references updated for qdrant

.env.example

@@ -5,11 +5,9 @@ OPENAI_BASE_URL=https://your-openai-compatible-endpoint.com/v1
 EMBEDDER_API_KEY=AIzaSy-your-google-gemini-api-key-here
 
 # Database Configuration
-POSTGRES_DB=mem0_db
-POSTGRES_USER=mem0_user
-POSTGRES_PASSWORD=mem0_password
-POSTGRES_HOST=postgres
-POSTGRES_PORT=5432
+QDRANT_HOST=qdrant
+QDRANT_PORT=6333
+QDRANT_COLLECTION_NAME=mem0
 
 # Neo4j Configuration
 NEO4J_AUTH=neo4j/mem0_neo4j_password
@@ -36,4 +34,5 @@ EXPERT_MODEL=o3                      # Expert-level comprehensive analysis
 # - Ensure all models are available on your OpenAI-compatible endpoint
 # - Verify model availability: curl -H "Authorization: Bearer $API_KEY" $BASE_URL/v1/models
 # - Neo4j must be version 5.18+ for vector.similarity.cosine() function
+# - Qdrant vector database for embeddings storage (replaces PostgreSQL+pgvector)
 # - Ollama must be running locally with nomic-embed-text:latest model

README.md

@@ -1,12 +1,12 @@
 # Mem0 Interface - Production Ready
 
-A fully operational Mem0 interface with PostgreSQL and Neo4j integration, featuring intelligent model routing, comprehensive memory management, and production-grade monitoring.
+A fully operational Mem0 interface with Qdrant and Neo4j integration, featuring intelligent model routing, comprehensive memory management, and production-grade monitoring.
 
 ## Features
 
 ### Core Memory System
 - ✅ **Mem0 OSS Integration**: Complete hybrid datastore (Vector + Graph + KV storage)
-- ✅ **PostgreSQL + pgvector**: High-performance vector embeddings storage
+- ✅ **Qdrant**: Purpose-built vector database for high-performance embeddings storage
 - ✅ **Neo4j 5.18**: Graph relationships with native vector similarity functions
 - ✅ **Google Gemini Embeddings**: Enterprise-grade embedding generation
 - ✅ **Memory Operations**: Store, search, update, delete memories with semantic search
@@ -62,7 +62,7 @@ curl http://localhost:8000/health
 ### Core Components
 - **FastAPI Backend**: Production-ready API with comprehensive monitoring
 - **Mem0 OSS**: Hybrid memory management (vector + graph + key-value)
-- **PostgreSQL + pgvector**: Vector embeddings storage and similarity search
+- **Qdrant**: Purpose-built vector database for embeddings storage and similarity search
 - **Neo4j 5.18**: Graph relationships with native vector functions
 - **Google Gemini**: Enterprise-grade embedding generation
 
@@ -203,13 +203,13 @@ curl http://localhost:8000/graph/relationships/alice
 
 ### Service Dependencies
 - **Neo4j**: Must start before backend for vector functions
-- **PostgreSQL**: Required for vector storage initialization
+- **Qdrant**: Required for vector storage initialization
 - **Ollama**: Must be running locally on port 11434
 - **API Endpoint**: Must have valid models available
 
 ## Production Notes
 
-- **Memory Usage**: Neo4j and PostgreSQL require adequate RAM for vector operations
+- **Memory Usage**: Neo4j and Qdrant require adequate RAM for vector operations
 - **API Rate Limits**: Monitor usage on custom endpoint
 - **Data Persistence**: All data stored in Docker volumes
 - **Scaling**: Individual services can be scaled independently

backend/README.md

@@ -9,7 +9,7 @@ A production-ready FastAPI backend that provides intelligent memory integration
 1. **Mem0Manager** (`mem0_manager.py`)
    - Central orchestration of memory operations
    - Integration with custom OpenAI-compatible endpoint
-   - Memory persistence across PostgreSQL and Neo4j
+   - Memory persistence across Qdrant and Neo4j
    - Performance timing and operation tracking
 
