my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: Langchain
#3	---
#4
#5	Build a personalized Travel Agent AI using LangChain for conversation flow and Mem0 for memory retention. This integration enables context-aware and efficient travel planning experiences.
#6
#7	## Overview
#8
#9	In this guide, we'll create a Travel Agent AI that:
#10	1. Uses LangChain to manage conversation flow
#11	2. Leverages Mem0 to store and retrieve relevant information from past interactions
#12	3. Provides personalized travel recommendations based on user history
#13
#14	## Setup and Configuration
#15
#16	Install necessary libraries:
#17
#18	```bash
#19	pip install langchain langchain_openai mem0ai python-dotenv
#20	```
#21
#22	Import required modules and set up configurations:
#23
#24	<Note>Remember to get the Mem0 API key from [Mem0 Platform](https://app.mem0.ai).</Note>
#25
#26	```python
#27	import os
#28	from typing import List, Dict
#29	from langchain_openai import ChatOpenAI
#30	from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
#31	from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
#32	from mem0 import MemoryClient
#33	from dotenv import load_dotenv
#34
#35	load_dotenv()
#36
#37	# Configuration
#38	# os.environ["OPENAI_API_KEY"] = "your-openai-api-key"
#39	# os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
#40
#41	# Initialize LangChain and Mem0
#42	llm = ChatOpenAI(model="gpt-4.1-nano-2025-04-14")
#43	mem0 = MemoryClient()
#44	```
#45
#46	## Create Prompt Template
#47
#48	Set up the conversation prompt template:
#49
#50	```python
#51	prompt = ChatPromptTemplate.from_messages([
#52	SystemMessage(content="""You are a helpful travel agent AI. Use the provided context to personalize your responses and remember user preferences and past interactions.
#53	Provide travel recommendations, itinerary suggestions, and answer questions about destinations.
#54	If you don't have specific information, you can make general suggestions based on common travel knowledge."""),
#55	MessagesPlaceholder(variable_name="context"),
#56	HumanMessage(content="{input}")
#57	])
#58	```
#59
#60	## Define Helper Functions
#61
#62	Create functions to handle context retrieval, response generation, and addition to Mem0:
#63
#64	```python
#65	def retrieve_context(query: str, user_id: str) -> List[Dict]:
#66	"""Retrieve relevant context from Mem0"""
#67	try:
#68	memories = mem0.search(query, user_id=user_id)
#69	memory_list = memories['results']
#70
#71	serialized_memories = ' '.join([mem["memory"] for mem in memory_list])
#72	context = [
#73	{
#74	"role": "system",
#75	"content": f"Relevant information: {serialized_memories}"
#76	},
#77	{
#78	"role": "user",
#79	"content": query
#80	}
#81	]
#82	return context
#83	except Exception as e:
#84	print(f"Error retrieving memories: {e}")
#85	# Return empty context if there's an error
#86	return [{"role": "user", "content": query}]
#87
#88	def generate_response(input: str, context: List[Dict]) -> str:
#89	"""Generate a response using the language model"""
#90	chain = prompt \| llm
#91	response = chain.invoke({
#92	"context": context,
#93	"input": input
#94	})
#95	return response.content
#96
#97	def save_interaction(user_id: str, user_input: str, assistant_response: str):
#98	"""Save the interaction to Mem0"""
#99	try:
#100	interaction = [
#101	{
#102	"role": "user",
#103	"content": user_input
#104	},
#105	{
#106	"role": "assistant",
#107	"content": assistant_response
#108	}
#109	]
#110	result = mem0.add(interaction, user_id=user_id)
#111	print(f"Memory saved successfully: {len(result.get('results', []))} memories added")
#112	except Exception as e:
#113	print(f"Error saving interaction: {e}")
#114	```
#115
#116	## Create Chat Turn Function
#117
#118	Implement the main function to manage a single turn of conversation:
#119
#120	```python
#121	def chat_turn(user_input: str, user_id: str) -> str:
#122	# Retrieve context
#123	context = retrieve_context(user_input, user_id)
#124
#125	# Generate response
#126	response = generate_response(user_input, context)
#127
#128	# Save interaction
#129	save_interaction(user_id, user_input, response)
#130
#131	return response
#132	```
#133
#134	## Main Interaction Loop
#135
#136	Set up the main program loop for user interaction:
#137
#138	```python
#139	if __name__ == "__main__":
#140	print("Welcome to your personal Travel Agent Planner! How can I assist you with your travel plans today?")
#141	user_id = "alice"
#142
#143	while True:
#144	user_input = input("You: ")
#145	if user_input.lower() in ['quit', 'exit', 'bye']:
#146	print("Travel Agent: Thank you for using our travel planning service. Have a great trip!")
#147	break
#148
#149	response = chat_turn(user_input, user_id)
#150	print(f"Travel Agent: {response}")
#151	```
#152
#153	## Key Features
#154
#155	1. Memory Integration: Uses Mem0 to store and retrieve relevant information from past interactions.
#156	2. Personalization: Provides context-aware responses based on user history and preferences.
#157	3. Flexible Architecture: LangChain structure allows for easy expansion of the conversation flow.
#158	4. Continuous Learning: Each interaction is stored, improving future responses.
#159
#160	## Conclusion
#161
#162	By integrating LangChain with Mem0, you can build a personalized Travel Agent AI that can maintain context across interactions and provide tailored travel recommendations and assistance.
#163
#164	<CardGroup cols={2}>
#165	<Card title="LangGraph Integration" icon="diagram-project" href="/integrations/langgraph">
#166	Build stateful agents with LangGraph and Mem0
#167	</Card>
#168	<Card title="LangChain Tools" icon="wrench" href="/integrations/langchain-tools">
#169	Use Mem0 as LangChain tools for agent workflows
#170	</Card>
#171	</CardGroup>
#172
#173
#174

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public