fix proxy and agent output

.env.template

@@ -0,0 +1,6 @@
+# OpenAI API Configuration
+OPENAI_API_KEY=your_openai_api_key_here
+OPENAI_API_BASE=https://api.openai.com/v1
+OPENAI_PROXY=http://127.0.0.1:7899
+PROXY_URL=http://127.0.0.1:7899
+# Add other configuration variables below

agent.py

@@ -19,19 +19,22 @@ tools = [
             read_file
         ]
 
-llm_with_tools = init_chat_model(
+llm = init_chat_model(
     model="gpt-4o",
     model_provider="openai",
     max_retries=2,
     openai_api_base=os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"),
     openai_api_key=os.getenv("OPENAI_API_KEY"),
     openai_proxy=os.getenv("OPENAI_PROXY"),
-).bind_tools(tools)
+)
+
+llm_with_tools = llm.bind_tools(tools)
 
 
 class State(TypedDict):
     input_file: Optional[str]
     messages: Annotated[list[AnyMessage], add_messages]
+    answer: str
 
 def should_continue(state: State):
     messages = state["messages"]
@@ -40,15 +43,36 @@ def should_continue(state: State):
         return "tools"
     return END
 
-
+def format_answer(last_message: str):
+    system_message_content = "You are a general AI assistant. \
+        Check the user's answer and validate and format it with the following rules: \
+        The output should be in the following format: \
+        FINAL ANSWER: [YOUR FINAL ANSWER]. \
+        YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. \
+        If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. \
+        If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. \
+        If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. \
+        Your answer should only start with 'FINAL ANSWER: ', then follows with the answer. "
+    system_message = SystemMessage(content=system_message_content)
+    messages = [system_message] + [last_message]
+    answer = llm_with_tools.invoke(messages)
+    return answer.content
 
 def agent(state: State):
-    system_message_content = "You are a helpful assistant that can read files and calling tools to answer questions. You should output results directly, without any additional text or explanation."
+    system_message_content = "You are a general AI assistant. I will ask you a question. \
+    Report your thoughts, and finish your answer with the following template: \
+        FINAL ANSWER: [YOUR FINAL ANSWER]. \
+        YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. \
+        If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. \
+        If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. \
+        If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string. \
+        Your answer should only start with 'FINAL ANSWER: ', then follows with the answer. "
     if state["input_file"]:
         system_message_content += f"\nYou are given a file: {state['input_file']}"
     system_message = SystemMessage(content=system_message_content)
     messages = [system_message] + state["messages"]
-    return {"messages": [llm_with_tools.invoke(messages)]}
+    answer = llm_with_tools.invoke(messages)
+    return {"messages": [answer], "answer": format_answer(answer.content)}
 
 
 class Agent:
@@ -77,4 +101,4 @@ class Agent:
 
     def __call__(self, question: str, file_name: str|None) -> str:
         result = self.graph.invoke({"input_file": file_name, "messages": [HumanMessage(content=question)]})
-        return result["messages"][-1].content
+        return result["answer"]

app.py

@@ -99,6 +99,7 @@ def run_all( username: str|None, submit: bool = True):
             print("-"*100)
             print(f"Running agent on task {task_id}: {question_text}")
             submitted_answer = agent(question_text, "")
+            print("-"*30)
             print(f"Submitted answer: {submitted_answer}")
             print("-"*100)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})

tool/youtube.py

@@ -8,12 +8,14 @@ def youtube_transcript(video_id: str) -> str:
     """
     print(f"Extracting transcript from: {video_id}")
     try:
-        ytt_api = YouTubeTranscriptApi(
-            proxy_config=GenericProxyConfig(
-                http_url=os.getenv("PROXY_URL"),
-                https_url=os.getenv("PROXY_URL"),
+        ytt_api = YouTubeTranscriptApi()
+        if os.getenv("PROXY_URL"):
+            ytt_api = YouTubeTranscriptApi(
+                proxy_config=GenericProxyConfig(
+                    http_url=os.getenv("PROXY_URL"),
+                    https_url=os.getenv("PROXY_URL"),
+                )
             )
-        )
         transcript = ytt_api.fetch(video_id)
         print(f"Transcript: {transcript}")
         return transcript