feat: :sparkles: add googleapi

qa_graph.py

@@ -34,13 +34,14 @@ def get_file_type(file_path: str) -> str:
 
 def ask_question(question: str, thread_id: str = "default") -> str:
     """Ask the agent a question."""
-    config = {"configurable": {"thread_id": thread_id}}
+    config = {"configurable": {"thread_id": thread_id}, "recursion_limit": 100}
     
     try:
         response = general_agent.invoke(
             {"messages": [{"role": "user", "content": question}]},
             config=config
         )
+        print(response["messages"])
         return response["messages"][-1].content
     except Exception as e:
         return f"Error: {str(e)}"
@@ -87,6 +88,12 @@ def ask_question_youtube(question: Question) -> str:
     return result["messages"][-1].content
 
 test = [
+    {
+    "task_id": "8e867cd7-cff9-4e6c-867a-ff5ddc2550be",
+    "question": "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.",
+    "Level": "1",
+    "file_name": ""
+  },
 #     {
 #     "task_id": "cca530fc-4052-43b2-b130-b30968d8aa44",
 #     "question": "Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.",
@@ -117,18 +124,18 @@ test = [
 #     "Level": "1",
 #     "file_name": ""
 #   },
-                    {
-    "task_id": "9d191bce-651d-4746-be2d-7ef8ecadb9c2",
-    "question": "Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\"",
-    "Level": "1",
-    "file_name": ""
-  },
-                      {
-    "task_id": "a1e91b78-d3d8-4675-bb8d-62741b4b68a6",
-    "question": "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?",
-    "Level": "1",
-    "file_name": ""
-  },        
+#                     {
+#     "task_id": "9d191bce-651d-4746-be2d-7ef8ecadb9c2",
+#     "question": "Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\"",
+#     "Level": "1",
+#     "file_name": ""
+#   },
+#                       {
+#     "task_id": "a1e91b78-d3d8-4675-bb8d-62741b4b68a6",
+#     "question": "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?",
+#     "Level": "1",
+#     "file_name": ""
+#   },        
             ]
 
 questions = [Question(**item) for item in test]
@@ -232,6 +239,7 @@ if __name__ == "__main__":
             "decision": "",
             "answer": ""
         })
+        print(result)
         
         print(f"Answer: {result['answer']}")
         print("-" * 50)

requirements.txt

@@ -11,3 +11,5 @@ arxiv
 openpyxl
 ultralytics
 youtube-transcript-api
+google-api-python-client
+langchain-google-community

tools.py

@@ -5,6 +5,10 @@ from langchain_community.tools import (
     WikipediaQueryRun,
     ArxivQueryRun
 )
+from langchain_google_community.search import (
+    GoogleSearchAPIWrapper,
+    GoogleSearchRun
+)
 from langchain_community.utilities import WikipediaAPIWrapper, ArxivAPIWrapper
 from langchain_openai import ChatOpenAI
 
@@ -25,6 +29,8 @@ import re
 from dotenv import load_dotenv
 load_dotenv()
 HF_TOKEN = os.getenv("HF_TOKEN")
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+GOOGLE_CSE_ID = os.getenv("GOOGLE_CSE_ID")
 client = InferenceClient(
     provider="hf-inference",
     api_key=HF_TOKEN,
@@ -323,11 +329,22 @@ def analyze_video_content(video_url: str, question: str = "", max_vision_frames:
         
     except Exception as e:
         return f"Error analyzing video content: {str(e)}"
+@tool
+def google_search():
+    """Google search tool"""
+    api_wrapper = GoogleSearchAPIWrapper(
+    google_api_key=GOOGLE_API_KEY,
+    google_cse_id=GOOGLE_CSE_ID,
+    k=10,  # Number of results
+    siterestrict=False  # Site restrictions
+)
+    google_search = GoogleSearchRun(api_wrapper=api_wrapper)
+    return google_search
 def general_tools():    
     tools = [
-        DuckDuckGoSearchRun(),
         WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper()),
         ArxivQueryRun(api_wrapper=ArxivAPIWrapper()),
+        google_search,
         analyze_image,
         read_python_file,
         transcribe_audio,