Spaces:
Running
Running
Update travel.py
Browse files
travel.py
CHANGED
@@ -1,38 +1,49 @@
|
|
1 |
import os
|
2 |
import json
|
|
|
3 |
from datetime import datetime, timedelta
|
4 |
from langchain_google_genai import ChatGoogleGenerativeAI
|
5 |
from langchain.schema import SystemMessage, HumanMessage
|
6 |
|
7 |
-
#
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
10 |
class Agent:
|
11 |
-
def __init__(self, role, goal, backstory, personality="", llm=None):
|
|
|
|
|
|
|
12 |
self.role = role
|
13 |
self.goal = goal
|
14 |
self.backstory = backstory
|
15 |
self.personality = personality
|
16 |
-
self.tools = [] # Initialize with empty list
|
17 |
self.llm = llm
|
18 |
|
19 |
class Task:
|
20 |
-
def __init__(self, description, agent, expected_output, context=None):
|
|
|
|
|
|
|
21 |
self.description = description
|
22 |
self.agent = agent
|
23 |
self.expected_output = expected_output
|
24 |
self.context = context or []
|
25 |
|
26 |
-
#
|
27 |
# Initialize LLM
|
28 |
-
#
|
29 |
-
google_api_key = os.getenv("GEMINI_API_KEY") #
|
|
|
|
|
30 |
llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", google_api_key=google_api_key)
|
31 |
|
32 |
-
#
|
33 |
# Define Travel Agents
|
34 |
-
#
|
35 |
-
# 1. Destination Research Agent
|
36 |
destination_research_agent = Agent(
|
37 |
role="Destination Research Agent",
|
38 |
goal=(
|
@@ -47,7 +58,6 @@ destination_research_agent = Agent(
|
|
47 |
llm=llm,
|
48 |
)
|
49 |
|
50 |
-
# 2. Accommodation Agent
|
51 |
accommodation_agent = Agent(
|
52 |
role="Accommodation Agent",
|
53 |
goal="Find and recommend suitable accommodations based on the traveler's preferences, budget, and location requirements.",
|
@@ -56,7 +66,6 @@ accommodation_agent = Agent(
|
|
56 |
llm=llm,
|
57 |
)
|
58 |
|
59 |
-
# 3. Transportation Agent
|
60 |
transportation_agent = Agent(
|
61 |
role="Transportation Agent",
|
62 |
goal="Plan efficient transportation between the origin, destination, and all points of interest in the itinerary.",
|
@@ -65,7 +74,6 @@ transportation_agent = Agent(
|
|
65 |
llm=llm,
|
66 |
)
|
67 |
|
68 |
-
# 4. Activities & Attractions Agent
|
69 |
activities_agent = Agent(
|
70 |
role="Activities & Attractions Agent",
|
71 |
goal="Curate personalized activities and attractions that align with the traveler's interests, preferences, and time constraints.",
|
@@ -74,7 +82,6 @@ activities_agent = Agent(
|
|
74 |
llm=llm,
|
75 |
)
|
76 |
|
77 |
-
# 5. Dining & Culinary Agent
|
78 |
dining_agent = Agent(
|
79 |
role="Dining & Culinary Agent",
|
80 |
goal="Recommend dining experiences that showcase local cuisine while accommodating dietary preferences and budget considerations.",
|
@@ -83,7 +90,6 @@ dining_agent = Agent(
|
|
83 |
llm=llm,
|
84 |
)
|
85 |
|
86 |
-
# 6. Itinerary Integration Agent
|
87 |
itinerary_agent = Agent(
|
88 |
role="Itinerary Integration Agent",
|
89 |
goal="Compile all recommendations into a cohesive, day-by-day itinerary that optimizes time, minimizes travel fatigue, and maximizes enjoyment.",
|
@@ -92,52 +98,48 @@ itinerary_agent = Agent(
|
|
92 |
llm=llm,
|
93 |
)
|
94 |
|
95 |
-
|
96 |
-
|
97 |
-
# ------------------------------------------------------------------------------
|
98 |
# Define Tasks
|
99 |
-
#
|
100 |
destination_research_task = Task(
|
101 |
description="""Research {destination} thoroughly, considering the traveler's interests in {preferences}.
|
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 |
agent=destination_research_agent,
|
127 |
-
|
128 |
expected_output="""Targeted destination brief containing:
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
)
|
142 |
|
143 |
accommodation_task = Task(
|
@@ -155,45 +157,43 @@ transportation_task = Task(
|
|
155 |
activities_task = Task(
|
156 |
description="""Suggest activities and attractions in {destination} that align with interests in {preferences}.