 2. **Configuration System** (`config.py`)
@@ -39,8 +39,8 @@ A production-ready FastAPI backend that provides intelligent memory integration
 
 ```
 ┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
-│   PostgreSQL    │    │     Neo4j       │    │  Custom LLM     │
-│   (pgvector)    │    │   (APOC)        │    │   Endpoint      │
+│     Qdrant      │    │     Neo4j       │    │  Custom LLM     │
+│  (Vector DB)    │    │   (APOC)        │    │   Endpoint      │
 ├─────────────────┤    ├─────────────────┤    ├─────────────────┤
 │ • Vector Store  │    │ • Graph Store   │    │ • claude-sonnet-4│
 │ • Embeddings    │    │ • Relationships │    │ • Gemini Embed │
@@ -134,11 +134,9 @@ backend/
 | `OPENAI_COMPAT_API_KEY` | Your custom endpoint API key | - | ✅ |
 | `OPENAI_BASE_URL` | Custom endpoint URL | - | ✅ |
 | `EMBEDDER_API_KEY` | Google Gemini API key for embeddings | - | ✅ |
-| `POSTGRES_HOST` | PostgreSQL host | postgres | ✅ |
-| `POSTGRES_PORT` | PostgreSQL port | 5432 | ✅ |
-| `POSTGRES_DB` | Database name | mem0_db | ✅ |
-| `POSTGRES_USER` | Database user | mem0_user | ✅ |
-| `POSTGRES_PASSWORD` | Database password | - | ✅ |
+| `QDRANT_HOST` | Qdrant vector database host | qdrant | ✅ |
+| `QDRANT_PORT` | Qdrant vector database port | 6333 | ✅ |
+| `QDRANT_COLLECTION_NAME` | Qdrant collection name | mem0 | ✅ |
 | `NEO4J_URI` | Neo4j connection URI | bolt://neo4j:7687 | ✅ |
 | `NEO4J_USERNAME` | Neo4j username | neo4j | ✅ |
 | `NEO4J_PASSWORD` | Neo4j password | - | ✅ |
@@ -283,7 +281,7 @@ docker exec mem0-neo4j cypher-shell -u neo4j -p mem0_neo4j_password \
 
 ### Key Integration Points Verified
 - ✅ **Ollama Embeddings**: nomic-embed-text:latest working for vector generation
-- ✅ **PostgreSQL + pgvector**: Vector storage and similarity search operational  
+- ✅ **Qdrant**: Vector storage and similarity search operational  
 - ✅ **Neo4j 5.18**: Graph relationships and native vector functions working
 - ✅ **Custom LLM Endpoint**: All 4 models accessible and routing correctly
 - ✅ **Memory Persistence**: Data survives container restarts via Docker volumes
@@ -390,7 +388,7 @@ backend:
 #### Dependency Requirements
 - Neo4j 5.18+ (for vector.similarity.cosine function)
 - Ollama running locally with nomic-embed-text:latest
-- PostgreSQL with pgvector extension
+- Qdrant vector database
 - Valid API keys for custom LLM endpoint
 
 ### Debugging Commands

backend/config.py

@@ -10,18 +10,16 @@ class Settings(BaseSettings):
     """Application settings loaded from environment variables."""
     
     # API Configuration
-    openai_api_key: str = Field(..., env="OPENAI_API_KEY")
-    openai_base_url: str = Field(..., env="OPENAI_BASE_URL")
+    openai_api_key: str = Field(..., env="OPENAI_COMPAT_API_KEY")
+    openai_base_url: str = Field(..., env="OPENAI_COMPAT_BASE_URL")
     embedder_api_key: str = Field(..., env="EMBEDDER_API_KEY")
 
     # ollama_base_url: str = Field(..., env="OLLAMA_BASE_URL")
 
     # Database Configuration
-    postgres_host: str = Field("localhost", env="POSTGRES_HOST")
-    postgres_port: int = Field(5432, env="POSTGRES_PORT")
-    postgres_db: str = Field("mem0_db", env="POSTGRES_DB")
-    postgres_user: str = Field("mem0_user", env="POSTGRES_USER")
-    postgres_password: str = Field("mem0_password", env="POSTGRES_PASSWORD")
+    qdrant_host: str = Field("localhost", env="QDRANT_HOST")
+    qdrant_port: int = Field(6333, env="QDRANT_PORT")
+    qdrant_collection_name: str = Field("mem0", env="QDRANT_COLLECTION_NAME")
     
     # Neo4j Configuration
     neo4j_uri: str = Field("bolt://localhost:7687", env="NEO4J_URI")
@@ -35,10 +33,6 @@ class Settings(BaseSettings):
     # Model Configuration - Ultra-minimal (single model)
     default_model: str = Field("claude-sonnet-4", env="DEFAULT_MODEL")
     
-    @property
-    def postgres_url(self) -> str:
-        """Build PostgreSQL connection URL."""
-        return f"postgresql://{self.postgres_user}:{self.postgres_password}@{self.postgres_host}:{self.postgres_port}/{self.postgres_db}"
     
     @property
     def cors_origins_list(self) -> List[str]:

backend/mem0_manager.py

@@ -39,14 +39,13 @@ class Mem0Manager:
