Added improved docs index and overview pages and quickstart (#3603)
This commit is contained in:
Parth Sharma
@@ -1,6 +1,6 @@
|
||||
---
|
||||
title: 'Mem0 with OpenAI Agents SDK for Voice'
|
||||
description: 'Integrate memory capabilities into your voice agents using Mem0 and OpenAI Agents SDK'
|
||||
title: "Mem0 with OpenAI Agents SDK for Voice"
|
||||
description: "Integrate memory capabilities into your voice agents using Mem0 and OpenAI Agents SDK"
|
||||
---
|
||||
|
||||
# Building Voice Agents with Memory using Mem0 and OpenAI Agents SDK
|
||||
@@ -12,16 +12,19 @@ This guide demonstrates how to combine OpenAI's Agents SDK for voice application
|
||||
Before you begin, make sure you have:
|
||||
|
||||
1. Installed OpenAI Agents SDK with voice dependencies:
|
||||
|
||||
```bash
|
||||
pip install 'openai-agents[voice]'
|
||||
```
|
||||
|
||||
2. Installed Mem0 SDK:
|
||||
|
||||
```bash
|
||||
pip install mem0ai
|
||||
```
|
||||
|
||||
3. Installed other required dependencies:
|
||||
|
||||
```bash
|
||||
pip install numpy sounddevice pydantic
|
||||
```
|
||||
@@ -64,6 +67,7 @@ mem0_client = AsyncMemoryClient()
|
||||
```
|
||||
|
||||
This section handles:
|
||||
|
||||
- Importing required modules from OpenAI Agents SDK and Mem0
|
||||
- Setting up environment variables for API keys
|
||||
- Defining a simple user identification system (using a global variable)
|
||||
@@ -94,7 +98,7 @@ async def save_memories(
|
||||
"""Store a user memory in memory."""
|
||||
# This will be visible in your console
|
||||
logger.debug(f"Saving memory: {memory} for user {USER_ID}")
|
||||
|
||||
|
||||
# Store the preference in Mem0
|
||||
memory_content = f"User memory - {memory}"
|
||||
await mem0_client.add(
|
||||
@@ -106,6 +110,7 @@ async def save_memories(
|
||||
```
|
||||
|
||||
This function:
|
||||
|
||||
- Takes a memory string
|
||||
- Creates a formatted memory string
|
||||
- Stores it in Mem0 using the `add()` method
|
||||
@@ -132,16 +137,17 @@ async def search_memories(
|
||||
threshold=0.7, # Higher threshold for more relevant results
|
||||
output_format="v1.1"
|
||||
)
|
||||
|
||||
|
||||
# Format and return the results
|
||||
if not results.get('results', []):
|
||||
return "I don't have any relevant memories about this topic."
|
||||
|
||||
|
||||
memories = [f"• {result['memory']}" for result in results.get('results', [])]
|
||||
return "Here's what I remember that might be relevant:\n" + "\n".join(memories)
|
||||
```
|
||||
|
||||
This tool:
|
||||
|
||||
- Takes a search query string
|
||||
- Passes it to Mem0's semantic search to find related memories
|
||||
- Sets a threshold for relevance to ensure quality results
|
||||
@@ -165,11 +171,12 @@ def create_memory_voice_agent():
|
||||
model="gpt-4.1-nano-2025-04-14",
|
||||
tools=[save_memories, search_memories],
|
||||
)
|
||||
|
||||
|
||||
return agent
|
||||
```
|
||||
|
||||
This function:
|
||||
|
||||
- Creates an OpenAI Agent with specific instructions
|
||||
- Configures it to use gpt-4.1-nano (you can use other models)
|
||||
- Registers the memory-related tools with the agent
|
||||
@@ -181,24 +188,25 @@ This function:
|
||||
async def record_from_microphone(duration=5, samplerate=24000):
|
||||
"""Record audio from the microphone for a specified duration."""
|
||||
print(f"Recording for {duration} seconds...")