|
157 |
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
|
163 |
-
|
164 |
-
|
165 |
-
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
agent=activities_agent,
|
181 |
-
|
182 |
expected_output="""Comprehensive curated list of activities and attractions with:
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
)
|
198 |
|
199 |
dining_task = Task(
|
@@ -205,80 +205,77 @@ dining_task = Task(
|
|
205 |
itinerary_task = Task(
|
206 |
description="""Create a day-by-day itinerary for a {duration} trip to {destination} from {origin}, incorporating all recommendations.
|
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 |
agent=itinerary_agent,
|
237 |
-
|
238 |
expected_output="""Comprehensive day-by-day itinerary featuring:
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
)
|
254 |
|
255 |
-
|
256 |
-
|
257 |
-
# ------------------------------------------------------------------------------
|
258 |
# Helper Function to Run a Task with Full Agent & Task Information
|
259 |
-
#
|
260 |
-
def run_task(task, input_text):
|
|
|
|
|
|
|
261 |
try:
|
262 |
-
# Ensure 'task' is an instance of the Task class
|
263 |
if not isinstance(task, Task):
|
264 |
-
raise ValueError(f"Expected 'task' to be an instance of Task
|
265 |
-
|
266 |
-
# Ensure 'task.agent' exists and is an instance of Agent
|
267 |
if not hasattr(task, 'agent') or not isinstance(task.agent, Agent):
|
268 |
-
raise ValueError(
|
269 |
-
|
270 |
-
system_input =
|
271 |
-
|
272 |
-
|
273 |
-
|
274 |
-
|
275 |
-
""
|
276 |
-
|
277 |
-
|
278 |
-
|
279 |
-
|
280 |
-
{
|
281 |
-
""
|
|
|
282 |
messages = [
|
283 |
SystemMessage(content=system_input),
|
284 |
HumanMessage(content=task_input)
|
@@ -288,13 +285,16 @@ Input for Task:
|
|
288 |
raise ValueError("Empty response from LLM.")
|
289 |
return response.content
|
290 |
except Exception as e:
|
291 |
-
|
292 |
return f"Error in {task.agent.role}: {e}"
|
293 |
|
294 |
-
#
|
295 |
# User Input Functions
|
296 |
-
#
|
297 |
-
def get_user_input():
|
|
|
|
|
|
|
298 |
print("\n=== Travel Itinerary Generator ===\n")
|
299 |
origin = input("Enter your origin city/country: ")
|
300 |
destination = input("Enter your destination city/country: ")
|
@@ -316,132 +316,85 @@ def get_user_input():
|
|
316 |
"special_requirements": special_requirements
|
317 |
}
|
318 |
|
319 |
-
#
|
320 |
# Main Function to Generate Travel Itinerary
|
321 |
-
#
|
322 |
-
def generate_travel_itinerary(user_input):
|
|
|
|
|
|
|
323 |
print("\nGenerating your personalized travel itinerary...\n")
|
324 |
|
325 |
-
#
|
326 |
-
input_context =
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
-
""
|
|
|
334 |
|
335 |
# Step 1: Destination Research
|
336 |
print("Researching your destination...")
|
337 |
-
destination_info = run_task(
|
338 |
-
destination_research_task,
|
339 |
-
input_context.format(
|
340 |
-
destination=user_input['destination'],
|
341 |
-
preferences=user_input['preferences']
|
342 |
-
)
|
343 |
-
)
|
344 |
print("✓ Destination research completed")
|
345 |
|
346 |
# Step 2: Accommodation Recommendations
|
347 |
print("Finding ideal accommodations...")
|
348 |
-
accommodation_info = run_task(
|
349 |
-
accommodation_task,
|
350 |
-
input_context.format(
|
351 |
-
destination=user_input['destination'],
|
352 |
-
budget=user_input['budget'],
|
353 |
-
preferences=user_input['preferences']
|
354 |
-
)
|
355 |
-
)
|
356 |
print("✓ Accommodation recommendations completed")
|
357 |
|
358 |
# Step 3: Transportation Planning
|
359 |
print("Planning transportation...")
|
360 |
-
transportation_info = run_task(
|
361 |
-
transportation_task,
|
362 |
-
input_context.format(
|
363 |
-
origin=user_input['origin'],
|
364 |
-
destination=user_input['destination']
|
365 |
-
)
|
366 |
-
)
|
367 |
print("✓ Transportation planning completed")
|
368 |
|
369 |
# Step 4: Activities & Attractions
|
370 |
print("Curating activities and attractions...")
