Update agent.py

agent.py

@@ -34,7 +34,7 @@ def visit_webpage(url: str) -> str:
     """
     try:
         response = requests.get(url, timeout=5)
-        return response.text
+        return response.text[:5000]
     except Exception as e:
         return f"[ERROR fetching {url}]: {str(e)}"
 
@@ -66,15 +66,8 @@ def youtube_transcript(video_url: str) -> str:
 # 4. File Reading
 @tool
 def read_file(dir: str) -> str:
-    """Read the content of the provided file
-    Args:
-        dir: the filepath
-    """
     extension = dir.split['.'][-1]
-    if extension == 'xlsx':
-        dataframe = pd.read_excel(dir)
-        return dataframe.to_string()
-    elif extension == 'pdf':
+    if extension == 'pdf':
         reader = PdfReader(dir)
         contents = [p.extract_text() for p in reader.pages]
         return "\n".join(contents)
@@ -82,6 +75,31 @@ def read_file(dir: str) -> str:
         with open(dir) as f:
             return f.read()
 
+@tool
+from langchain_community.document_loaders import UnstructuredExcelLoader
+# from langchain_core.documents import Document
+def excel_read(dir: str) -> str:
+    """Read the content of the excel file
+    Args:
+        dir: the filepath
+    """
+    loader = UnstructuredExcelLoader(dir, mode="elements")
+    docs = loader.load()
+    contents = [doc.page_content for doc in docs]
+    return "\n".join(contents)
+
+@tool
+from langchain_community.document_loaders import AssemblyAIAudioTranscriptLoader
+def mp3_listen(dir: str) -> str:
+    """Listen to the provided mp3 file
+    Args:
+        dir: the filepath
+    """
+    loader = AssemblyAIAudioTranscriptLoader(file_path=dir)
+    docs = loader.load()
+    contents = [doc.page_content for doc in docs]
+    return "\n".join(contents)
+    
 # 5. Image Open
 @tool
 def image_caption(dir: str) -> str:
@@ -95,6 +113,46 @@ def image_caption(dir: str) -> str:
 
 # 2. Coding
 from langchain_experimental.tools import PythonREPLTool
+python_tool = PythonREPLTool()
+
+@tool
+def multiply(a: float, b: float) -> float:
+    """Multiply two numbers.
+    Args:
+        a: first float
+        b: second float
+    """
+    return a * b
+
+@tool
+def add(a: float, b: float) -> float:
+    """Add two numbers.
+    Args:
+        a: first float
+        b: second float
+    """
+    return a + b
+
+@tool
+def subtract(a: float, b: float) -> float:
+    """Subtract two numbers.
+    Args:
+        a: first float
+        b: second float
+    """
+    return a - b
+
+@tool
+def divide(a: float, b: float) -> float:
+    """Divide two numbers.
+    Args:
+        a: first float
+        b: second float
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
 # 3. Multi-Modality
 
 # ("human", f"Question: {question}\nReport to validate: {final_answer}")
@@ -123,24 +181,16 @@ class BasicAgent:
                 - wiki_search: wiki search the content of the query by passing the query as input if the question asks for wiki search it
                 - youtube_transcript: fetch the transcript of the Youtube video by passing the video url as input if the question asks for watching a Youtube video
                 - read_file: read the content of the attached file by passing the file directory as input
+                - excel_read: read the content of the attached excel file by passing the file directory as input
+                - mp3_listen: listen to the content of the attached mp3 file by passing the file directory as input
                 - image_caption: understand the visual content of the attached image by passing the image directory as input
-                - PythonREPLTool: run the python code 
-                
-                HERE are some examples illustrating how and what tools to call.
-                ---------------
-                TASK: "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?"
-                ACTION: Find the Youtube url in the provided TASK info, that is 'https://www.youtube.com/watch?v=L1vXCYZAYYM'. Call youtube_transcript tool to extract video transcript with ht extracted Youtube url. Use LLM to understand the retrived transcript.
-
-                TASK: How many Grammy Awards that Taylor Swift has won.
-                ACTION: Call the web_search tools with the query: 'how many Grammy Awards that Taylor Swift has won.' to extract the answer.
-
-                TASK: How much the total expense in this spreadsheet?
-                ACTION: Call the read_file tool to extract the content of the provided spreadfile. Then, use LLM to extract the amount of every expense and sum them up.
-
-                TASK: How many All England Title that Lee Chong Wei won?
-                ACTION: Call wiki_search with the query: "Lee Chong Wei". Extract the relevant row of All England Title and count how many rows is there.
+                - python_tool: run the python code 
+                - multiply: multiply two numbers, A and B
+                - add: add two numbers, A and B
+                - subtract: Subtract A by B with passing A as the first argument
+                - divide: Divide A by B with passing A as the first argument
         """
-        self.tools = [web_search, visit_webpage, wiki_search, youtube_transcript, read_file, image_caption, PythonREPLTool()]
+        self.tools = [web_search, visit_webpage, wiki_search, youtube_transcript, read_file, excel_read, mp3_listen, image_caption, python_tool, multiply, add, subtract, divide]
         self.prompt = ChatPromptTemplate.from_messages([
             ("system", self.sys_prompt),
             ("human", "{input}")
@@ -152,14 +202,14 @@ class BasicAgent:
             verbose=True,
             system_prompt=self.prompt
         )
-        print("BasicAgent initialized.")
+        prfloat("BasicAgent initialized.")
     
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        prfloat(f"Agent received question (first 50 chars): {question[:50]}...")
         # response = self.agent_exe.invoke({"input": f"Question: {question}"})
         # fixed_answer = response['message'][-1].content
         time.sleep(15)
         fixed_answer = self.agent.run(question)
         # fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
+        prfloat(f"Agent returning fixed answer: {fixed_answer}")
         return fixed_answer