Update app.py

app.py

@@ -160,7 +160,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     travily_api_search_tool = get_travily_api_search_tool(tavily_api_key)
     #tools = [travily_api_search_tool, repl_tool, file_saver_tool,audio_transcriber_tool,wikipedia_search_tool,wikipedia_full_content_tool]
-    tools = [ repl_tool, file_saver_tool,audio_transcriber_tool,serpapi_Google_Search_tool]
+    tools = [ repl_tool, file_saver_tool,audio_transcriber_tool,travily_api_search_tool]
 
     # Pull a predefined prompt from LangChain Hub
     # "hwchase17/react-chat" is a prompt template designed for ReAct-style conversational agents.
@@ -193,8 +193,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 
     IMPORTANT: When processing audio files (like .mp3) that have been saved using 'file_saver', the 'audio_transcriber_tool' MUST be used with the 'local_filename' of the saved audio file as its Action Input. Do NOT pass URLs or remote paths directly to 'audio_transcriber_tool'.
-
-    If you have sufficient information and can provide a CONCISE response, or if no tool is needed, you MUST use this precise format:
+    For any incoming image files (e.g., .jpg, .png), it's crucial to download and save them locally using the 'file_saver' tool. Once the image is saved, you should then analyze its content and decide whether to utilize other available tools or your LLM to formulate a response.    If you have sufficient information and can provide a CONCISE response, or if no tool is needed, you MUST use this precise format:
+    
     if you can use a LLM to answer the question, think step-by-step and then answer the question.
     Example: given a chess board image and asked to predict the next best move, if Multi-modal LLM is available, you can use it to answer the question.
 
@@ -223,7 +223,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     Example 3:
     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.
-    Thought: The user is asking for specific information from Wikipedia, likely requiring a list or discography. The `serpapi_Google_Search_tool` is best for this to get the detailed section. After getting the content, I will need to parse it using `python_repl` to count the albums within the specified years.
+    Thought: The user is asking for specific information from Wikipedia, likely requiring a list or discography. The `travily_api_search_tool` is best for this to get the detailed section. After getting the content, I will need to parse it using `python_repl` to count the albums within the specified years.
     Action: serpapi_Google Search
     Action Input: Mercedes Sosa section: Discography
     Observation: [Discography text content]
@@ -254,9 +254,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
     )
     #'''
-    #summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history")
-    summary_memory = ConversationSummaryBufferMemory(llm=llm_client, memory_key="chat_history",
-                max_token_limit=4000) # Adjust this value based on your observations and model's context window
+    summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history")
+    '''summary_memory = ConversationSummaryBufferMemory(llm=llm_client, memory_key="chat_history",
+                max_token_limit=4000) # Adjust this value based on your observations and model's context window'''
 
 
     # Initialize gemini model with streaming enabled