|
371 |
-
activities_info = run_task(
|
372 |
-
activities_task,
|
373 |
-
input_context.format(
|
374 |
-
destination=user_input['destination'],
|
375 |
-
preferences=user_input['preferences']
|
376 |
-
)
|
377 |
-
)
|
378 |
print("✓ Activities and attractions curated")
|
379 |
|
380 |
# Step 5: Dining Recommendations
|
381 |
print("Finding dining experiences...")
|
382 |
-
dining_info = run_task(
|
383 |
-
dining_task,
|
384 |
-
input_context.format(
|
385 |
-
destination=user_input['destination'],
|
386 |
-
preferences=user_input['preferences']
|
387 |
-
)
|
388 |
-
)
|
389 |
print("✓ Dining recommendations completed")
|
390 |
|
391 |
# Step 6: Create Day-by-Day Itinerary
|
392 |
print("Creating your day-by-day itinerary...")
|
393 |
-
combined_info =
|
394 |
-
|
395 |
-
Destination Information
|
396 |
-
|
397 |
-
|
398 |
-
|
399 |
-
|
400 |
-
|
401 |
-
Transportation Plan:
|
402 |
-
{transportation_info}
|
403 |
-
|
404 |
-
Recommended Activities:
|
405 |
-
{activities_info}
|
406 |
-
|
407 |
-
Dining Recommendations:
|
408 |
-
{dining_info}
|
409 |
-
"""
|
410 |
-
|
411 |
-
itinerary = run_task(
|
412 |
-
itinerary_task,
|
413 |
-
combined_info.format(
|
414 |
-
duration=user_input['duration'],
|
415 |
-
origin=user_input['origin'],
|
416 |
-
destination=user_input['destination']
|
417 |
-
)
|
418 |
)
|
|
|
419 |
print("✓ Itinerary creation completed")
|
420 |
-
|
421 |
-
# Return the completed itinerary
|
422 |
print("✓ Itinerary generation completed")
|
423 |
|
424 |
return itinerary
|
425 |
|
426 |
-
#
|
427 |
# Save Itinerary to File
|
428 |
-
#
|
429 |
-
def save_itinerary_to_file(itinerary, user_input, output_dir=None):
|
430 |
-
|
|
|
|
|
431 |
date_str = datetime.now().strftime("%Y-%m-%d")
|
432 |
filename = f"{user_input['destination'].replace(' ', '_')}_{date_str}_itinerary.txt"
|
433 |
|
434 |
-
# If output directory is specified, ensure it exists and use it
|
435 |
if output_dir:
|
436 |
if not os.path.exists(output_dir):
|
437 |
try:
|
438 |
os.makedirs(output_dir)
|
439 |
-
|
440 |
except Exception as e:
|
441 |
-
|
442 |
-
return
|
443 |
-
|
444 |
-
# Combine the output directory with the filename
|
445 |
filepath = os.path.join(output_dir, filename)
|
446 |
else:
|
447 |
filepath = filename
|
@@ -449,37 +402,34 @@ def save_itinerary_to_file(itinerary, user_input, output_dir=None):
|
|
449 |
try:
|
450 |
with open(filepath, "w", encoding="utf-8") as f:
|
451 |
f.write(itinerary)
|
452 |
-
|
453 |
return filepath
|
454 |
except Exception as e:
|
455 |
-
|
456 |
-
return
|
457 |
|
458 |
-
#
|
459 |
# Main Function
|
460 |
-
#
|
461 |
-
def main():
|
|
|
|
|
|
|
462 |
print("Welcome to BlockX Travel Itinerary Generator!")
|
463 |
print("This AI-powered tool will create a personalized travel itinerary based on your preferences.")
|
464 |
|
465 |
user_input = get_user_input()
|
466 |
|
467 |
-
# Ask for output directory
|
468 |
print("\nWhere would you like to save the itinerary?")
|
469 |
print("Press Enter to save in the current directory, or specify a path:")
|
470 |
-
output_dir = input("> ").strip()
|
471 |
-
|
472 |
-
# If empty, use current directory
|
473 |
-
if not output_dir:
|
474 |
-
output_dir = None
|
475 |
-
print("Will save in the current directory.")
