feat: add-rainforest-product-integration

integrations/rainforest/README.md

@@ -0,0 +1,57 @@
+# Rainforest API Integration
+
+## Overview
+Rainforest API integration enhances the capabilities of an AI agent by leveraging Rainforest Product Data API. This integration allows the AI agent to perform advanced searches, providing users with relevant data based on their search queries.  
+
+
+## Rainforest API
+**Rainforest** is a real-time, high-scale API to request Amazon product data, customer reviews, seller offers, search results, category listing results and bestselling products.
+
+## Usage
+To use the Rainforest API integration, create an instance of the `SearchAmazonRequest` model with a specific query and send it to the agent. The agent will utilize the Rainforest Product Search API to perform the search and respond with formatted results.
+
+# Getting Rainforest API Key
+
+To access the Rainforest API, you need an API key. Follow these steps to obtain your API key:
+
+1. Visit the Rainforest website at [https://www.rainforestapi.com/](https://www.rainforestapi.com/).
+2. Sign up or log in to your account.
+3. Navigate to the API section.
+4. Create a new API key.
+5. Copy the generated API key.
+6. Replace the placeholder in the script with your actual API key.
+
+Ensure that you keep your API key secure and do not share it publicly. It is a sensitive credential that grants access to Rainforest services.
+
+# Agent Secrets on Agentverse
+
+1. Go to the Agentverse platform.
+2. Navigate to the Agent Secrets section.
+3. Create an agent and copy the code in it
+4. Add a new secret with the key `API_KEY` and the value as your API KEY.
+
+# Steps to Enroll an Agent as a Service on Agentverse
+
+You can integrate into DeltaV your Agents created on your local computer, IoT devices, in the VMs, or agents created on Agentverse. The steps are the same.
+
+Once your agents are run, the agent protocol manifests are uploaded to the Almanac contract in the form of protocol digests. After uploading the manifests, we take the agent addresses and enroll the agents as a service under the "Services" tab in Agentverse.
+
+## Agent Validation on Agentverse Explorer
+*Note: You can validate the procedure by searching for your agent's address on Agent Explorer, checking if the protocols have been uploaded successfully. If not, you need to wait for some time (1-2 minutes) until the protocols are uploaded successfully.*
+
+## Create a Service Group
+
+1. Start by creating a new service group on Agentverse.
+2. Set up the service group as PRIVATE (you will only be able to see your own agents).
+   - If you set up your service group as Public, anyone will be able to see your agents.
+
+**Service group has been created.**
+
+## Create a Service
+
+1. To register the agents as a service, input a concise title and description for the agent service.
+2. Choose the service group for the agent service that you've created previously.
+3. Fill in the agent address in the Agent field.
+4. Set the task type to Task.
+
+Now, your agents are enrolled as a service in Agentverse. You can manage and monitor them under the "Services" tab. Ensure that you follow the agent validation steps on Agent Explorer to confirm successful enrollment.

integrations/rainforest/agent.py

@@ -0,0 +1,103 @@
+# Here we demonstrate how we can create a DeltaV compatible agent responsible for getting Amazon Product from Rainforest
+# API. After running this agent, it can be registered to DeltaV on Agentverse's Services tab. For registration,
+# you will have to use the agent's address.
+#
+# third party modules used in this example
+import requests
+from pydantic import Field
+from ai_engine import UAgentResponse, UAgentResponseType
+
+
+# Define the updated Rainforest API protocol
+class SearchAmazonRequest(Model):
+    search_term: str = Field(description="Describes the text field to query for a product to search in marketplace")
+
+
+# Define the Rainforest API details
+rainforest_base_url = "https://api.rainforestapi.com/request"
+
+rainforest_protocol = Protocol("Rainforst Protocol")
+
+
+# Function to extract top 5 products from the search results
+def extract_top_5_products(data) -> list or None:
+    """
+    Extracts all the Search Results from the API Response
+
+    Returns:
+        List of top 5 Products.
+    """
+    products = data.get("search_results", [])  # Extract top 5 results
+    enriched_products = []
+    index = 1
+    for product_info in products:
+        if len(enriched_products) <= 5:
+            if product_info.get('price'):
+                enriched_product = (
+                    f"{index}. Title: {product_info.get('title')}\n"
+                    f"   ASIN: {product_info.get('asin')}\n"
+                    f"   Link: <a href={product_info.get('link')}>Product Link</a>\n"
+                    f"   Rating: {product_info.get('rating')}\n"
+                    f"   Price: {product_info.get('price').get('raw')}\n"
+                )
+                enriched_products.append(enriched_product)
+                index += 1
+            else:
+                continue
+        else:
+            break
+    return '\n\n'.join(enriched_products)
+
+
+# Function to perform a search on Amazon using the Rainforest API
+def search_amazon_products(search_term):
+    """
+    Retrieves data from the Rainforest API for Amazon Products.
+    Args:
+        search_term: search term for product.
+
+    Returns:
+        list or None: A list of Amazon product data if successful, or None if the request fails.
+    """
+    params = {
+        'api_key': API_KEY,
+        'type': 'search',
+        'amazon_domain': 'amazon.co.uk',
+        'search_term': search_term + ' above 100',
+        'output': 'json'
+    }
+
+    response = requests.get(rainforest_base_url, params=params)
+
+    if response.status_code == 200:
+        return response.json()
+    else:
+        return None
+
+@rainforest_protocol.on_query(model=SearchAmazonRequest, replies=UAgentResponse)
+async def search_amazon_q(ctx: Context, sender: str, msg: SearchAmazonRequest):
+    ctx.logger.info(f"Received message from {sender} to search Amazon for '{msg.search_term}'")
+    try:
+        data = search_amazon_products(msg.search_term)
+
+        if data is not None:
+            top_5_products = extract_top_5_products(data)
+            await ctx.send(sender, UAgentResponse(
+                message=top_5_products,
+                type=UAgentResponseType.FINAL,
+            ))
+        else:
+            await ctx.send(sender, UAgentResponse(
+                message="Please try some other query, could not find any result for the given search query.",
+                type=UAgentResponseType.FINAL,
+            ))
+    except Exception as exc:
+        ctx.logger.error(exc)
+        await ctx.send(sender, UAgentResponse(
+            message="Facing some trouble while finding the product from amazon, please try again after some time",
+            type=UAgentResponseType.FINAL,
+        ))
+
+
+# Include the updated Rainforest API protocol in the agent
+agent.include(rainforest_protocol)

integrations/rainforest/project.json

@@ -0,0 +1,6 @@
+{
+    "title": "Rainforest Product Finder",
+    "description": "Rainforest API integration enhances the capabilities of an AI agent by leveraging Rainforest Product Data API. ",
+    "categories": ["Product Finder"],
+    "deltav": true
+}