NevaMind-AI / NevaMind-AI/memU
[BUG] Cannot get to connect to postgres
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 14.4k
- Forks
- 1.1k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 16
Description
Description
No AI tool is able to help. Cannot find documentation. Spent a day - cannot connect and persist to postgres.
this is in my docker-compose (latest edit)
memu:
image: nevamindai/memu-server:latest
container_name: memu
restart: unless-stopped
environment:
# Force metadata store provider to postgres (not in memory)
# Use the generic "STORE" key to force all layers to Postgres
- MEMU_STORE_PROVIDER=postgres
- STORE_TYPE=postgres
- MEMU_METADATA_STORE_PROVIDER=postgres
- MEMU_VECTOR_STORE_PROVIDER=postgres
- MEMU_MEMORY_DIR=/tmp/memu_temp
# The DSN (Simplified)
- DATABASE_URL=postgresql://echo_user_name:${POSTGRES_PASSWORD}@postgres:5432/blog_database
- MEMU_DATABASE_URL=postgresql://echo_user_name:${POSTGRES_PASSWORD}@postgres:5432/blog_database
# Individual connection params (for internal fallbacks)
- PGHOST=postgres
- PGUSER=echo_user_name
- PGPASSWORD=${POSTGRES_PASSWORD}
- PGDATABASE=blog_database
- PGPORT=5432
# openai
- OPENAI_API_KEY=${OPENAI_API_KEY}
# Primary/Default LLM
- MEMU_LLM_PROVIDER=openai
- MEMU_LLM_MODEL=gpt-4o-mini
# Embedding Profile
- MEMU_EMBEDDING_PROVIDER=openai
- MEMU_EMBEDDING_MODEL=text-embedding-3-small
# STT redirected to internal whisper
- MEMU_STT_PROVIDER=openai
- MEMU_STT_BASE_URL=http://models-server:8081/v1
- MEMU_STT_API_KEY=not-needed-locally
cpuset: "28-31"
depends_on:
postgres-db:
condition: service_healthy
# volumes:
# - ./custom_main.py:/app/app/main.py:ro
networks:
- livekit-net
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
interval: 30s
timeout: 10s
retries: 3
Environment
Docker on Linux
Steps to reproduce
Install and run, Only in-memory works. Dont see any tables in postgres, No error messages on docker compose up
Expected behavior
Data should persist to postgres
Version
latest
Severity
Critical
Additional Information
There has got to be better documentation or full examples to use a database like postgres
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the docker-compose service configuration and the listed Postgres environment variables, including DATABASE_URL, MEMU_DATABASE_URL, and the depends_on entry. Reproduce the deployment on Docker/Linux, inspect the service logs and database state, and confirm that the application creates and persists tables in Postgres rather than using in-memory storage.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- postgres, python
- Domain
- databases
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100