|
476 |
|
477 |
itinerary = generate_travel_itinerary(user_input)
|
478 |
|
479 |
-
|
480 |
|
481 |
-
if
|
482 |
-
print(f"\nYour personalized travel itinerary is ready! Open {
|
483 |
print("Thank you for using BlockX Travel Itinerary Generator!")
|
484 |
|
485 |
if __name__ == "__main__":
|
|
|
1 |
import os
|
2 |
import json
|
3 |
+
import logging
|
4 |
from datetime import datetime, timedelta
|
5 |
from langchain_google_genai import ChatGoogleGenerativeAI
|
6 |
from langchain.schema import SystemMessage, HumanMessage
|
7 |
|
8 |
+
# Setup logging configuration
|
9 |
+
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
|
10 |
+
|
11 |
+
# -------------------------------------------------------------------------------
|
12 |
+
# Agent and Task Classes with Type Hints and Docstrings
|
13 |
+
# -------------------------------------------------------------------------------
|
14 |
class Agent:
|
15 |
+
def __init__(self, role: str, goal: str, backstory: str, personality: str = "", llm=None) -> None:
|
16 |
+
"""
|
17 |
+
Initialize an Agent with role, goal, backstory, personality, and assigned LLM.
|
18 |
+
"""
|
19 |
self.role = role
|
20 |
self.goal = goal
|
21 |
self.backstory = backstory
|
22 |
self.personality = personality
|
23 |
+
self.tools = [] # Initialize with empty list for future tool integrations
|
24 |
self.llm = llm
|
25 |
|
26 |
class Task:
|
27 |
+
def __init__(self, description: str, agent: Agent, expected_output: str, context=None) -> None:
|
28 |
+
"""
|
29 |
+
Initialize a Task with its description, the responsible agent, expected output, and optional context.
|
30 |
+
"""
|
31 |
self.description = description
|
32 |
self.agent = agent
|
33 |
self.expected_output = expected_output
|
34 |
self.context = context or []
|
35 |
|
36 |
+
# -------------------------------------------------------------------------------
|
37 |
# Initialize LLM
|
38 |
+
# -------------------------------------------------------------------------------
|
39 |
+
google_api_key = os.getenv("GEMINI_API_KEY") # 실제 Google API 키 사용
|
40 |
+
if not google_api_key:
|
41 |
+
logging.error("GEMINI_API_KEY is not set in the environment variables.")
|
42 |
llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", google_api_key=google_api_key)
|
43 |
|
44 |
+
# -------------------------------------------------------------------------------
|
45 |
# Define Travel Agents
|
46 |
+
# -------------------------------------------------------------------------------
|
|
|
47 |
destination_research_agent = Agent(
|
48 |
role="Destination Research Agent",
|
49 |
goal=(
|
|
|
58 |
llm=llm,
|
59 |
)
|
60 |
|
|
|
61 |
accommodation_agent = Agent(
|
62 |
role="Accommodation Agent",
|
63 |
goal="Find and recommend suitable accommodations based on the traveler's preferences, budget, and location requirements.",
|
|
|
66 |
llm=llm,
|
67 |
)
|
68 |
|
|
|
69 |
transportation_agent = Agent(
|
70 |
role="Transportation Agent",
|
71 |
goal="Plan efficient transportation between the origin, destination, and all points of interest in the itinerary.",
|
|
|
74 |
llm=llm,
|
75 |
)
|
76 |
|
|
|
77 |
activities_agent = Agent(
|
78 |
role="Activities & Attractions Agent",
|
79 |
goal="Curate personalized activities and attractions that align with the traveler's interests, preferences, and time constraints.",
|
|
|
82 |
llm=llm,
|
83 |
)
|
84 |
|
|
|
85 |
dining_agent = Agent(
|
86 |
role="Dining & Culinary Agent",
|
87 |
goal="Recommend dining experiences that showcase local cuisine while accommodating dietary preferences and budget considerations.",
|
|
|
90 |
llm=llm,
|
91 |
)
|
92 |
|
|
|
93 |
itinerary_agent = Agent(
|
94 |
role="Itinerary Integration Agent",
|
95 |
goal="Compile all recommendations into a cohesive, day-by-day itinerary that optimizes time, minimizes travel fatigue, and maximizes enjoyment.",
|
|
|
98 |
llm=llm,
|
99 |
)
|
100 |
|
101 |
+
# -------------------------------------------------------------------------------
|
|
|
|
|
102 |
# Define Tasks
|
103 |
+
# -------------------------------------------------------------------------------
|
104 |
destination_research_task = Task(
|
105 |
description="""Research {destination} thoroughly, considering the traveler's interests in {preferences}.
