admin-valentin/awesome-llm-apps
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

changes made

Browse source
This commit is contained in:
Madhu 2025-01-19 17:43:13 +05:30
parent abb2cffa62
commit a57138b7bc
2 changed files with 89 additions and 56 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ai_agent_tutorials/ai_customer_support_agent/README.md
View file

@ -28,7 +28,7 @@ The app expects Qdrant to be running on localhost:6333. Adjust the configuration
docker pull qdrant/qdrant docker pull qdrant/qdrant
docker run -p 6333:6333 -p 6334:6334 \ docker run -p 6333:6333 -p 6334:6334 \
-v $(pwd)/qdrant_storage:/qdrant/storage:z \ -v "$(pwd)/qdrant_storage:/qdrant/storage:z" \
qdrant/qdrant qdrant/qdrant
``` ```

143
ai_agent_tutorials/ai_customer_support_agent/customer_support_agent.py
View file

@ -14,86 +14,115 @@ openai_api_key = st.text_input("Enter OpenAI API Key", type="password")
if openai_api_key: if openai_api_key:
os.environ['OPENAI_API_KEY'] = openai_api_key os.environ['OPENAI_API_KEY'] = openai_api_key
class CustomerSupportAIAgent: class CustomerSupportAIAgent:
def __init__(self): def __init__(self):
# Initialize Mem0 with Qdrant as the vector store
config = { config = {
"vector_store": { "vector_store": {
"provider": "qdrant", "provider": "qdrant",
"config": { "config": {
"model": "gpt-4o-mini",
"host": "localhost", "host": "localhost",
"port": 6333, "port": 6333,
} }
}, },
} }
self.memory = Memory.from_config(config) try:
self.memory = Memory.from_config(config)
except Exception as e:
st.error(f"Failed to initialize memory: {e}")
st.stop() # Stop execution if memory initialization fails
self.client = OpenAI() self.client = OpenAI()
self.app_id = "customer-support" self.app_id = "customer-support"
def handle_query(self, query, user_id=None): def handle_query(self, query, user_id=None):
relevant_memories = self.memory.search(query=query, user_id=user_id) try:
context = "Relevant past information:\n" # Search for relevant memories
if relevant_memories and "results" in relevant_memories: relevant_memories = self.memory.search(query=query, user_id=user_id)
for memory in relevant_memories["results"]:
if "memory" in memory: # Build context from relevant memories
context += f"- {memory['memory']}\n" context = "Relevant past information:\n"
if relevant_memories and "results" in relevant_memories:
for memory in relevant_memories["results"]:
if "memory" in memory:
context += f"- {memory['memory']}\n"
full_prompt = f"{context}\nCustomer: {query}\nSupport Agent:" # Generate a response using OpenAI
full_prompt = f"{context}\nCustomer: {query}\nSupport Agent:"
response = self.client.chat.completions.create(
model="gpt-4",
messages=[
{"role": "system", "content": "You are a customer support AI agent for TechGadgets.com, an online electronics store."},
{"role": "user", "content": full_prompt}
]
)
answer = response.choices[0].message.content
response = self.client.chat.completions.create( # Add the query and answer to memory
model="gpt-4o-mini", self.memory.add(query, user_id=user_id, metadata={"app_id": self.app_id, "role": "user"})
messages=[ self.memory.add(answer, user_id=user_id, metadata={"app_id": self.app_id, "role": "assistant"})
{"role": "system", "content": "You are a customer support AI agent for TechGadgets.com, an online electronics store."},
{"role": "user", "content": full_prompt}
]
)
answer = response.choices[0].message.content
self.memory.add(query, user_id=user_id, metadata={"app_id": self.app_id, "role": "user"}) return answer
self.memory.add(answer, user_id=user_id, metadata={"app_id": self.app_id, "role": "assistant"}) except Exception as e:
st.error(f"An error occurred while handling the query: {e}")
return answer return "Sorry, I encountered an error. Please try again later."
def get_memories(self, user_id=None): def get_memories(self, user_id=None):
return self.memory.get_all(user_id=user_id) try:
# Retrieve all memories for a user
return self.memory.get_all(user_id=user_id)
except Exception as e:
st.error(f"Failed to retrieve memories: {e}")
return None
def generate_synthetic_data(self, user_id): def generate_synthetic_data(self, user_id: str) -> dict | None:
today = datetime.now() try:
order_date = (today - timedelta(days=10)).strftime("%B %d, %Y") today = datetime.now()
