Add search api engine integration class

Add documentation and example action invoke

Add steps to perform searches on various engines using SearchApi

Author: raju249

dev/Readme.md

@@ -40,6 +40,7 @@
    ```bash
    export AZURE_OPENAI_API_KEY="<your key>" # required AZURE OPENAI USAGE
    export SERPER_API_KEY="<your key>" # required for Google Serper API
+   export SEARCHAPI_API_KEY="<your key>" # required to perform web searches on any search engines.
    python usecases/ProfAgent.py
    ```
 

docs/components/action/tools.md

@@ -25,7 +25,35 @@ admin = Admin(
 )
 ```
 
-### 2. Serper Search Tool
+### 2. SearchApi Search
+
+[SearchApi.io](https://searchapi.io/) provides a real-time API to access search results from Google (default), Google Scholar, Bing, Baidu, and other search engines. Any existing or upcoming SERP engine that returns `organic_results` is supported. The default web search engine is `google`, but it can be changed to `bing`, `baidu`, `google_news`, `bing_news`, `google_scholar`, `google_patents`, and others.
+
+#### Setup API
+
+```python
+import os
+
+os.environ['SEARCHAPI_API_KEY'] = "<replace-with-your-api-key>"
+os.environ['SEARCHAPI_ENGINE'] = "bing" # defaults to google.
+```
+
+Get your API key by creating an account or logging into your account on [SearchApi](https://searchapi.io/).
+
+```python
+from openagi.actions.tools.searchapi_search import SearchApiSearch
+from openagi.agent import Admin
+from openagi.llms.openai import OpenAIModel
+from openagi.planner.task_decomposer import TaskPlanner
+
+admin = Admin(
+    llm = llm,
+    actions=[SearchApiSearch],
+    planner=TaskPlanner(),
+)
+```
+
+### 3. Serper Search Tool
 
 Serper is a low-cost Google Search API that can be used to add answer box, knowledge graph, and organic results data from Google Search. This tool is mainly helps user to query the Google results with less throughput and latency.&#x20;
 
@@ -52,7 +80,7 @@ admin = Admin(
 )
 ```
 
-### 3.  Google Serp API Search
+### 4.  Google Serp API Search
 
 Serp API is yet another solution to integrate search data. SERP stands for _Search Engine Results Page_. It refers to the page displayed by a search engine in response to a user's query.
 
@@ -79,7 +107,7 @@ admin = Admin(
 )
 ```
 
-### 4. Github Search Tool
+### 5. Github Search Tool
 
 The Github SearchTool is used for retrieving information from Github repositories using natural language queries. This tool provides functionality for querying Github repositories for various information, such as code changes, commits, active pull requests, issues, etc., using natural language input. It is designed to be used as part of a larger AI-driven agent system.
 
@@ -106,7 +134,7 @@ admin = Admin(
 )
 ```
 
-### 5. YouTube Search Tool
+### 6. YouTube Search Tool
 
 The YouTube Search tool allows users to search for videos on YouTube using natural language queries. This tool retrieves relevant video content based on user-defined search parameters, making it easier to find specific videos or topics of interest.
 
@@ -132,7 +160,7 @@ admin = Admin(
 )
 ```
 
-### 6. Tavily QA Search Tool
+### 7. Tavily QA Search Tool
 
 The Tavily QA Search tool is designed to provide answers to user queries by fetching data from various online sources. This tool enhances the capability of the agent to retrieve precise information and answer questions effectively.
 
@@ -166,7 +194,7 @@ admin = Admin(
 )
 ```
 
-### 7. Exa Search Tool
+### 8. Exa Search Tool
 
 The Exa Search tool allows users to query the Exa API to retrieve relevant responses based on user-defined questions. This tool is particularly useful for extracting information and insights from various data sources using natural language queries.
 
@@ -202,7 +230,7 @@ admin = Admin(
 )
 ```
 
-### 8. Unstructured PDF Loader Tool
+### 9. Unstructured PDF Loader Tool
 
 The Unstructured PDF Loader tool is designed to extract content, including metadata, from PDF files. It utilizes the Unstructured library to partition the PDF and chunk the content based on titles. This tool is useful for processing large volumes of PDF documents and making their contents accessible for further analysis.
 

docs/use-cases/jobsearch-agent.md

@@ -6,7 +6,7 @@ It utilize various tools for internet search and document comparison to fulfill
 
 First, we need to import the necessary modules. Each module serves a specific purpose in our script. We utilize various tools for internet search and document comparison to fulfill the agent's task. Here’s what each import does:
 
-* `GoogleSerpAPISearch` and `DuckDuckGoSearch` are tools for performing web searches.
+* `SearchApiSearch`, `GoogleSerpAPISearch` and `DuckDuckGoSearch` are tools for performing web searches.
 * `Admin` manages the overall execution of tasks.
 * `AzureChatOpenAIModel` is used to configure the large language model from Azure.
 * `Memory` is for maintaining context during the agent's operations.

src/openagi/actions/tools/searchapi_search.py

@@ -0,0 +1,44 @@
+import logging
+import os
+import requests
+from urllib.parse import urlencode
+from typing import Any
+
+from pydantic import Field
+
+from openagi.actions.base import BaseAction
+from openagi.exception import OpenAGIException
+
+
+class SearchApiSearch(BaseAction):
+    """SearchApi.io provides a real-time API to access search results from Google (default), Google Scholar, Bing, Baidu, and other search engines."""
+    query: str = Field(
+        ..., description="User query of type string used to fetch web search results from a search engine."
+    )
+
+    def execute(self):
+        base_url = "https://www.searchapi.io/api/v1/search"
+        searchapi_api_key = os.environ["SEARCHAPI_API_KEY"]
+        engine = os.environ.get("SEARCHAPI_ENGINE") or "google"
+        search_dict = {
+            "q": self.query,
+            "engine": engine,
+            "api_key": searchapi_api_key
+        }
+        logging.debug(f"{search_dict=}")
+        url = f"{base_url}?{urlencode(search_dict)}"
+        response = requests.request("GET", url)
+        json_response = response.json()
+
+        if not json_response:
+            raise OpenAGIException(f"Unable to generate result for the query {self.query}")
+
+        logging.debug(json_response)
+
+        organic_results = json_response.get("organic_results", [])
+
+        meta_data = ""
+        for organic_result in organic_results:
+            meta_data += f"CONTEXT: {organic_result['title']} \ {organic_result['snippet']}"
+            meta_data += f"Reference URL: {organic_result['link']}\n"
+        return meta_data

src/openagi/utils/tool_list.py

@@ -2,6 +2,7 @@
 from openagi.actions.tools import (
     ddg_search,
     document_loader,
+    searchapi_search,
     serp_search,
     serper_search,
     webloader,
@@ -14,6 +15,7 @@
 modules = [
     document_loader,
     ddg_search,
+    searchapi_search,
     serp_search,
     serper_search,
     webloader,