|
106 |
|
107 |
+
Efficient research parameters:
|
108 |
+
- Prioritize research in these critical categories:
|
109 |
+
* Top attractions that match specific {preferences} (not generic lists)
|
110 |
+
* Local transportation systems with cost-efficiency analysis
|
111 |
+
* Neighborhood breakdown with accommodation recommendations by budget tier
|
112 |
+
* Seasonal considerations for the specific travel dates
|
113 |
+
* Safety assessment with specific areas to embrace or avoid
|
114 |
+
* Cultural norms that impact visitor experience (dress codes, tipping, etiquette)
|
115 |
+
|
116 |
+
- Apply efficiency filters:
|
117 |
+
* Focus exclusively on verified information from official tourism boards, recent travel guides, and reliable local sources
|
118 |
+
* Analyze recent visitor reviews (< 6 months old) to identify changing conditions
|
119 |
+
* Evaluate price-to-experience value for attractions instead of just popularity
|
120 |
+
* Identify logistical clusters where multiple interests can be satisfied efficiently
|
121 |
+
* Research off-peak times for popular attractions to minimize waiting
|
122 |
+
* Evaluate digital tools (apps, passes, reservation systems) that streamline the visit
|
123 |
+
|
124 |
+
- Create practical knowledge matrices:
|
125 |
+
* Transportation method comparison (cost vs. time vs. convenience)
|
126 |
+
* Weather impact on specific activities
|
127 |
+
* Budget allocation recommendations based on preference priorities
|
128 |
+
* Time-saving opportunity identification""",
|
|
|
129 |
agent=destination_research_agent,
|
|
|
130 |
expected_output="""Targeted destination brief containing:
|
131 |
+
1. Executive summary highlighting the 5 most relevant aspects based on {preferences}
|
132 |
+
2. Neighborhood analysis with accommodation recommendations mapped to specific interests
|
133 |
+
3. Transportation efficiency guide with cost/convenience matrix
|
134 |
+
4. Cultural briefing focusing only on need-to-know information that impacts daily activities
|
135 |
+
5. Seasonal advantages and challenges specific to travel dates
|
136 |
+
6. Digital resource toolkit (essential apps, websites, reservation systems)
|
137 |
+
7. Budget optimization strategies with price ranges for key experiences
|
138 |
+
8. Safety and health quick-reference including emergency contacts
|
139 |
+
9. Logistics efficiency map showing optimal activity clustering
|
140 |
+
10. Local insider advantage recommendations that save time or money
|
141 |
+
|
142 |
+
Format should prioritize scannable information with bullet points, comparison tables, and decision matrices rather than lengthy prose."""
|
143 |
)
|
144 |
|
145 |
accommodation_task = Task(
|
|
|
157 |
activities_task = Task(
|
158 |
description="""Suggest activities and attractions in {destination} that align with interests in {preferences}.
|
159 |
|
160 |
+
Detailed requirements:
|
161 |
+
- Categorize activities into: Cultural Experiences, Outdoor Adventures, Culinary Experiences,
|
162 |
+
Entertainment & Nightlife, Family-Friendly Activities, and Local Hidden Gems
|
163 |
+
- For each activity, include:
|
164 |
+
* Detailed description with historical/cultural context where relevant
|
165 |
+
* Precise location with neighborhood information
|
166 |
+
* Operating hours with seasonal variations noted
|
167 |
+
* Pricing information with different ticket options/packages
|
168 |
+
* Accessibility considerations for travelers with mobility limitations
|
169 |
+
* Recommended duration for the activity (minimum and ideal time)
|
170 |
+
* Best time of day/week/year to visit
|
171 |
+
* Crowd levels by season
|
172 |
+
* Photography opportunities and restrictions
|
173 |
+
* Required reservations or booking windows
|
174 |
+
- Include a mix of iconic must-see attractions and off-the-beaten-path experiences
|
175 |
+
- Consider weather patterns in {destination} during travel period
|
176 |
+
- Analyze the {preferences} to match specific personality types and interest levels
|
177 |
+
- Include at least 2-3 rainy day alternatives for outdoor activities
|
178 |
+
- Provide local transportation options to reach each attraction
|
179 |
+
- Note authentic local experiences that provide cultural immersion
|
180 |
+
- Flag any activities requiring special equipment, permits, or physical fitness levels""",
|
|
|
181 |
agent=activities_agent,
|
|
|
182 |
expected_output="""Comprehensive curated list of activities and attractions with:
|
183 |
+
1. Clear categorization by type (cultural, outdoor, culinary, entertainment, family-friendly, hidden gems)
|
184 |
+
2. Detailed descriptions that include historical and cultural context
|
185 |
+
3. Complete practical information (hours, pricing, location, accessibility)
|
186 |
+
4. Time optimization recommendations (best time to visit, how to avoid crowds)
|
187 |
+
5. Personalized matches explaining why each activity aligns with specific {preferences}
|
188 |
+
6. Local transportation details to reach each attraction
|
189 |
+
7. Alternative options for inclement weather or unexpected closures
|
190 |
+
8. Insider tips from locals that enhance the experience
|
191 |
+
9. Suggested combinations of nearby activities for efficient itinerary planning
|
192 |
+
10. Risk level assessment and safety considerations where applicable
|
193 |
+
11. Sustainability impact and responsible tourism notes
|
194 |
+
12. Photographic highlights and optimal viewing points
|
195 |
+
|
196 |
+
Format should include a summary table for quick reference followed by detailed cards for each activity."""