expected_delivery = (today + timedelta(days=2)).strftime("%B %d, %Y") order_date = (today - timedelta(days=10)).strftime("%B %d, %Y")
expected_delivery = (today + timedelta(days=2)).strftime("%B %d, %Y")
prompt = f"""Generate a detailed customer profile and order history for a TechGadgets.com customer with ID {user_id}. Include: prompt = f"""Generate a detailed customer profile and order history for a TechGadgets.com customer with ID {user_id}. Include:
1. Customer name and basic info 1. Customer name and basic info
2. A recent order of a high-end electronic device (placed on {order_date}, to be delivered by {expected_delivery}) 2. A recent order of a high-end electronic device (placed on {order_date}, to be delivered by {expected_delivery})
3. Order details (product, price, order number) 3. Order details (product, price, order number)
4. Customer's shipping address 4. Customer's shipping address
5. 2-3 previous orders from the past year 5. 2-3 previous orders from the past year
6. 2-3 customer service interactions related to these orders 6. 2-3 customer service interactions related to these orders
7. Any preferences or patterns in their shopping behavior 7. Any preferences or patterns in their shopping behavior
Format the output as a JSON object.""" Format the output as a JSON object."""
response = self.client.chat.completions.create( response = self.client.chat.completions.create(
model="gpt-4o-mini", model="gpt-4",
messages=[ messages=[
{"role": "system", "content": "You are a data generation AI that creates realistic customer profiles and order histories. Always respond with valid JSON."}, {"role": "system", "content": "You are a data generation AI that creates realistic customer profiles and order histories. Always respond with valid JSON."},
{"role": "user", "content": prompt} {"role": "user", "content": prompt}
], ]
response_format={"type": "json_object"} )
)
customer_data = json.loads(response.choices[0].message.content) customer_data = json.loads(response.choices[0].message.content)
# Add generated data to memory # Add generated data to memory
for key, value in customer_data.items(): for key, value in customer_data.items():
if isinstance(value, list): if isinstance(value, list):
for item in value: for item in value:
self.memory.add(json.dumps(item), user_id=user_id, metadata={"app_id": self.app_id, "role": "system"}) self.memory.add(
else: json.dumps(item),
self.memory.add(f"{key}: {json.dumps(value)}", user_id=user_id, metadata={"app_id": self.app_id, "role": "system"}) user_id=user_id,
metadata={"app_id": self.app_id, "role": "system"}
)
else:
self.memory.add(
f"{key}: {json.dumps(value)}",
user_id=user_id,
metadata={"app_id": self.app_id, "role": "system"}
)
return customer_data return customer_data
except Exception as e:
st.error(f"Failed to generate synthetic data: {e}")
return None
# Initialize the CustomerSupportAIAgent # Initialize the CustomerSupportAIAgent
support_agent = CustomerSupportAIAgent() support_agent = CustomerSupportAIAgent()
@ -113,7 +142,10 @@ if openai_api_key:
if customer_id: if customer_id:
with st.spinner("Generating customer data..."): with st.spinner("Generating customer data..."):
st.session_state.customer_data = support_agent.generate_synthetic_data(customer_id) st.session_state.customer_data = support_agent.generate_synthetic_data(customer_id)
st.sidebar.success("Synthetic data generated successfully!") if st.session_state.customer_data:
st.sidebar.success("Synthetic data generated successfully!")
else:
st.sidebar.error("Failed to generate synthetic data.")
else: else:
st.sidebar.error("Please enter a customer ID first.") st.sidebar.error("Please enter a customer ID first.")
@ -156,7 +188,8 @@ if openai_api_key:
st.markdown(query) st.markdown(query)
# Generate and display response # Generate and display response
answer = support_agent.handle_query(query, user_id=customer_id) with st.spinner("Generating response..."):
answer = support_agent.handle_query(query, user_id=customer_id)
# Add assistant response to chat history # Add assistant response to chat history
st.session_state.messages.append({"role": "assistant", "content": answer}) st.session_state.messages.append({"role": "assistant", "content": answer})