Merge branch 'master' into ddg-search

scripts/commands.py

@@ -10,6 +10,9 @@ from file_operations import read_file, write_to_file, append_to_file, delete_fil
 from execute_code import execute_python_file
 from json_parser import fix_and_parse_json
 from duckduckgo_search import ddg
+from googleapiclient.discovery import build
+from googleapiclient.errors import HttpError
+
 cfg = Config()
 
 
@@ -44,7 +47,13 @@ def get_command(response):
 def execute_command(command_name, arguments):
     try:
         if command_name == "google":
-            return google_search(arguments["input"])
+            
+            # Check if the Google API key is set and use the official search method
+            # If the API key is not set or has only whitespaces, use the unofficial search method
+            if cfg.google_api_key and (cfg.google_api_key.strip() if cfg.google_api_key else None):
+                return google_official_search(arguments["input"])
+            else:
+                return google_search(arguments["input"])
         elif command_name == "memory_add":
             return commit_memory(arguments["string"])
         elif command_name == "memory_del":
@@ -63,7 +72,7 @@ def execute_command(command_name, arguments):
         elif command_name == "delete_agent":
             return delete_agent(arguments["key"])
         elif command_name == "get_text_summary":
-            return get_text_summary(arguments["url"])
+            return get_text_summary(arguments["url"], arguments["question"])
         elif command_name == "get_hyperlinks":
             return get_hyperlinks(arguments["url"])
         elif command_name == "read_file":
@@ -75,7 +84,7 @@ def execute_command(command_name, arguments):
         elif command_name == "delete_file":
             return delete_file(arguments["file"])
         elif command_name == "browse_website":
-            return browse_website(arguments["url"])
+            return browse_website(arguments["url"], arguments["question"])
         # TODO: Change these to take in a file rather than pasted code, if
         # non-file is given, return instructions "Input should be a python
         # filepath, write your code to file and try again"
@@ -108,9 +117,43 @@ def google_search(query, num_results=8):
 
     return json.dumps(search_results, ensure_ascii=False, indent=4)
 
+def google_official_search(query, num_results=8):
+    from googleapiclient.discovery import build
+    from googleapiclient.errors import HttpError
+    import json
 
-def browse_website(url):
-    summary = get_text_summary(url)
+    try:
+        # Get the Google API key and Custom Search Engine ID from the config file
+        api_key = cfg.google_api_key
+        custom_search_engine_id = cfg.custom_search_engine_id
+
+        # Initialize the Custom Search API service
+        service = build("customsearch", "v1", developerKey=api_key)
+        
+        # Send the search query and retrieve the results
+        result = service.cse().list(q=query, cx=custom_search_engine_id, num=num_results).execute()
+
+        # Extract the search result items from the response
+        search_results = result.get("items", [])
+        
+        # Create a list of only the URLs from the search results
+        search_results_links = [item["link"] for item in search_results]
+
+    except HttpError as e:
+        # Handle errors in the API call
+        error_details = json.loads(e.content.decode())
+        
+        # Check if the error is related to an invalid or missing API key
+        if error_details.get("error", {}).get("code") == 403 and "invalid API key" in error_details.get("error", {}).get("message", ""):
+            return "Error: The provided Google API key is invalid or missing."
+        else:
+            return f"Error: {e}"
+
+    # Return the list of search result URLs
+    return search_results_links
+
+def browse_website(url, question):
+    summary = get_text_summary(url, question)
     links = get_hyperlinks(url)
 
     # Limit links to 5
@@ -122,9 +165,9 @@ def browse_website(url):
     return result
 
 
-def get_text_summary(url):
+def get_text_summary(url, question):
     text = browse.scrape_text(url)
-    summary = browse.summarize_text(text)
+    summary = browse.summarize_text(text, question)
     return """ "Result" : """ + summary