File size: 13,214 Bytes
10e9b7d
 
eccf8e4
7d65c66
3c4371f
0519c89
7319d31
0519c89
7319d31
 
 
 
 
 
 
10e9b7d
e80aab9
3db6293
e80aab9
0519c89
 
a1c1d9a
0519c89
 
a1c1d9a
0519c89
 
 
 
a1c1d9a
0519c89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1c1d9a
0519c89
 
 
a1c1d9a
0519c89
 
7319d31
31243f4
 
7319d31
 
 
 
 
 
 
 
 
0519c89
7319d31
 
 
 
 
0519c89
7319d31
 
 
 
 
 
 
a1c1d9a
 
0519c89
a1c1d9a
 
 
 
0519c89
a1c1d9a
0519c89
7319d31
 
 
 
 
 
 
 
a1c1d9a
7319d31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4021bf3
7319d31
31243f4
0519c89
 
31243f4
a1c1d9a
3c4371f
7e4a06b
1ca9f65
3c4371f
7e4a06b
3c4371f
7d65c66
3c4371f
7e4a06b
31243f4
 
e80aab9
a1c1d9a
31243f4
 
 
3c4371f
31243f4
7319d31
36ed51a
c1fd3d2
3c4371f
7d65c66
31243f4
eccf8e4
31243f4
7d65c66
31243f4
 
3c4371f
 
31243f4
e80aab9
31243f4
 
7d65c66
31243f4
 
e80aab9
a1c1d9a
7d65c66
 
a1c1d9a
 
3c4371f
0519c89
31243f4
 
 
a1c1d9a
0519c89
31243f4
 
 
0519c89
a1c1d9a
0519c89
 
a1c1d9a
0519c89
a1c1d9a
 
0519c89
31243f4
a1c1d9a
0519c89
7d65c66
0519c89
 
 
 
 
 
31243f4
0519c89
 
 
 
a1c1d9a
0519c89
31243f4
a1c1d9a
 
 
 
 
 
 
 
 
31243f4
3c4371f
31243f4
 
a1c1d9a
7d65c66
3c4371f
31243f4
e80aab9
a1c1d9a
31243f4
e80aab9
7d65c66
e80aab9
 
31243f4
e80aab9
 
3c4371f
 
 
e80aab9
 
31243f4
 
e80aab9
3c4371f
e80aab9
 
3c4371f
e80aab9
7d65c66
3c4371f
31243f4
7d65c66
31243f4
3c4371f
 
 
 
 
e80aab9
31243f4
 
 
 
7d65c66
31243f4
 
 
 
e80aab9
a1c1d9a
e80aab9
7319d31
0ee0419
e514fd7
 
 
7319d31
 
 
 
e514fd7
7319d31
 
 
 
 
 
e514fd7
7319d31
e514fd7
e80aab9
 
7e4a06b
e80aab9
31243f4
e80aab9
9088b99
7d65c66
e80aab9
31243f4
 
 
e80aab9
 
 
3c4371f
 
7319d31
7d65c66
3c4371f
 
7d65c66
3c4371f
7d65c66
 
7319d31
7d65c66
 
 
 
 
 
3c4371f
 
7319d31
a1c1d9a
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
import os
import gradio as gr
import requests
import inspect
import pandas as pd
import tempfile
from dotenv import load_dotenv
from typing import Optional

# Load environment variables
load_dotenv()

# Import your LangGraph agent
from graph.graph_builder import graph
from langchain_core.messages import HumanMessage

# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# --- File Download Helper Function ---
def download_file(task_id: str, api_url: str) -> Optional[str]:
    """Download file associated with a task_id from the evaluation API"""
    try:
        file_url = f"{api_url}/files/{task_id}"
        print(f"๐Ÿ“ Downloading file for task {task_id}")
        
        response = requests.get(file_url, timeout=30)
        response.raise_for_status()
        
        # Get filename from headers or create one
        content_disposition = response.headers.get('Content-Disposition', '')
        if 'filename=' in content_disposition:
            filename = content_disposition.split('filename=')[1].strip('"')
        else:
            content_type = response.headers.get('Content-Type', '')
            if 'image' in content_type:
                extension = '.jpg'
            elif 'audio' in content_type:
                extension = '.mp3'
            elif 'video' in content_type:
                extension = '.mp4'
            else:
                extension = '.txt'
            filename = f"task_{task_id}_file{extension}"
        
