#i have set up elevenlabs api agent and it initiates my conversation but its not receiving my conver
warm phoenix
conversation = Conversation(
client=client,
agent_id=AGENT_ID,
requires_auth=bool(API_KEY),
audio_interface=DefaultAudioInterface(),
callback_agent_response=lambda response: print(f"Agent: {response}"),
callback_agent_response_correction=lambda original, corrected: print(f"Agent: {original} -> {corrected}"),
callback_user_transcript=lambda transcript: print(f"User: {transcript}"),
callback_latency_measurement=lambda latency: print(f"Latency: {latency}ms"),
)
#Start the conversation session
#def start_conversation():
#print("Starting conversation...")
conversation.start_session()
# Example of custom function calling during the session
while True:
try:
user_input = input("You: ")
if user_input.lower() == "exit":
break
# Call the custom function
custom_response = custom_function_calling(user_input)
print(f"Custom Function Response: {custom_response}")
except KeyboardInterrupt:
break
safe runeBOT
warm phoenix
im not using websocket connection im using python sdk
safe runeBOT
warm phoenix
api
safe runeBOT
warm phoenix
the following is what i have set up. def start_conversation():
print("Starting conversation...")
conversation.start_session()
# Example of custom function calling during the session
while True:
try:
user_input = input("You: ")
if user_input.lower() == "exit":
break
# Call the custom function
custom_response = custom_function_calling(user_input)
print(f"Custom Function Response: {custom_response}")
except KeyboardInterrupt:
break
# End the session gracefully
conversation.end_session()
print("Conversation ended.")
if name == "main":
start_conversation()
safe runeBOT
warm phoenix
is websocket api better thaan python sdk for function calling lopcally
safe runeBOT
warm phoenix
im trying to have a conversation with the agent though the pyaudio default interface to control selenium
safe runeBOT
warm phoenix
does this following code sem right for using the audio interface in the conversation: def start_conversation():
print("Starting conversation...")
conversation.start_session()
# Example of custom function calling during the session
while True:
try:
user_input = input("You: ")
if user_input.lower() == "exit":
break
# Capture and send audio data
encoded_audio = capture_audio()
conversation.send_audio(encoded_audio)
# Call the custom function
custom_response = custom_function_calling(user_input)
print(f"Custom Function Response: {custom_response}")
im not using keyboard input i am using audio.
safe runeBOT
warm phoenix
so what do i need to change in the following to have the audio audio conversation responses dictate the custom function calls.: conversation = Conversation(
client=client,
agent_id=AGENT_ID,
requires_auth=bool(API_KEY),
audio_interface=DefaultAudioInterface(),
callback_agent_response=lambda response: print(f"Agent: {response}"),
callback_agent_response_correction=lambda original, corrected: print(f"Agent: {original} -> {corrected}"),
callback_user_transcript=lambda transcript: print(f"User: {transcript}"),
callback_latency_measurement=lambda latency: print(f"Latency: {latency}ms"),
)
Start the conversation session
def start_conversation():
print("Starting conversation...")
conversation.start_session()
# Example of custom function calling during the session
while True:
try:
user_input = input("You: ")
if user_input.lower() == "exit":
break
# Call the custom function
custom_response = custom_function_calling(user_input)
print(f"Custom Function Response: {custom_response}")
except KeyboardInterrupt:
break
# End the session gracefully
conversation.end_session()
print("Conversation ended.")
Handle SIGINT (Ctrl+C) to end the conversation gracefully
signal.signal(signal.SIGINT, lambda sig, frame:
conversation.end_session())
if name == "main":
start_conversation()
safe runeBOT
warm phoenix
how do i set custom function calling so that llm in the agent can determine the client response
safe runeBOT
warm phoenix
okay, how can i restructure the following example to extract the city from the response of the client and call the function perform_city_search
safe runeBOT
warm phoenix
def custom_function_calling(user_input):
global driver # Ensure the driver instance is accessible
if "search city" in user_input.lower():
# Extract the city name from the user input
city_name = user_input.lower().replace("search city", "").strip()
if not city_name:
return "Please specify a city name to search."
# Call the perform_city_search function and return the results
result = perform_city_search(city_name)
if "error" in result:
return f"Error: {result['error']}"
else:
# Format the results for user readability
rates = result.get("rates", [])
if not rates:
return f"No rates found for {city_name}."
response = f"Found {len(rates)} rates for {city_name}:\n"
for rate in rates:
response += f"Hotel ID: {rate['hotel_id']}, Description: {rate['description']}, Price: {rate['price']}\n"
return response
else:
return "Invalid input. To perform a search, use the format: 'search city <city name>'."
yes, i would like to adjust the input decision making to be handled by the llm in my agents set up. do i do this in my agent dashboard?
safe runeBOT
warm phoenix
if im using the sdk i dotn have to use the tool in my agent dashboard correct?
safe runeBOT
warm phoenix
this is great, how would that look for the following : def custom_function_calling(user_input):
global driver # Ensure the driver instance is accessible
if "search city" in user_input.lower():
# Extract the city name from the user input
city_name = user_input.lower().replace("search city", "").strip()
if not city_name:
return "Please specify a city name to search."
# Call the perform_city_search function and return the results
result = perform_city_search(city_name)
if "error" in result:
return f"Error: {result['error']}"
else:
# Format the results for user readability
rates = result.get("rates", [])
if not rates:
return f"No rates found for {city_name}."
response = f"Found {len(rates)} rates for {city_name}:\n"
for rate in rates:
response += f"Hotel ID: {rate['hotel_id']}, Description: {rate['description']}, Price: {rate['price']}\n"
return response