                 }
             },
             "vector_store": {
-                "provider": "pgvector",
+                "provider": "qdrant",
                 "config": {
-                    "dbname": settings.postgres_db,
-                    "user": settings.postgres_user,
-                    "password": settings.postgres_password,
-                    "host": settings.postgres_host,
-                    "port": settings.postgres_port,
-                    "embedding_model_dims": 2560
+                    "collection_name": settings.qdrant_collection_name,
+                    "host": settings.qdrant_host,
+                    "port": settings.qdrant_port,
+                    "embedding_model_dims": 2560,
+                    "on_disk": True
                 }
             },
             "graph_store": {

backend/requirements.txt

@@ -9,8 +9,7 @@ openai
 google-genai
 
 # Database
-psycopg2-binary
-pgvector
+qdrant-client
 neo4j
 langchain-neo4j
 rank-bm25

config/postgres-init.sql

@@ -1,66 +0,0 @@
--- Initialize PostgreSQL database for Mem0 with pgvector extension
-
--- Create the pgvector extension for vector operations
-CREATE EXTENSION IF NOT EXISTS vector;
-
--- Create user if not exists (in case it's needed)
-DO
-$do$
-BEGIN
-   IF NOT EXISTS (
-      SELECT FROM pg_catalog.pg_roles
-      WHERE  rolname = 'mem0_user') THEN
-
-      CREATE ROLE mem0_user LOGIN PASSWORD 'mem0_password';
-   END IF;
-END
-$do$;
-
--- Grant necessary permissions
-GRANT ALL PRIVILEGES ON DATABASE mem0_db TO mem0_user;
-GRANT ALL ON SCHEMA public TO mem0_user;
-
--- Create table for vector embeddings (if needed by Mem0's pgvector implementation)
-CREATE TABLE IF NOT EXISTS embeddings (
-    id SERIAL PRIMARY KEY,
-    user_id VARCHAR(255),
-    content TEXT,
-    embedding VECTOR(2560),  -- OpenAI embedding dimension
-    metadata JSONB,
-    created_at TIMESTAMP DEFAULT NOW()
-);
-
--- Create index for efficient vector similarity search
-CREATE INDEX IF NOT EXISTS embeddings_embedding_idx ON embeddings 
-USING ivfflat (embedding vector_cosine_ops) WITH (lists = 100);
-
--- Create index for user_id lookups
-CREATE INDEX IF NOT EXISTS embeddings_user_id_idx ON embeddings (user_id);
-
--- Create index for metadata queries
-CREATE INDEX IF NOT EXISTS embeddings_metadata_idx ON embeddings USING GIN (metadata);
-
--- Grant permissions on the table
-GRANT ALL PRIVILEGES ON TABLE embeddings TO mem0_user;
-GRANT USAGE, SELECT ON SEQUENCE embeddings_id_seq TO mem0_user;
-
--- Create table for memory history tracking
-CREATE TABLE IF NOT EXISTS memory_history (
-    id SERIAL PRIMARY KEY,
-    memory_id VARCHAR(255),
-    user_id VARCHAR(255),
-    action VARCHAR(50),
-    previous_value TEXT,
-    new_value TEXT,
-    metadata JSONB,
-    created_at TIMESTAMP DEFAULT NOW()
-);
-
--- Create indexes for memory history
-CREATE INDEX IF NOT EXISTS memory_history_memory_id_idx ON memory_history (memory_id);
-CREATE INDEX IF NOT EXISTS memory_history_user_id_idx ON memory_history (user_id);
-CREATE INDEX IF NOT EXISTS memory_history_created_at_idx ON memory_history (created_at);
-
--- Grant permissions
-GRANT ALL PRIVILEGES ON TABLE memory_history TO mem0_user;
-GRANT USAGE, SELECT ON SEQUENCE memory_history_id_seq TO mem0_user;

docker-compose.yml

@@ -1,20 +1,17 @@
 services:
-  # PostgreSQL with pgvector extension for vector storage
-  postgres:
-    image: pgvector/pgvector:pg17-trixie
-    container_name: mem0-postgres
-    environment:
-      POSTGRES_DB: ${POSTGRES_DB:-mem0_db}
-      POSTGRES_USER: ${POSTGRES_USER:-mem0_user}
-      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-mem0_password}
+  # Qdrant vector database for vector storage
+  qdrant:
+    image: qdrant/qdrant:latest
+    container_name: mem0-qdrant
     expose:
-      - "5432"
+      - "6333"
     volumes:
-      - postgres_data:/var/lib/postgresql/data
-      - ./config/postgres-init.sql:/docker-entrypoint-initdb.d/init.sql
+      - qdrant_data:/qdrant/storage
+    command: >
+      sh -c "apt-get update && apt-get install -y curl && ./entrypoint.sh"
     healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-mem0_user} -d ${POSTGRES_DB:-mem0_db}"]
