------------------

### Example User Prompts

Source: https://docs.dappier.com/cookbook/recipes/agent-ai-dynamic-travel-planner

Provides examples of prompts that can be used to gather necessary information from the user for the travel itinerary generation process.

```text
Destination Prompt:
  "Where would you like to go?"
  Example: "Paris"

Travel Dates Prompt:
  "When would you like to leave for [destination]?"
  Example: "Coming weekend"

Trip Duration Prompt:
  "How long will this trip be? (in number of days)"
  Example: 7
```

--------------------------------

### Install Libraries (Bash)

Source: https://docs.dappier.com/integrations/open-ai-function-calling-integration

Installs the necessary Python libraries, 'openai' and 'dappier', required for integrating OpenAI Function Calling with the Dappier SDK.

```bash
pip install openai dappier
```

--------------------------------

### Verify UV Installation

Source: https://docs.dappier.com/integrations/cursor-dappier-mcp-integration

Checks if the UV package manager has been successfully installed by displaying its version. This confirms the installation process.

```bash
uv --version
```

--------------------------------

### Install UV Package Manager (Windows)

Source: https://docs.dappier.com/integrations/cursor-dappier-mcp-integration

Installs the UV package manager using a PowerShell command for Windows systems. This is a prerequisite for using Dappier MCP.

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

--------------------------------

### Install UV Package Manager (macOS/Linux)

Source: https://docs.dappier.com/integrations/cursor-dappier-mcp-integration

Installs the UV package manager using a curl script for macOS and Linux systems. This is a prerequisite for using Dappier MCP.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

--------------------------------

### Initialize and Launch Dappier MCP Workflow (Python)

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-news-letter

This Python function initializes the Dappier MCP server with specified parameters, including environment variables for API keys. It then enables tracing for observability and executes the `run` function to start the smart content curator agent.

```Python
async def main():
    async with MCPServerStdio(
        cache_tools_list=True,
        params={
            "command": "uvx",
            "args": ["dappier-mcp"],
            "env": {"DAPPIER_API_KEY": os.environ["DAPPIER_API_KEY"]},
        },
    ) as server:
        with trace(workflow_name="Smart Content Curator with Dappier MCP"):
            await run(server)
```

--------------------------------

### Install Project Dependencies with UV

Source: https://docs.dappier.com/cookbook/recipes/agentstack-dynamic-travel-planner

Synchronizes and installs all project dependencies defined in pyproject.toml using the 'uv' package manager. 'uv lock' generates a lock file, and 'uv sync' installs the packages into the active virtual environment, ensuring a consistent setup.

```bash
uv lock
uv sync
```

--------------------------------

### Use Real-Time Search API with Go

Source: https://docs.dappier.com/integrations/go-sdk

Demonstrates how to initialize the Dappier client and perform a real-time search query using the dappier-go SDK. It shows how to handle API keys and process search results.

```go
package main

import (
	"fmt"
	"log"

	"github.com/DappierAI/dappier-go"
)

func main() {
	// Initialize Dappier client
	client, err := dappier.NewDappierApp("your-api-key")
	if err != nil {
		log.Fatalf("Failed to initialize Dappier client: %v", err)
	}

	// Make real-time search API request
	result, err := client.RealtimeSearchAPI("when is election in USA")
	if err != nil {
		log.Fatalf("Failed to get search result: %v", err)
	}

	// Print the search result
	fmt.Println("Search Result:", result.Response.Results)
}
```

--------------------------------

### Manually Run Dappier MCP Server

Source: https://docs.dappier.com/integrations/claude-dappier-mcp-server-integration

Command to manually start the Dappier MCP Server, useful for troubleshooting when the server is not automatically detected or responding.

```bash
uvx dappier-mcp
```

--------------------------------

### Get 9 and 10 News Recommendations

Source: https://docs.dappier.com/integrations/llama-index-integration

Fetches news recommendations from 9 and 10 News using a specified query and similarity threshold. This example demonstrates a basic usage of the Dappier tool for news retrieval.

```python
print(
    dappier_tool.get_nine_and_ten_news_recommendations(
        query="northern michigan local news", similarity_top_k=1
    )
)
```

--------------------------------

### Initialize Dappier Client

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-stock-analyser

Initializes the Dappier client using the provided API key, enabling access to Dappier's real-time data platform.

```python
dappier_client = Dappier(api_key=os.environ["DAPPIER_API_KEY"])
```

--------------------------------

### Initialize and Launch Workflow

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-travel-assistant

The `main` function initializes the Dappier MCP server with necessary parameters and environment variables. It then enables tracing for observability and calls the `run` function to execute the travel planning agent.

```Python
async def main():
    city, num_days, travel_date = get_user_input()

    async with MCPServerStdio(
        cache_tools_list=True,
        params={
            "command": "uvx",
            "args": ["dappier-mcp"],
            "env": {"DAPPIER_API_KEY": os.environ["DAPPIER_API_KEY"]},
        },
    ) as server:
        with trace(workflow_name="Dynamic Travel Planner with Dappier MCP"):
            await run(server, city, num_days, travel_date)
```

--------------------------------

### Install Required Packages

Source: https://docs.dappier.com/cookbook/recipes/open-ai-function-calling-sports-summarizer

Installs the necessary Python libraries, openai and dappier, for the project. This command is typically run in a terminal or notebook environment.

```bash
!pip install openai dappier
```

--------------------------------

### Install uv (Windows)

Source: https://docs.dappier.com/integrations/dappier-mcp-server-integration

Installs the uv package manager on Windows systems using PowerShell. This is a prerequisite for installing Dappier MCP Server.

