refactoring

app.py

@@ -5,72 +5,14 @@ import requests
 import inspect
 import pandas as pd
 import time
+from langchain_agent import LangChainAgent
 
-# --- LangChain Imports 
-import constants
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain.agents import AgentExecutor, create_tool_calling_agent
-from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain_core.messages import SystemMessage
-
-# --- Custom Tools ---
-from wikipedia_tool import wikipedia_revision_by_year_keyword
-from count_max_bird_species_tool import count_max_bird_species_in_video
-from image_to_text_tool import image_to_text
-from internet_search_tool import internet_search
-from botanical_classification_tool import get_botanical_classification
-from excel_parser_tool import parse_excel
-from download_task_file import download_file_as_base64
 from utils import get_bytes, get_text_file_contents, get_base64
 
 # (Keep Constants as is) ok!
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class LangChainAgent:
-    def __init__(self):
-        llm = ChatGoogleGenerativeAI(
-            model=constants.MODEL,
-            api_key=constants.API_KEY, 
-            temperature=0.7)
-
-        tools = [
-            wikipedia_revision_by_year_keyword,
-            count_max_bird_species_in_video,
-            image_to_text,
-            internet_search,
-            get_botanical_classification,
-            parse_excel
-        ]
-
-        prompt = ChatPromptTemplate.from_messages([
-            SystemMessage(content=(constants.PROMPT_LIMITADOR_LLM)),
-            MessagesPlaceholder(variable_name="chat_history"),
-            ("human", "{input}"),
-            MessagesPlaceholder(variable_name="agent_scratchpad"),
-        ])
-
-        agent = create_tool_calling_agent(llm, tools, prompt=prompt)
-        self.executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
-
-    def __call__(self, question: str) -> str:
-        print(f"LangChain agent received: {question[:50]}...")
-        
-        #print("Waiting 60s before answering")
-        #time.sleep(10)  # Delay for 60 seconds
-        
-        result = self.executor.invoke({
-            "input": question,
-            "chat_history": []
-        })
-        output = result.get("output", "No answer returned.")
-        print(f"Agent response: {output}")
-        match = re.search(r"FINAL ANSWER:\s*(.*)", output)
-        if match:
-            return match.group(1).strip()
-        else:
-            return output
-
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,

langchain_agent.py

@@ -0,0 +1,55 @@
+import re
+import constants
+import time
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.agents import AgentExecutor, create_tool_calling_agent
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_core.messages import SystemMessage
+
+# --- Custom Tools ---
+from wikipedia_tool import wikipedia_revision_by_year_keyword
+from count_max_bird_species_tool import count_max_bird_species_in_video
+from image_to_text_tool import image_to_text
+from internet_search_tool import internet_search
+from botanical_classification_tool import get_botanical_classification
+from excel_parser_tool import parse_excel
+
+class LangChainAgent:
+    def __init__(self):
+        llm = ChatGoogleGenerativeAI(
+            model=constants.MODEL,
+            api_key=constants.API_KEY, 
+            temperature=0.7)
+
+        tools = [
+            wikipedia_revision_by_year_keyword,
+            count_max_bird_species_in_video,
+            image_to_text,
+            internet_search,
+            get_botanical_classification,
+            parse_excel
+        ]
+
+        prompt = ChatPromptTemplate.from_messages([
+            SystemMessage(content=constants.PROMPT_LIMITADOR_LLM),
+            MessagesPlaceholder(variable_name="chat_history"),
+            ("human", "{input}"),
+            MessagesPlaceholder(variable_name="agent_scratchpad"),
+        ])
+
+        agent = create_tool_calling_agent(llm, tools, prompt=prompt)
+        self.executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+
+    def __call__(self, question: str) -> str:
+        print(f"LangChain agent received: {question[:50]}...")
+        result = self.executor.invoke({
+            "input": question,
+            "chat_history": []
+        })
+        output = result.get("output", "No answer returned.")
+        print(f"Agent response: {output}")
+        match = re.search(r"FINAL ANSWER:\s*(.*)", output)
+        if match:
+            return match.group(1).strip()
+        else:
+            return output