references updated for qdrant
This commit is contained in:
Pratik Narola
parent
f625f8f556
commit
971548321f
3 changed files with 20 additions and 23 deletions
11
.env.example
11
.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
|
||||
# - Ollama must be running locally with nomic-embed-text:latest model
|
||||
# - Qdrant vector database for embeddings storage (replaces PostgreSQL+pgvector)
|
||||
# - Ollama must be running locally with nomic-embed-text:latest model
|
||||
|
|
|
|||
12
README.md
12
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
|
||||
|
|
@ -217,4 +217,4 @@ curl http://localhost:8000/graph/relationships/alice
|
|||
|
||||
## Development
|
||||
|
||||
See individual README files in `backend/` and `frontend/` directories for development setup.
|
||||
See individual README files in `backend/` and `frontend/` directories for development setup.
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
@ -447,4 +445,4 @@ docker logs mem0-backend --tail 20 -f
|
|||
|
||||
## 📄 License
|
||||
|
||||
This POC is designed for demonstration and evaluation purposes.
|
||||
This POC is designed for demonstration and evaluation purposes.
|
||||
|
|
|
|||
Loading…
Reference in a new issue