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

--------------------------------

### Execute Workflow with uvx Check (Python)

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-news-letter

This Python script serves as the entry point for the application. It first checks if the 'uvx' binary is installed and available in the system path, raising an error if it's not found. Subsequently, it runs the main asynchronous workflow using `asyncio.run()`.

```Python
if __name__ == "__main__":
    if not shutil.which("uvx"):
        raise RuntimeError(
            "uvx is not installed. Please install it with `pip install uvx` or "
            "`curl -LsSf https://astral.sh/uv/install.sh | sh`."
        )

    asyncio.run(main())
```

--------------------------------

### Verify UV Installation

Source: https://docs.dappier.com/cookbook/recipes/dappier-mcp-claude-integration

Checks the installed version of the UV package manager to confirm a successful installation.

```bash
uv --version
```

--------------------------------

### Install Langchain Dappier and OpenAI Packages

Source: https://docs.dappier.com/cookbook/recipes/langchain-real-time-market-strategyzer

Installs the necessary Langchain Dappier integration package along with its dependencies and the OpenAI package. This ensures all required libraries are available for the project.

```Python
#!pip install langchain langchain-dappier langchain-openai
```

--------------------------------

### Run Dappier MCP Agent with LangChain

Source: https://docs.dappier.com/integrations/mcp-use-integration

Python script demonstrating how to set up and run an agent using MCP-Use and a Dappier MCP Server. It configures the server connection, initializes an LLM, and executes a query.

```python
import asyncio
import os
from dotenv import load_dotenv
from langchain_openai import ChatOpenAI
from mcp_use import MCPAgent, MCPClient

async def main():
    load_dotenv()

    config = {
        "mcpServers": {
            "dappier": {
                "command": "uvx",
                "args": ["dappier-mcp"],
                "env": {
                    "DAPPIER_API_KEY": os.getenv("DAPPIER_API_KEY")
                }
            }
        }
    }

    client = MCPClient.from_dict(config)
    llm = ChatOpenAI(model="gpt-4o")

    agent = MCPAgent(llm=llm, client=client, max_steps=30)

    result = await agent.run("Show me the latest news about Tesla.")
    print(result)

if __name__ == "__main__":
    asyncio.run(main())
```

--------------------------------

### Install uv (macOS/Linux)

Source: https://docs.dappier.com/integrations/dappier-mcp-server-integration

Installs the uv package manager using a curl script on macOS and Linux systems. This is a prerequisite for installing Dappier MCP Server.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

--------------------------------

### Install Dappier MCP Server (uv)

Source: https://docs.dappier.com/integrations/dappier-mcp-server-integration

Installs the Dappier MCP Server Python package using the uv package manager. This is an alternative installation method for the server.

```bash
uv pip install dappier-mcp
```

--------------------------------

### Install Dappier MCP Server (pip)

Source: https://docs.dappier.com/integrations/dappier-mcp-server-integration

Installs the Dappier MCP Server Python package using pip. This command fetches and installs the necessary libraries for the server.

```bash
pip install dappier-mcp
```

--------------------------------

### Install Dappier and LlamaIndex Packages

Source: https://docs.dappier.com/cookbook/recipes/llama-index-dyamic-travel-planner

Installs the necessary Python packages for LlamaIndex, the Dappier tool integration, and OpenAI. This command is essential for setting up the environment to run the travel planner.

```bash
pip install llama-index llama-index-tools-dappier openai
```

--------------------------------

### Verify UV Installation

Source: https://docs.dappier.com/cookbook/recipes/dappier-mcp-5ire-integration

Checks if the UV package manager has been successfully installed by displaying its version number. This command confirms that the installation process was completed correctly.

```shell
uv --version
```

