t66_langmem/populate_test_data.py

#!/usr/bin/env python3
"""
Populate LangMem with test data for Supabase web UI viewing
"""

import asyncio
import httpx
import json
from datetime import datetime

# Configuration
API_BASE_URL = "http://localhost:8765"
API_KEY = "langmem_api_key_2025"

# Test memories to store
test_memories = [
    {
        "content": "Claude Code is an AI-powered CLI tool that helps with software development tasks. It can read files, search codebases, and generate code.",
        "user_id": "demo_user",
        "session_id": "demo_session_1",
        "metadata": {
            "category": "tools",
            "subcategory": "ai_development",
            "importance": "high",
            "tags": ["claude", "ai", "cli", "development"]
        }
    },
    {
        "content": "FastAPI is a modern, fast web framework for building APIs with Python. It provides automatic API documentation and type hints.",
        "user_id": "demo_user", 
        "session_id": "demo_session_1",
        "metadata": {
            "category": "frameworks",
            "subcategory": "python_web",
            "importance": "medium",
            "tags": ["fastapi", "python", "web", "api"]
        }
    },
    {
        "content": "Docker containers provide lightweight virtualization for applications. They package software with all dependencies for consistent deployment.",
        "user_id": "demo_user",
        "session_id": "demo_session_2", 
        "metadata": {
            "category": "devops",
            "subcategory": "containerization",
            "importance": "high",
            "tags": ["docker", "containers", "devops", "deployment"]
        }
    },
    {
        "content": "PostgreSQL with pgvector extension enables vector similarity search for embeddings. This is useful for semantic search and AI applications.",
        "user_id": "demo_user",
        "session_id": "demo_session_2",
        "metadata": {
            "category": "databases",
            "subcategory": "vector_search",
            "importance": "high", 
            "tags": ["postgresql", "pgvector", "embeddings", "search"]
        }
    },
    {
        "content": "N8N is an open-source workflow automation tool that connects different services and APIs. It provides a visual interface for building workflows.",
        "user_id": "demo_user",
        "session_id": "demo_session_3",
        "metadata": {
            "category": "automation",
            "subcategory": "workflow_tools",
            "importance": "medium",
            "tags": ["n8n", "automation", "workflow", "integration"]
        }
    },
    {
        "content": "Ollama runs large language models locally on your machine. It supports models like Llama, Mistral, and provides embedding capabilities.",
        "user_id": "demo_user",
        "session_id": "demo_session_3",
        "metadata": {
            "category": "ai",
            "subcategory": "local_models",
            "importance": "high",
            "tags": ["ollama", "llm", "local", "embeddings"]
        }
    },
    {
        "content": "Supabase is an open-source Firebase alternative that provides database, authentication, and real-time subscriptions with PostgreSQL.",
        "user_id": "demo_user",
        "session_id": "demo_session_4",
        "metadata": {
            "category": "backend",
            "subcategory": "baas",
            "importance": "medium",
            "tags": ["supabase", "database", "authentication", "backend"]
        }
    },
    {
        "content": "Neo4j is a graph database that stores data as nodes and relationships. It's excellent for modeling complex relationships and network data.",
        "user_id": "demo_user",
        "session_id": "demo_session_4",
        "metadata": {
            "category": "databases",
            "subcategory": "graph_database",
            "importance": "medium",
            "tags": ["neo4j", "graph", "relationships", "cypher"]
        }
    }
]

async def store_test_memories():
    """Store test memories in LangMem API"""
    print("🧪 Populating LangMem with test data...")
    print("=" * 50)
    
    headers = {"Authorization": f"Bearer {API_KEY}"}
    
    async with httpx.AsyncClient() as client:
        stored_memories = []
        
        for i, memory in enumerate(test_memories, 1):
            try:
                print(f"\n{i}. Storing: {memory['content'][:50]}...")
                
                response = await client.post(
                    f"{API_BASE_URL}/v1/memories/store",
                    json=memory,
                    headers=headers,
                    timeout=30.0
                )
                
                if response.status_code == 200:
                    data = response.json()
                    stored_memories.append(data)
                    print(f"   ✅ Stored with ID: {data['id']}")
                else:
                    print(f"   ❌ Failed: {response.status_code}")
                    print(f"   Response: {response.text}")
                    
            except Exception as e:
                print(f"   ❌ Error: {e}")
        
        print(f"\n🎉 Successfully stored {len(stored_memories)} memories!")
        print("\n📊 Summary:")
        print(f"   - Total memories: {len(stored_memories)}")
        print(f"   - User: demo_user")
        print(f"   - Sessions: {len(set(m['session_id'] for m in test_memories))}")
        print(f"   - Categories: {len(set(m['metadata']['category'] for m in test_memories))}")
        
        # Test search functionality
        print("\n🔍 Testing search functionality...")
        search_tests = [
            "Python web development",
            "AI and machine learning",
            "Database and storage",
            "Docker containers"
        ]
        
        for query in search_tests:
            try:
                response = await client.post(
                    f"{API_BASE_URL}/v1/memories/search",
                    json={
                        "query": query,
                        "user_id": "demo_user",
                        "limit": 3,
                        "threshold": 0.5
                    },
                    headers=headers,
                    timeout=30.0
                )
                
                if response.status_code == 200:
                    data = response.json()
                    print(f"   Query: '{query}' -> {data['total_count']} results")
                    for memory in data['memories']:
                        print(f"     - {memory['content'][:40]}... ({memory['similarity']:.3f})")
                else:
                    print(f"   Query: '{query}' -> Failed ({response.status_code})")
                    
            except Exception as e:
                print(f"   Query: '{query}' -> Error: {e}")
        
        print("\n✅ Test data population complete!")
        print("   You can now view the memories in Supabase web UI:")
        print("   - Table: langmem_documents")
        print("   - URL: http://localhost:8000")

if __name__ == "__main__":
    asyncio.run(store_test_memories())