        # Save to temporary file
        temp_dir = tempfile.gettempdir()
        file_path = os.path.join(temp_dir, filename)
        
        with open(file_path, 'wb') as f:
            f.write(response.content)
        
        print(f"โœ… File downloaded: {file_path}")
        return file_path
        
    except Exception as e:
        print(f"โŒ Error downloading file for task {task_id}: {e}")
        return None

# --- Your LangGraph Agent Definition ---
class BasicAgent:
    def __init__(self):
        """Initialize the LangGraph agent"""
        print("LangGraph Agent initialized with multimodal, search, math, and YouTube tools.")
        
        if not os.getenv("OPENROUTER_API_KEY"):
            raise ValueError("OPENROUTER_API_KEY not found in environment variables")
        
        self.graph = graph
        print("โœ… Agent ready with tools: multimodal, search, math, YouTube")
    
    def __call__(self, question: str, file_path: Optional[str] = None) -> str:
        """
        Process a question using the LangGraph agent and return just the answer
        
        Args:
            question: The question to answer
            file_path: Optional path to associated file (image, audio, etc.)
            
        Returns:
            str: The final answer (formatted for evaluation)
        """
        print(f"๐Ÿค– Processing question: {question[:50]}...")
        
        try:
            # CRITICAL: Only modify the prompt if there's actually a valid file
            if file_path and os.path.exists(file_path):
                enhanced_question = f"{question}\n\nFile provided: {file_path}"
                print(f"๐Ÿ“Ž Processing with file: {file_path}")
            else:
                # Keep EXACTLY the same behavior as before for non-file questions
                enhanced_question = question
            
            # Create initial state with the question (enhanced or original)
            initial_state = {"messages": [HumanMessage(content=enhanced_question)]}
            
            # Run the LangGraph agent
            result = self.graph.invoke(initial_state)
            
            # Extract the final message content
            final_message = result["messages"][-1]
            answer = final_message.content
            
            # Clean up the answer for evaluation (UNCHANGED from original)
            if isinstance(answer, str):
                answer = answer.strip()
                
                prefixes_to_remove = [
                    "The answer is: ",
                    "Answer: ",
                    "The result is: ",
                    "Result: ",
                    "The final answer is: ",
                ]
                
                for prefix in prefixes_to_remove:
                    if answer.startswith(prefix):
                        answer = answer[len(prefix):].strip()
                        break
            
            print(f"โœ… Agent answer: {answer}")
            return answer
            
        except Exception as e:
            error_msg = f"Error processing question: {str(e)}"
            print(f"โŒ {error_msg}")
            return error_msg

def run_and_submit_all(profile: gr.OAuthProfile | None):
    """
    Fetches all questions, downloads associated files, runs the BasicAgent on them, 
    submits all answers, and displays the results.
    """
    space_id = os.getenv("SPACE_ID")

    if profile:
        username= f"{profile.username}"
        print(f"User logged in: {username}")
    else:
        print("User not logged in.")
        return "Please Login to Hugging Face with the button.", None

    api_url = DEFAULT_API_URL
    questions_url = f"{api_url}/questions"
    submit_url = f"{api_url}/submit"

    # 1. Instantiate Agent
    try:
        agent = BasicAgent()
    except Exception as e:
        print(f"Error instantiating agent: {e}")
        return f"Error initializing agent: {e}", None
    
    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
    print(agent_code)

    # 2. Fetch Questions
    print(f"Fetching questions from: {questions_url}")
    try:
        response = requests.get(questions_url, timeout=15)
        response.raise_for_status()
        questions_data = response.json()
        if not questions_data:
             print("Fetched questions list is empty.")
             return "Fetched questions list is empty or invalid format.", None
        print(f"Fetched {len(questions_data)} questions.")
    except requests.exceptions.RequestException as e:
        print(f"Error fetching questions: {e}")
        return f"Error fetching questions: {e}", None
    except Exception as e:
        print(f"An unexpected error occurred fetching questions: {e}")
        return f"An unexpected error occurred fetching questions: {e}", None

    # 3. Process Questions (with minimal changes)
    results_log = []
    answers_payload = []
    downloaded_files = []  # Track files for cleanup
    
    print(f"Running agent on {len(questions_data)} questions...")
    