|
||||
|
||||
|
||||
# Create a buffer to store the recorded audio
|
||||
frames = []
|
||||
|
||||
|
||||
# Callback function to store audio data
|
||||
def callback(indata, frames_count, time_info, status):
|
||||
frames.append(indata.copy())
|
||||
|
||||
|
||||
# Start recording
|
||||
with sd.InputStream(samplerate=samplerate, channels=1, callback=callback, dtype=np.int16):
|
||||
await asyncio.sleep(duration)
|
||||
|
||||
|
||||
# Combine all frames into a single numpy array
|
||||
audio_data = np.concatenate(frames)
|
||||
return audio_data
|
||||
```
|
||||
|
||||
This function:
|
||||
|
||||
- Creates a simple asynchronous microphone recording function
|
||||
- Uses the sounddevice library to capture audio input
|
||||
- Stores frames in a buffer during recording
|
||||
@@ -211,16 +219,16 @@ This function:
|
||||
async def main():
|
||||
# Create the agent
|
||||
agent = create_memory_voice_agent()
|
||||
|
||||
|
||||
# Set up the voice pipeline
|
||||
pipeline = VoicePipeline(
|
||||
workflow=SingleAgentVoiceWorkflow(agent)
|
||||
)
|
||||
|
||||
|
||||
# Configure TTS settings
|
||||
pipeline.config.tts_settings.voice = "alloy"
|
||||
pipeline.config.tts_settings.speed = 1.0
|
||||
|
||||
|
||||
try:
|
||||
while True:
|
||||
# Get user input
|
||||
@@ -228,19 +236,19 @@ async def main():
|
||||
user_input = input()
|
||||
if user_input.lower() == 'q':
|
||||
break
|
||||
|
||||
|
||||
# Record and process audio
|
||||
audio_data = await record_from_microphone(duration=5)
|
||||
audio_input = AudioInput(buffer=audio_data)
|
||||
result = await pipeline.run(audio_input)
|
||||
|
||||
|
||||
# Play response and handle events
|
||||
player = sd.OutputStream(samplerate=24000, channels=1, dtype=np.int16)
|
||||
player.start()
|
||||
|
||||
|
||||
agent_response = ""
|
||||
print("\nAgent response:")
|
||||
|
||||
|
||||
async for event in result.stream():
|
||||
if event.type == "voice_stream_event_audio":
|
||||
player.write(event.data)
|
||||
@@ -248,23 +256,24 @@ async def main():
|
||||
content = event.data
|
||||
agent_response += content
|
||||
print(content, end="", flush=True)
|
||||
|
||||
|
||||
# Save the agent's response to memory
|
||||
if agent_response:
|
||||
try:
|
||||
await mem0_client.add(
|
||||
f"Agent response: {agent_response}",
|
||||
f"Agent response: {agent_response}",
|
||||
user_id=USER_ID,
|
||||
metadata={"type": "agent_response"}
|
||||
)
|
||||
except Exception as e:
|
||||
print(f"Failed to store memory: {e}")
|
||||
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("\nExiting...")
|
||||
```
|
||||
|
||||
This main function orchestrates the entire process:
|
||||
|
||||
1. Creates the memory-enabled voice agent
|
||||
2. Sets up the voice pipeline with TTS settings
|
||||
3. Implements an interactive loop for recording and processing voice input
|
||||
@@ -348,11 +357,11 @@ async def search_memories(
|
||||
threshold=0.7, # Higher threshold for more relevant results
|
||||
output_format="v1.1"
|
||||
)
|
||||
|
||||
|
||||
# Format and return the results
|
||||
if not results.get('results', []):
|
||||
return "I don't have any relevant memories about this topic."
|
||||
|
||||
|
||||
memories = [f"• {result['memory']}" for result in results.get('results', [])]
|
||||
return "Here's what I remember that might be relevant:\n" + "\n".join(memories)
|
||||
|
||||
@@ -372,43 +381,43 @@ def create_memory_voice_agent():
|
||||
model="gpt-4.1-nano-2025-04-14",
|
||||
tools=[save_memories, search_memories],
|
||||
)
|
||||
|
||||
|
||||
return agent
|
||||
|
||||
async def record_from_microphone(duration=5, samplerate=24000):
|
||||
"""Record audio from the microphone for a specified duration."""