|
197 |
)
|
198 |
|
199 |
dining_task = Task(
|
|
|
205 |
itinerary_task = Task(
|
206 |
description="""Create a day-by-day itinerary for a {duration} trip to {destination} from {origin}, incorporating all recommendations.
|
207 |
|
208 |
+
Detailed requirements:
|
209 |
+
- Begin with arrival logistics including airport transfer options, check-in times, and first-day orientation activities
|
210 |
+
- Structure each day with:
|
211 |
+
* Morning, afternoon, and evening activity blocks with precise timing
|
212 |
+
* Estimated travel times between locations using various transportation methods
|
213 |
+
* Buffer time for rest, spontaneous exploration, and unexpected delays
|
214 |
+
* Meal recommendations with reservation details and backup options
|
215 |
+
* Sunset/sunrise opportunities for optimal photography or experiences
|
216 |
+
- Apply intelligent sequencing to:
|
217 |
+
* Group attractions by geographic proximity to minimize transit time
|
218 |
+
* Schedule indoor activities strategically for predicted weather patterns
|
219 |
+
* Balance high-energy activities with relaxation periods
|
220 |
+
* Alternate between cultural immersion and entertainment experiences
|
221 |
+
* Account for opening days/hours of attractions and potential closures
|
222 |
+
- Include practical timing considerations:
|
223 |
+
* Museum/attraction fatigue limitations
|
224 |
+
* Jet lag recovery for first 1-2 days
|
225 |
+
* Time zone adjustment strategies
|
226 |
+
* Local rush hours and traffic patterns to avoid
|
227 |
+
* Cultural norms for meal times and business hours
|
228 |
+
- End with departure logistics including check-out procedures, airport transfer timing, and luggage considerations
|
229 |
+
- Add specialized planning elements:
|
230 |
+
* Local festivals or events coinciding with the travel dates
|
231 |
+
* Free time blocks for personal exploration or shopping
|
232 |
+
* Contingency recommendations for weather disruptions
|
233 |
+
* Early booking requirements for popular attractions/restaurants
|
234 |
+
* Local emergency contacts and nearby medical facilities""",
|
|
|
235 |
agent=itinerary_agent,
|
|
|
236 |
expected_output="""Comprehensive day-by-day itinerary featuring:
|
237 |
+
1. Detailed timeline for each day with hour-by-hour scheduling and transit times
|
238 |
+
2. Color-coded activity blocks that visually distinguish between types of activities
|
239 |
+
3. Intelligent geographic clustering to minimize transportation time
|
240 |
+
4. Strategic meal placements with both reservation-required and casual options
|
241 |
+
5. Built-in flexibility with free time blocks and alternative suggestions
|
242 |
+
6. Weather-adaptive scheduling with indoor/outdoor activity balance
|
243 |
+
7. Energy level considerations throughout the trip arc
|
244 |
+
8. Cultural timing adaptations (accommodating local siesta times, religious observances, etc.)
|
245 |
+
9. Practical logistical details (bag storage options, dress code reminders, etc.)
|
246 |
+
10. Local transportation guidance including transit cards, apps, and pre-booking requirements
|
247 |
+
11. Visual map representation showing daily movement patterns
|
248 |
+
12. Key phrases in local language for each day's activities
|
249 |
+
|
250 |
+
Format should include both a condensed overview calendar and detailed daily breakdowns with time, activity, location, notes, and contingency plans."""
