Multi-Modal Content Processing with strands agent and FAISS Memory

import boto3
from strands.models import BedrockModel
from strands import Agent
from strands_tools import image_reader, file_read, mem0_memory, use_llm
from video_reader import video_reader

# Enhanced system prompt with memory instructions
MULTIMODAL_SYSTEM_PROMPT = """ You are a helpful assistant that can process documents, images, and videos. 
Analyze their contents and provide relevant information. You have memory capabilities and can remember previous interactions.

You can:
1. For PNG, JPEG/JPG, GIF, or WebP formats use image_reader to process file
2. For PDF, csv, docx, xls or xlsx formats use file_read to process file  
3. For MP4, MOV, AVI, MKV, WebM formats use video_reader to process file
4. Just deliver the answer

Memory capabilities:
- Store new information using mem0_memory tool (action="store")
- Retrieve relevant memories (action="retrieve")
- List all memories (action="list")
- Provide personalized responses

Key Rules:
- Always include user_id={USER_ID} in tool calls
- Be conversational and natural in responses
- Format output clearly
- Acknowledge stored information
- Reference relevant past interactions when appropriate
"""

# Configure Amazon Bedrock
session = boto3.Session(region_name='us-west-2')
bedrock_model = BedrockModel(
    model_id="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
    boto_session=session,
    streaming=False
)

# Create enhanced agent with memory capabilities
multimodal_agent = Agent(
    system_prompt=MULTIMODAL_SYSTEM_PROMPT,
    tools=[image_reader, file_read, video_reader, mem0_memory, use_llm],
    model=bedrock_model,
)

USER_ID = "eli_abc"  # Generate a unique user ID
content = """Hello, my name is Elizabeth, but they call me Eli. I'm a developer advocate at AWS, 
and I want to understand what's in images, videos, and documents to improve my day-to-day work."""

# Store user context in memory
multimodal_agent.tool.mem0_memory(action="store", content=content, user_id=USER_ID)

print("=== 📸 IMAGE ANALYSIS WITH MEMORY ===")
image_result = multimodal_agent(
    f"Analyze the image data-sample/diagram.jpg in detail and describe everything you observe. "
    f"Remember this information for later. USER_ID: {USER_ID}"
)
print(image_result)


print("=== 🎬 VIDEO ANALYSIS WITH MEMORY ===")
video_result = multimodal_agent(
    "Analyze the video data-sample/moderation-video.mp4 and describe in detail "
    "the actions and scenes you observe. Store this information in your memory."
)
print(video_result)

print("=== 📄 DOCUMENT ANALYSIS WITH MEMORY ===")
doc_result = multimodal_agent(
    "Summarize as json the content of the document data-sample/Welcome-Strands-Agents-SDK.pdf "
    "and store this information in your memory."
)
print(doc_result)

# Retrieve memories related to a specific query
retrieved_memories = multimodal_agent.tool.mem0_memory(
    action="retrieve", 
    query="What services are in the image?", 
    user_id=USER_ID
)
print("Retrieved Memories:", retrieved_memories)


# List all stored memories for the user
all_memories = multimodal_agent.tool.mem0_memory(
    action="list", 
    user_id=USER_ID
)
print("All Stored Memories:", all_memories)}


print("=== 🧠 MEMORY RECALL TEST ===")
memory_result = multimodal_agent(
    "What do you remember about the image, video, and document I showed you earlier?"
)
print(memory_result)


git clone https://github.com/elizabethfuentes12/strands-agent-samples)
cd notebook

pip install -r requirements.txt