Skip to main content

Memory Approaches Comparison Demo

Complete Application

This is a complete, runnable application demonstrating Atulya integration. View source on GitHub →

Interactive Streamlit app comparing three memory approaches for LLM applications:

  1. No Memory - Each query is independent (baseline)
  2. Full Conversation History - Pass entire conversation (truncated to simulate context limits)
  3. Atulya Memory - Intelligent semantic memory retrieval

This demo showcases how Atulya's semantic memory outperforms traditional approaches, especially as conversations grow longer.

Quick Start​

# 1. Set your OpenAI API key
export OPENAI_API_KEY=your-key

# 2. Start Atulya server
docker run -d -p 8888:8888 -p 9999:9999 \
  -e ATULYA_API_LLM_PROVIDER=openai \
  -e ATULYA_API_LLM_API_KEY=$OPENAI_API_KEY \
  ghcr.io/eight-atulya/atulya:latest

# 3. Run the demo
./run.sh

Then open http://localhost:8501 in your browser.

What This Demo Shows​

The Problem with Traditional Approaches​

ApproachHow it WorksLimitation
No MemoryEach query standaloneForgets everything between messages
Full HistoryPass all messages to LLMToken limits cause truncation - loses early context
AtulyaSemantic retrieval of relevant factsRetrieves what's relevant regardless of when it was said

Key Insight​

After 5-10 messages, watch the Full Conversation History column start losing early context due to truncation (artificially set to 4 messages to demonstrate this quickly). Meanwhile, Atulya Memory can still recall facts from the beginning because it uses semantic retrieval rather than sequential history.

Testing the Demo​

  1. Introduce yourself:

    • "Hi, I'm Sarah, a data scientist at Netflix"
    • "I prefer Python and love machine learning"

  2. Have several exchanges about different topics

  3. Test recall:

    • "What programming language should I use?"
    • "What do you know about me?"

Watch how the three columns respond differently as the conversation grows.

Features​

  • Side-by-side comparison of all three approaches
  • Debug panels showing what context each approach uses
  • Memory explorer to search Atulya memories directly
  • Configurable settings for history truncation, max memories, etc.
  • Multi-provider support via LiteLLM (OpenAI, Anthropic, Groq)

Prerequisites​

  • Python 3.10+
  • Atulya server running (Docker recommended)
  • At least one LLM API key (OpenAI recommended)

Setup​

# Set API key
export OPENAI_API_KEY=your-key

# Start Atulya, then run:
./run.sh

The script will check and install dependencies automatically.

Manual Setup​

# Install dependencies
pip install streamlit litellm

# Install Atulya packages
pip install atulya-client atulya-litellm

# Run the app
streamlit run app.py

Starting Atulya Server​

docker run -d -p 8888:8888 -p 9999:9999 \
  -e ATULYA_API_LLM_PROVIDER=openai \
  -e ATULYA_API_LLM_API_KEY=$OPENAI_API_KEY \
  ghcr.io/eight-atulya/atulya:latest

# Verify it's running
curl http://localhost:8888/health

Configuration​

Model Selection:

  • Provider: OpenAI, Anthropic, Groq
  • Model: Various models per provider
  • Custom model ID support

Full History Config:

  • Max Messages to Keep (default: 4 to demonstrate truncation)

Atulya Config:

  • API URL (default: http://localhost:8888)
  • Bank ID and Entity ID for memory isolation
  • Max Memories to retrieve
  • Recall Budget (low/mid/high)

Generation Settings:

  • Temperature
  • Max Tokens
  • System Prompt

Supported Models​

OpenAI​

  • gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-4, gpt-3.5-turbo

Anthropic​

  • claude-3-5-sonnet-20241022, claude-3-5-haiku-20241022
  • claude-3-opus-20240229, claude-3-sonnet-20240229

Groq​

  • groq/llama-3.1-70b-versatile, groq/llama-3.1-8b-instant
  • groq/mixtral-8x7b-32768

Environment Variables​

# Required
export OPENAI_API_KEY=sk-...

# Optional (for other providers)
export ANTHROPIC_API_KEY=sk-ant-...
export GROQ_API_KEY=gsk_...

# Optional
export ATULYA_URL=http://localhost:8888

Troubleshooting​

Atulya server not responding​

# Check if running
curl http://localhost:8888/health

# Start with Docker
docker run -d -p 8888:8888 -p 9999:9999 \
  -e ATULYA_API_LLM_PROVIDER=openai \
  -e ATULYA_API_LLM_API_KEY=$OPENAI_API_KEY \
  ghcr.io/eight-atulya/atulya:latest

atulya-litellm not installed​

pip install atulya-litellm

API key errors​

Make sure the appropriate API key is set:

export OPENAI_API_KEY=your-key

License​

MIT