--------------------------------

### Use AI Recommendations API with Go

Source: https://docs.dappier.com/integrations/go-sdk

Illustrates the usage of the AI Recommendations API with the dappier-go SDK, including basic and advanced parameter configurations. It covers fetching AI-driven recommendations for datamodels and displaying results.

```go
package main

import (
	"fmt"
	"log"

	"github.com/DappierAI/dappier-go"
)

func main() {
	// Initialize Dappier client
	client, err := dappier.NewDappierApp("your-api-key")
	if err != nil {
		log.Fatalf("Failed to initialize Dappier client: %v", err)
	}

	// Example usage of DappierRagAPI
	// Parameters:
	// - query (string): A natural language query or a URL. If a URL is passed,
	//                      the AI analyzes the page and performs a semantic search query.
	// - similarityTopK (int): Number of articles to return (default is 9).
	// - ref (string): The domain of the site to fetch recommendations from (e.g., techcrunch.com). optional
	// - numArticlesRef (int): Number of guaranteed articles from the specified domain (if ref is provided). optional
	// - datamodelID (string): The Data Model ID for the API request.

	recommendations, err := client.AIRecommendations("latest tech news", "dm_02hr75e8ate6adr15hjrf3ikol")
	if err != nil {
		log.Fatalf("Failed to get AI recommendations: %v", err)
	}

	// Print the results
	for _, result := range recommendations.Results {
		fmt.Printf("Title: %s\nAuthor: %s\nSite: %s\nURL: %s\n\n", result.Title, result.Author, result.Site, result.URL)
	}

	// With optional params
	recommendations, err = client.AIRecommendations(
		"latest tech news",
		"dm_02hr75e8ate6adr15hjrf3ikol",
		dappier.WithSimilarityTopK(5), // Set custom similarity_top_k
		dappier.WithRef("techcrunch.com"), // Set custom ref
		dappier.WithNumArticlesRef(5),
	)
	if err != nil {
		log.Fatalf("Failed to get AI recommendations: %v", err)
	}

	// Print the results
	for _, result := range recommendations.Results {
		fmt.Printf("Title: %s\nAuthor: %s\nSite: %s\nURL: %s\n\n", result.Title, result.Author, result.Site, result.URL)
	}
}
```

--------------------------------

### Initialize LLM and Dappier Tool

Source: https://docs.dappier.com/cookbook/recipes/langchain-real-time-market-strategyzer

Sets up the language model (e.g., GPT-4o) with streaming enabled and binds it to the Dappier Real-Time Search Tool. This prepares the LLM to use the tool for fetching real-time data.

```Python
llm = init_chat_model("gpt-4o", model_provider="openai", streaming=True)
dappier_tool = DappierRealTimeSearchTool()
llm_with_tools = llm.bind_tools([dappier_tool])
```

--------------------------------

### Install CAMEL Package

Source: https://docs.dappier.com/integrations/camel-integration

Installs the CAMEL package with all its dependencies using pip.

```bash
pip install "camel-ai[all]"
```

--------------------------------

### Initialize Dappier SDK

Source: https://docs.dappier.com/integrations/python-sdk

Initializes the Dappier SDK by setting the API key as an environment variable and creating an instance of the Dappier client. Ensure your API key is kept secure.

```python
import os
from dappier import Dappier

# Set your API key as an environment variable
os.environ["DAPPIER_API_KEY"] = "<YOUR_API_KEY>"

# Initialize the Dappier SDK
app = Dappier()
```

--------------------------------

### Setup Google ADK Agent with Dappier Tools (Python)

Source: https://docs.dappier.com/integrations/google-adk-integration

Demonstrates the initialization of a Google ADK Agent. It specifies the agent's name, model, description, instructions, and integrates a list of Dappier tools for fetching live data. This setup enables the agent to interact with various data sources via Dappier.

```python
from google.adk.agents import Agent

root_agent = Agent(
    name="dappier_tools_agent",
    model="gemini-2.0-flash",
    description="Agent to answer questions using Dappier tools.",
    instruction="You are a helpful assistant that uses Dappier tools to fetch live data.",
    tools=[
        real_time_web_search,
        stock_market_data_search,
        get_sports_news,
        get_lifestyle_news,
        get_iheartdogs_content,
        get_iheartcats_content,
        get_greenmonster_guides
    ]
)
```

--------------------------------

### Install uv Package Manager (Windows)

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-stock-analyst

Installs the `uv` package manager using a PowerShell script on Windows systems. `uv` is a fast Python package installer and is required to run the Dappier MCP server.

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

--------------------------------

### Install UV Package Manager (Windows)

Source: https://docs.dappier.com/cookbook/recipes/dappier-mcp-claude-integration

Installs the UV package manager on Windows systems using a PowerShell script. This command bypasses execution policy restrictions to download and run the installer.

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
```

--------------------------------

### Install uv Package Manager (macOS/Linux)

Source: https://docs.dappier.com/cookbook/recipes/open-ai-agent-mcp-stock-analyst

Installs the `uv` package manager using a curl script on macOS and Linux systems. `uv` is a fast Python package installer and is required to run the Dappier MCP server.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

--------------------------------

### Install Project Dependencies with UV

Source: https://docs.dappier.com/cookbook/recipes/agentstack-stock-market-researcher

Installs and locks project dependencies using the 'uv' package manager. 'uv lock' generates a lock file based on pyproject.toml, and 'uv sync' installs the specified dependencies into the active virtual environment.

```bash
uv lock
uv sync
```