|
251 |
)
|
252 |
|
253 |
+
# -------------------------------------------------------------------------------
|
|
|
|
|
254 |
# Helper Function to Run a Task with Full Agent & Task Information
|
255 |
+
# -------------------------------------------------------------------------------
|
256 |
+
def run_task(task: Task, input_text: str) -> str:
|
257 |
+
"""
|
258 |
+
Executes the given task using the associated agent's LLM and returns the response content.
|
259 |
+
"""
|
260 |
try:
|
|
|
261 |
if not isinstance(task, Task):
|
262 |
+
raise ValueError(f"Expected 'task' to be an instance of Task, got {type(task)}")
|
|
|
|
|
263 |
if not hasattr(task, 'agent') or not isinstance(task.agent, Agent):
|
264 |
+
raise ValueError("Task must have a valid 'agent' attribute of type Agent.")
|
265 |
+
|
266 |
+
system_input = (
|
267 |
+
f"Agent Details:\n"
|
268 |
+
f"Role: {task.agent.role}\n"
|
269 |
+
f"Goal: {task.agent.goal}\n"
|
270 |
+
f"Backstory: {task.agent.backstory}\n"
|
271 |
+
f"Personality: {task.agent.personality}\n"
|
272 |
+
)
|
273 |
+
task_input = (
|
274 |
+
f"Task Details:\n"
|
275 |
+
f"Task Description: {task.description}\n"
|
276 |
+
f"Expected Output: {task.expected_output}\n"
|
277 |
+
f"Input for Task:\n{input_text}\n"
|
278 |
+
)
|
279 |
messages = [
|
280 |
SystemMessage(content=system_input),
|
281 |
HumanMessage(content=task_input)
|
|
|
285 |
raise ValueError("Empty response from LLM.")
|
286 |
return response.content
|
287 |
except Exception as e:
|
288 |
+
logging.error(f"Error in task '{task.agent.role}': {e}")
|
289 |
return f"Error in {task.agent.role}: {e}"
|
290 |
|
291 |
+
# -------------------------------------------------------------------------------
|
292 |
# User Input Functions
|
293 |
+
# -------------------------------------------------------------------------------
|
294 |
+
def get_user_input() -> dict:
|
295 |
+
"""
|
296 |
+
Collects user input for travel itinerary generation.
|
297 |
+
"""
|
298 |
print("\n=== Travel Itinerary Generator ===\n")
|
299 |
origin = input("Enter your origin city/country: ")
|
300 |
destination = input("Enter your destination city/country: ")
|
|
|
316 |
"special_requirements": special_requirements
|
317 |
}
|
318 |
|
319 |
+
# -------------------------------------------------------------------------------
|
320 |
# Main Function to Generate Travel Itinerary
|
321 |
+
# -------------------------------------------------------------------------------
|
322 |
+
def generate_travel_itinerary(user_input: dict) -> str:
|
323 |
+
"""
|
324 |
+
Generates a personalized travel itinerary by sequentially running defined tasks.
|
325 |
+
"""
|
326 |
print("\nGenerating your personalized travel itinerary...\n")
|
327 |
|
328 |
+
# Create input context using f-string formatting
|
329 |
+
input_context = (
|
330 |
+
f"Travel Request Details:\n"
|
331 |
+
f"Origin: {user_input['origin']}\n"
|
332 |
+
f"Destination: {user_input['destination']}\n"
|
333 |
+
f"Duration: {user_input['duration']} days\n"
|
334 |
+
f"Budget Level: {user_input['budget']}\n"
|
335 |
+
f"Preferences/Interests: {user_input['preferences']}\n"
|
336 |
+
f"Special Requirements: {user_input['special_requirements']}\n"
|
337 |
+
)
|
338 |
|
339 |
# Step 1: Destination Research
|
340 |
print("Researching your destination...")
|
341 |
+
destination_info = run_task(destination_research_task, input_context)
|
|
|
|
|
|
|
|
|
|
|
|
|
342 |
print("✓ Destination research completed")
|
343 |
|
344 |
# Step 2: Accommodation Recommendations
|
345 |
print("Finding ideal accommodations...")
|
346 |
+
accommodation_info = run_task(accommodation_task, input_context)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
347 |
print("✓ Accommodation recommendations completed")
|
348 |
|
349 |
# Step 3: Transportation Planning
|
350 |
print("Planning transportation...")
