record result update

app.py

@@ -6,28 +6,42 @@ import json_repair
 import random
 import os
 import re
+import firebase_admin
+from firebase_admin import credentials, firestore
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
-openai_api_key = os.getenv("OPENAI_API_KEY")
+cred = credentials.Certificate(os.getenv("Firebase_JSON"))
+firebase_admin.initialize_app(cred)
+db = firestore.client()
 
-task_completed = 0
-task_completed_steps = None
+openai_api_key = os.getenv("OPENAI_API_KEY")
 
 
-def is_task_incomplete(example):
-    return example["task_completed"] is None and example["task_completed_steps"] is None
+def find_smallest_incomplete_task(app_name):
 
+    collection_ref = db.collection(app_name)
+    docs = collection_ref.stream()
 
-def is_task_given_up(example):
-    return example["task_completed"] == 0 and example["task_completed_steps"] == 0
+    smallest_incomplete_idx = None
+    for doc in docs:
+        doc_id = doc.id
+        _, idx = doc_id.split('_')
+        idx = int(idx)
 
+        task_data = doc.to_dict()
+        if task_data['task_completed'] is None and task_data['task_completed_steps'] is None:
+            if smallest_incomplete_idx is None or idx < smallest_incomplete_idx:
+                smallest_incomplete_idx = idx
 
-def is_task_incomplete_idx(example, idx):
-    return example["task_completed"] is None and example["task_completed_steps"] is None
+    return smallest_incomplete_idx
 
 
-def is_task_given_up_idx(example, idx):
-    return example["task_completed"] == 0 and example["task_completed_steps"] == 0
+def write_task_data(app_name, idx, task_complete, task_completed_step):
+    doc_ref = db.collection(app_name).document(f"{app_name}_{idx}")
+    doc_ref.set({
+        "task_completed": task_complete,
+        "task_completed_steps": task_completed_step
+    })
 
 
 class AppSimulator:
@@ -35,6 +49,7 @@ class AppSimulator:
         self.simulation = None
         self.openai_api_key = openai_api_key
         self.app_name = None
+        self.smallest_index = None
 
     def initialize_simulator(self, sitemap_url, progress=gr.Progress(track_tqdm=True)):
         """Initialize the simulator with retries and elapsed time tracking."""
@@ -53,23 +68,16 @@ class AppSimulator:
                 system_data = json_repair.loads(row['value'])
 
         self.app_name = app_name
-        human_result_url = "jjz5463/simulator_human_result"
-        synthetic_tasks = load_dataset(human_result_url, app_name, split='train')
-
-        incomplete_tasks = synthetic_tasks.filter(is_task_incomplete)
-        give_up_tasks = synthetic_tasks.filter(is_task_given_up)
-        if len(incomplete_tasks) > 0:
-            incomplete_task = incomplete_tasks[0]
-            task = incomplete_task["tasks"]
-            solution = incomplete_task["steps"]
-            user_data = incomplete_task["attributes"]["user_data"]
-        elif len(give_up_tasks) > 0:
-            give_up_task = give_up_tasks[0]
-            task = give_up_task["tasks"]
-            solution = give_up_task["steps"]
-            user_data = give_up_task["attributes"]["user_data"]
-        else:
+        smallest_index = find_smallest_incomplete_task(app_name)
+        if smallest_index is None:
             return "All tasks in this app have been completed!"
+        self.smallest_index = smallest_index
+
+        synthetic_tasks = load_dataset(sitemap_url, "tasks", split='train')
+        incomplete_task = synthetic_tasks[smallest_index]
+        task = incomplete_task["tasks"]
+        solution = incomplete_task["steps"]
+        user_data = incomplete_task["attributes"]["user_data"]
 
         self.simulation = ChatbotSimulation(
             app_name=app_name,
@@ -108,66 +116,27 @@ def chat(user_input, history):
     pattern = r"Task completed! You took (\d+) steps\."
     match = re.match(pattern, response)
 
-    global task_completed
-    global task_completed_steps
-    task_completed = 0
-    task_completed_steps = None
     if match:
-        task_completed = 1
-        task_completed_steps = int(match.group(1))
-        human_result_url = "jjz5463/simulator_human_result"
+        task_complete = 1
+        task_completed_step = int(match.group(1))
         app_name = simulator_app.app_name
-        synthetic_tasks = load_dataset(human_result_url, app_name, split='train')
-        incomplete_tasks = synthetic_tasks.filter(is_task_incomplete_idx, with_indices=True,)
-        if len(incomplete_tasks) > 0:
-            incomplete_task_index = incomplete_tasks['"__index"'][0]
-            synthetic_tasks = synthetic_tasks.map(
-                lambda example, idx: {
-                    "task_completed": task_completed if idx == incomplete_task_index else example["task_completed"],
-                    "task_completed_steps": task_completed_steps if idx == incomplete_task_index else example["task_completed_steps"],
-                },
-                with_indices=True,
-            )
-            # Push the updated dataset back to Hugging Face
-            synthetic_tasks.push_to_hub(human_result_url)
+        idx = simulator_app.smallest_index
+        write_task_data(app_name, idx, task_complete, task_completed_step)
 
     return response
 
 
 def give_up():
     """Handle the Give-Up action by marking the first incomplete task as abandoned."""
-    global task_completed, task_completed_steps
     task_completed = 0
     task_completed_steps = 0
 
-    # Access the app_name from the simulator instance
     app_name = simulator_app.app_name
-    if not app_name:
-        return "Simulator has not been initialized with an app!"
-
-    # Load the human result dataset
-    human_result_url = "jjz5463/simulator_human_result"
-    synthetic_tasks = load_dataset(human_result_url, app_name, split='train')
-
-    # Find the first incomplete task
-    incomplete_tasks = synthetic_tasks.filter(is_task_incomplete_idx, with_indices=True,)
-    if len(incomplete_tasks) > 0:
-        incomplete_task_index = incomplete_tasks['"__index"'][0]
-
-        # Update the dataset to mark the task as abandoned
-        synthetic_tasks = synthetic_tasks.map(
-            lambda example, idx: {
-                "task_completed": task_completed if idx == incomplete_task_index else example["task_completed"],
-                "steps": task_completed_steps if idx == incomplete_task_index else example["steps"],
-            },
-            with_indices=True,
-        )
+    idx = simulator_app.smallest_index
+
+    write_task_data(app_name, idx, task_completed, task_completed_steps)
 
-        # Push the updated dataset back to Hugging Face
-        synthetic_tasks.push_to_hub(human_result_url)
-        return "Task marked as abandoned (Give-Up action)."
-    else:
-        return "No incomplete tasks found to abandon!"
+    return "Task marked as abandoned (Give-Up action)."
 
 
 # Gradio Interface using ChatInterface

requirements.txt

@@ -1,3 +1,4 @@
 datadreamer.dev==0.38.0
 huggingface-hub==0.24.7
-json_repair
+json_repair
+firebase_admin