|
||||
print(f"Recording for {duration} seconds...")
|
||||
|
||||
|
||||
# Create a buffer to store the recorded audio
|
||||
frames = []
|
||||
|
||||
|
||||
# Callback function to store audio data
|
||||
def callback(indata, frames_count, time_info, status):
|
||||
frames.append(indata.copy())
|
||||
|
||||
|
||||
# Start recording
|
||||
with sd.InputStream(samplerate=samplerate, channels=1, callback=callback, dtype=np.int16):
|
||||
await asyncio.sleep(duration)
|
||||
|
||||
|
||||
# Combine all frames into a single numpy array
|
||||
audio_data = np.concatenate(frames)
|
||||
return audio_data
|
||||
|
||||
async def main():
|
||||
print("Starting Memory Voice Agent")
|
||||
|
||||
|
||||
# Create the agent and context
|
||||
agent = create_memory_voice_agent()
|
||||
|
||||
|
||||
# Set up the voice pipeline
|
||||
pipeline = VoicePipeline(
|
||||
workflow=SingleAgentVoiceWorkflow(agent)
|
||||
)
|
||||
|
||||
|
||||
# Configure TTS settings
|
||||
pipeline.config.tts_settings.voice = "alloy"
|
||||
pipeline.config.tts_settings.speed = 1.0
|
||||
|
||||
|
||||
try:
|
||||
while True:
|
||||
# Get user input
|
||||
@@ -416,23 +425,23 @@ async def main():
|
||||
user_input = input()
|
||||
if user_input.lower() == 'q':
|
||||
break
|
||||
|
||||
|
||||
# Record and process audio
|
||||
audio_data = await record_from_microphone(duration=5)
|
||||
audio_input = AudioInput(buffer=audio_data)
|
||||
|
||||
|
||||
print("Processing your request...")
|
||||
|
||||
|
||||
# Process the audio input
|
||||
result = await pipeline.run(audio_input)
|
||||
|
||||
|
||||
# Create an audio player
|
||||
player = sd.OutputStream(samplerate=24000, channels=1, dtype=np.int16)
|
||||
player.start()
|
||||
|
||||
|
||||
# Store the agent's response for adding to memory
|
||||
agent_response = ""
|
||||
|
||||
|
||||
print("\nAgent response:")
|
||||
# Play the audio stream as it comes in
|
||||
async for event in result.stream():
|
||||
@@ -443,20 +452,20 @@ async def main():
|
||||
content = event.data
|
||||
agent_response += content
|
||||
print(content, end="", flush=True)
|
||||
|
||||
|
||||
print("\n")
|
||||
|
||||
|
||||
# Example of saving the conversation to Mem0 after completion
|
||||
if agent_response:
|
||||
try:
|
||||
await mem0_client.add(
|
||||
f"Agent response: {agent_response}",
|
||||
f"Agent response: {agent_response}",
|
||||
user_id=USER_ID,
|
||||
metadata={"type": "agent_response"}
|
||||
)
|
||||
except Exception as e:
|
||||
print(f"Failed to store memory: {e}")
|
||||
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("\nExiting...")
|
||||
|
||||
@@ -486,7 +495,7 @@ To run this example:
|
||||
|
||||
1. Replace the placeholder API keys with your actual keys
|
||||
2. Make sure your microphone is properly connected
|
||||
3. Run the script with Python 3.8 or newer
|
||||
3. Run the script with Python 3.10 or newer
|
||||
4. Press Enter to start recording, then speak your request
|
||||
5. Press 'q' to quit the application
|
||||
|
||||
@@ -533,6 +542,6 @@ async def save_memories(
|
||||
"""Store a user memory in memory."""
|
||||
# This will be visible in your console
|
||||
logger.debug(f"Saving memory: {memory} for user {USER_ID}")
|
||||
|
||||
|
||||
# Rest of your function...
|
||||
```
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user