-      interval: 5s
+      test: ["CMD", "curl", "-f", "http://localhost:6333/"]
+      interval: 10s
       timeout: 5s
       retries: 5
     restart: unless-stopped
@@ -57,11 +54,9 @@ services:
       OPENAI_API_KEY: ${OPENAI_COMPAT_API_KEY}
       OPENAI_BASE_URL: ${OPENAI_COMPAT_BASE_URL}
       EMBEDDER_API_KEY: ${EMBEDDER_API_KEY:-AIzaSyA_}
-      POSTGRES_HOST: postgres
-      POSTGRES_PORT: 5432
-      POSTGRES_DB: ${POSTGRES_DB:-mem0_db}
-      POSTGRES_USER: ${POSTGRES_USER:-mem0_user}
-      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-mem0_password}
+      QDRANT_HOST: qdrant
+      QDRANT_PORT: 6333
+      QDRANT_COLLECTION_NAME: ${QDRANT_COLLECTION_NAME:-mem0}
       NEO4J_URI: bolt://neo4j:7687
       NEO4J_USERNAME: ${NEO4J_USERNAME:-neo4j}
       NEO4J_PASSWORD: ${NEO4J_PASSWORD:-mem0_neo4j_password}
@@ -71,7 +66,7 @@ services:
     ports:
       - "${BACKEND_PORT:-8000}:8000"
     depends_on:
-      postgres:
+      qdrant:
         condition: service_healthy
       neo4j:
         condition: service_healthy
@@ -81,7 +76,7 @@ services:
     command: ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
 
 volumes:
-  postgres_data:
+  qdrant_data:
   neo4j_data:
   neo4j_logs:
   neo4j_import:

frontend/index.html

@@ -37,7 +37,14 @@
             padding: 20px;
             background: #fafafa;
             border-bottom: 1px solid #e0e0e0;
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+
+        .chat-header-content {
             text-align: center;
+            flex: 1;
         }
 
         .chat-header h1 {
@@ -51,6 +58,31 @@
             font-size: 14px;
         }
 
+        .clear-chat-btn {
+            background: #f8f9fa;
+            color: #666;
+            border: 1px solid #e0e0e0;
+            padding: 8px 12px;
+            border-radius: 6px;
+            cursor: pointer;
+            font-size: 12px;
+            font-weight: 500;
+            display: flex;
+            align-items: center;
+            gap: 5px;
+            transition: all 0.2s ease;
+        }
+
+        .clear-chat-btn:hover {
+            background: #e9ecef;
+            border-color: #ced4da;
+            color: #495057;
+        }
+
+        .clear-chat-btn:active {
+            background: #dee2e6;
+        }
+
         .chat-messages {
             flex: 1;
             overflow-y: auto;
@@ -242,9 +274,14 @@
         <!-- Chat Section -->
         <div class="chat-section">
             <div class="chat-header">
+                <div class="chat-header-content">
                     <h1>What can I help you with?</h1>
                     <p>Chat with your memories - User: pratik</p>
                 </div>
+                <button class="clear-chat-btn" id="clearChatBtn" title="Clear chat history">
+                    🗑️ Clear Chat
+                </button>
+            </div>
             
             <div class="chat-messages" id="chatMessages">
                 <!-- Messages will be loaded here -->
@@ -281,6 +318,7 @@
         const memoriesList = document.getElementById('memoriesList');
         const memoryCount = document.getElementById('memoryCount');
         const refreshButton = document.getElementById('refreshMemories');
+        const clearChatBtn = document.getElementById('clearChatBtn');
 
         // Chat history in localStorage
         let chatHistory = JSON.parse(localStorage.getItem('chatHistory') || '[]');
@@ -296,6 +334,7 @@
                 if (e.key === 'Enter') sendMessage();
             });
             refreshButton.addEventListener('click', loadMemories);
+            clearChatBtn.addEventListener('click', clearChatWithConfirmation);
         });
 
         // Load chat history from localStorage
@@ -493,6 +532,13 @@
             }, 5000);
         }
 
+        // Clear chat history with confirmation
+        function clearChatWithConfirmation() {
+            if (confirm('Are you sure you want to clear the chat history? This action cannot be undone.')) {
+                clearChatHistory();
+            }
+        }
+
         // Clear chat history (for debugging)
         function clearChatHistory() {
             chatHistory = [];