Update app.py

app.py

@@ -55,6 +55,9 @@ st.set_page_config(layout="wide")
 import logging
 import asyncio
 import re 
+from langchain_community.tools import TavilySearchResults
+
+
 # Set up logging to suppress Streamlit warnings about experimental functions
 logging.getLogger('streamlit').setLevel(logging.ERROR)
 INITIAL_MESSAGE_LIMIT = 100
@@ -1025,39 +1028,51 @@ def search_knowledge_base(query):
     return retrieved_docs
 
 def google_search(query):
+    """
+    Performs a Google search using the SerpApi service and retrieves search result snippets.
+    This function uses the SerpApi client to perform a Google search based on the provided query.
+    It extracts and returns the snippets from the organic search results.
+    Args:
+        query (str): The search query to be used for the Google search.
+    Returns:
+        list: A list of snippets from the organic search results. If an error occurs, returns a list with an error message.
+    Raises:
+        requests.exceptions.HTTPError: If an HTTP error occurs during the search, it is logged and an error message is returned.
+        Exception: For any other general errors, they are logged and an error message is returned.
+    """
     try:
-        # Initialize the search client and parameters
-        search_client = serpapi.Client(api_key=serper_api_key)
-        search_params = {
-            "engine": "google",
-            "q": query,
-            "sort": "date",  # Sort results by date for freshness
-            "hl": "en",  # Language: English
-            "gl": "us",  # Geolocation: United States
+        # Set up connection to google.serper.dev API
+        conn = http.client.HTTPSConnection("google.serper.dev")
+        payload = json.dumps({"q": query})
+        headers = {
+            "X-API-KEY": "07b4113c2730711b568623b13f7c88078bab9c78",
+            "Content-Type": "application/json",
         }
 
-        # Perform the search
-        results = search_client.search(search_params)
-        organic_results = results.get("organic_results", [])
-        formatted_results = []
+        # Send POST request to the API
+        conn.request("POST", "/search", payload, headers)
 
-        for result in organic_results:
-            link = result.get("link", "")
-            snippet = result.get("snippet", "")
+        # Get response and decode the data
+        res = conn.getresponse()
+        data = res.read()
+        results = json.loads(data.decode("utf-8"))
 
-            # Ensure proper Markdown formatting with only "Source" as the clickable text
-            if link.startswith("http"):
-                formatted_results.append(f"{snippet} - [Source]({link})")
-
-        if formatted_results:
-            return formatted_results
-        return ["No valid links found"]
+        # Extract snippets from organic search results
+        snippets = [result["snippet"] for result in results.get("organic", [])]
 
+        # Return the list of snippets
+        return snippets
+    except http.client.HTTPException as http_err:
+        # Log HTTP errors and return a specific error message
+        print(f"HTTP error occurred: {http_err}")
+        return ["HTTP error occurred during Google search"]
     except Exception as e:
-        logger.error(f"Error in Google search: {e}")
+        # Log any other general errors and return a generic error message
+        print(f"General Error: {e}")
         return ["Error occurred during Google search"]
 
 
+
 def rag_response(query):
     """
     Handle queries by searching both static and dynamically uploaded knowledge bases.
@@ -1093,7 +1108,6 @@ def rag_response(query):
         return "An error occurred during the RAG response generation process."
 
 
-# Define tools
 @tool
 def knowledge_base_tool(query: str):
     """Query the knowledge base and retrieve a response."""
@@ -1104,7 +1118,24 @@ def google_search_tool(query: str):
     """Perform a Google search using the SERPER API."""
     return google_search(query)
 
-tools = [knowledge_base_tool, google_search_tool]
+tavily_tool = TavilySearchResults(
+    max_results=5,
+    search_depth="advanced",
+    include_answer=True,
+    include_raw_content=True,
+    include_images=True,
+    # include_domains=[...],
+    # exclude_domains=[...],
+    # name="...",            # overwrite default tool name
+    # description="...",     # overwrite default tool description
+    # args_schema=...,       # overwrite default args_schema: BaseModel
+)
+# Compile all tool functions into a list
+tools = [
+    knowledge_base_tool,  # Tool for querying the knowledge base and retrieving responses
+    tavily_tool,
+    # google_search_tool,  # Tool for performing a Google search and retrieving search result snippets
+]
 
 prompt_message = f"""
 ** You are a Professional copywriter tasked with creating non-flowery fluid, interconnected marketing content that integrates Trust Builders into various formats for  food for the hungry. Your content should be compelling, factual, well-structured, concise, and based on the knowledgebase. Write in an active voice using the first-person perspective ("we"), and avoid the third-person perspective. Creatively interconnect trust-building elements to enhance flow and impact. Avoid using terms like Stability, Development, Competence, Relationship, Benefit, Vision, trust, beacon, beacon of hope, and realm, except where specified.