    for item in questions_data:
        task_id = item.get("task_id")
        question_text = item.get("question")
        file_name = item.get("file_name")
        
        if not task_id or question_text is None:
            print(f"Skipping item with missing task_id or question: {item}")
            continue
        
        # Download file if it exists
        downloaded_file_path = None
        if file_name:
            print(f"๐Ÿ“‹ Task {task_id} has file: {file_name}")
            downloaded_file_path = download_file(task_id, api_url)
            if downloaded_file_path:
                downloaded_files.append(downloaded_file_path)  # Track for cleanup
        
        try:
            # Call agent (behavior unchanged for non-file questions)
            submitted_answer = agent(question_text, downloaded_file_path)
            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
            results_log.append({
                "Task ID": task_id, 
                "Question": question_text, 
                "Submitted Answer": submitted_answer
            })
            
        except Exception as e:
            print(f"โŒ Error running agent on task {task_id}: {e}")
            results_log.append({
                "Task ID": task_id, 
                "Question": question_text, 
                "Submitted Answer": f"AGENT ERROR: {e}"
            })

    # Cleanup downloaded files AFTER all processing is complete
    for file_path in downloaded_files:
        try:
            if os.path.exists(file_path):
                os.remove(file_path)
                print(f"๐Ÿงน Cleaned up: {file_path}")
        except Exception as e:
            print(f"โš ๏ธ Could not clean up {file_path}: {e}")

    if not answers_payload:
        print("Agent did not produce any answers to submit.")
        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)

    # 4. Prepare Submission (UNCHANGED)
    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
    print(status_update)

    # 5. Submit (UNCHANGED)
    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
    try:
        response = requests.post(submit_url, json=submission_data, timeout=60)
        response.raise_for_status()
        result_data = response.json()
        final_status = (
            f"Submission Successful!\n"
            f"User: {result_data.get('username')}\n"
            f"Overall Score: {result_data.get('score', 'N/A')}% "
            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
            f"Message: {result_data.get('message', 'No message received.')}"
        )
        print("Submission successful.")
        results_df = pd.DataFrame(results_log)
        return final_status, results_df
    except requests.exceptions.HTTPError as e:
        error_detail = f"Server responded with status {e.response.status_code}."
        try:
            error_json = e.response.json()
            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
        except requests.exceptions.JSONDecodeError:
            error_detail += f" Response: {e.response.text[:500]}"
        status_message = f"Submission Failed: {error_detail}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.Timeout:
        status_message = "Submission Failed: The request timed out."
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except requests.exceptions.RequestException as e:
        status_message = f"Submission Failed: Network error - {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df
    except Exception as e:
        status_message = f"An unexpected error occurred during submission: {e}"
        print(status_message)
        results_df = pd.DataFrame(results_log)
        return status_message, results_df

# --- Build Gradio Interface (UNCHANGED) ---
with gr.Blocks() as demo:
    gr.Markdown("# LangGraph Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        This space uses a LangGraph agent with multimodal, search, math, and YouTube tools powered by OpenRouter.
        
        1.  Log in to your Hugging Face account using the button below.
        2.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.

        **Agent Capabilities:**
        - ๐ŸŽจ **Multimodal**: Analyze images, extract text (OCR), process audio transcripts
        - ๐Ÿ” **Search**: Web search using multiple providers (DuckDuckGo, Tavily, SerpAPI)
        - ๐Ÿงฎ **Math**: Basic arithmetic, complex calculations, percentages, factorials
        - ๐Ÿ“บ **YouTube**: Extract captions, get video information
        
        ---
        **Note:** Processing all questions may take some time as the agent carefully analyzes each question and uses appropriate tools.
        """
    )

    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")

    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)

    run_button.click(
        fn=run_and_submit_all,
        outputs=[status_output, results_table]
    )

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")

    if space_host_startup:
        print(f"โœ… SPACE_HOST found: {space_host_startup}")
        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
    else:
        print("โ„น๏ธ  SPACE_HOST environment variable not found (running locally?).")

    if space_id_startup:
        print(f"โœ… SPACE_ID found: {space_id_startup}")
        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
    else:
        print("โ„น๏ธ  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")

    print("-"*(60 + len(" App Starting ")) + "\n")

    print("Launching Gradio Interface for LangGraph Agent Evaluation...")
    demo.launch(debug=True, share=True)