|
351 |
+
transportation_info = run_task(transportation_task, input_context)
|
|
|
|
|
|
|
|
|
|
|
|
|
352 |
print("✓ Transportation planning completed")
|
353 |
|
354 |
# Step 4: Activities & Attractions
|
355 |
print("Curating activities and attractions...")
|
356 |
+
activities_info = run_task(activities_task, input_context)
|
|
|
|
|
|
|
|
|
|
|
|
|
357 |
print("✓ Activities and attractions curated")
|
358 |
|
359 |
# Step 5: Dining Recommendations
|
360 |
print("Finding dining experiences...")
|
361 |
+
dining_info = run_task(dining_task, input_context)
|
|
|
|
|
|
|
|
|
|
|
|
|
362 |
print("✓ Dining recommendations completed")
|
363 |
|
364 |
# Step 6: Create Day-by-Day Itinerary
|
365 |
print("Creating your day-by-day itinerary...")
|
366 |
+
combined_info = (
|
367 |
+
input_context + "\n"
|
368 |
+
"Destination Information:\n" + destination_info + "\n"
|
369 |
+
"Accommodation Options:\n" + accommodation_info + "\n"
|
370 |
+
"Transportation Plan:\n" + transportation_info + "\n"
|
371 |
+
"Recommended Activities:\n" + activities_info + "\n"
|
372 |
+
"Dining Recommendations:\n" + dining_info + "\n"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
373 |
)
|
374 |
+
itinerary = run_task(itinerary_task, combined_info)
|
375 |
print("✓ Itinerary creation completed")
|
|
|
|
|
376 |
print("✓ Itinerary generation completed")
|
377 |
|
378 |
return itinerary
|
379 |
|
380 |
+
# -------------------------------------------------------------------------------
|
381 |
# Save Itinerary to File
|
382 |
+
# -------------------------------------------------------------------------------
|
383 |
+
def save_itinerary_to_file(itinerary: str, user_input: dict, output_dir: str = None) -> str:
|
384 |
+
"""
|
385 |
+
Saves the generated itinerary to a text file and returns the filepath.
|
386 |
+
"""
|
387 |
date_str = datetime.now().strftime("%Y-%m-%d")
|
388 |
filename = f"{user_input['destination'].replace(' ', '_')}_{date_str}_itinerary.txt"
|
389 |
|
|
|
390 |
if output_dir:
|
391 |
if not os.path.exists(output_dir):
|
392 |
try:
|
393 |
os.makedirs(output_dir)
|
394 |
+
logging.info(f"Created output directory: {output_dir}")
|
395 |
except Exception as e:
|
396 |
+
logging.error(f"Error creating directory {output_dir}: {e}")
|
397 |
+
return ""
|
|
|
|
|
398 |
filepath = os.path.join(output_dir, filename)
|
399 |
else:
|
400 |
filepath = filename
|
|
|
402 |
try:
|
403 |
with open(filepath, "w", encoding="utf-8") as f:
|
404 |
f.write(itinerary)
|
405 |
+
logging.info(f"Your itinerary has been saved as: {filepath}")
|
406 |
return filepath
|
407 |
except Exception as e:
|
408 |
+
logging.error(f"Error saving itinerary: {e}")
|
409 |
+
return ""
|
410 |
|
411 |
+
# -------------------------------------------------------------------------------
|
412 |
# Main Function
|
413 |
+
# -------------------------------------------------------------------------------
|
414 |
+
def main() -> None:
|
415 |
+
"""
|
416 |
+
Main entry point for the travel itinerary generator application.
|
417 |
+
"""
|
418 |
print("Welcome to BlockX Travel Itinerary Generator!")
|
419 |
print("This AI-powered tool will create a personalized travel itinerary based on your preferences.")
|
420 |
|
421 |
user_input = get_user_input()
|
422 |
|
|
|
423 |
print("\nWhere would you like to save the itinerary?")
|
424 |
print("Press Enter to save in the current directory, or specify a path:")
|
425 |
+
output_dir = input("> ").strip() or None
|
|
|
|
|
|
|
|
|
|
|
426 |
|
427 |
itinerary = generate_travel_itinerary(user_input)
|
428 |
|
429 |
+
filepath = save_itinerary_to_file(itinerary, user_input, output_dir)
|
430 |
|
431 |
+
if filepath:
|
432 |
+
print(f"\nYour personalized travel itinerary is ready! Open {filepath} to view it.")
|
433 |
print("Thank you for using BlockX Travel Itinerary Generator!")
|
434 |
|
435 |
if __name__ == "__main__":
|