Describe the bug
Letta's Dockerfile is based on ankane/pgvector:v0.5.1, an image that hasn't been updated in 2 years and leverages PostgreSQL 15, which poses some security issues. Current development of PostgreSQL's vector similarity search is published in pgvector/pgvector, so why not changing to this base image?
Please describe your setup

• [X ] How are you running Letta?
  • Docker
• [ X] Describe your setup
  • Linux

Screenshots
If applicable, add screenshots to help explain your problem.

Additional context
Add any other context about the problem here.

• What model you are using

Agent File (optional)
Please attach your .af file, as this helps with reproducing issues.

If you're not using OpenAI, please provide additional information on your local LLM setup:

Local LLM details

If you are trying to run Letta with local LLMs, please provide the following information:

• The exact model you're trying to use (e.g. dolphin-2.1-mistral-7b.Q6_K.gguf)
• The local LLM backend you are using (web UI? LM Studio?)
• Your hardware for the local LLM backend (local computer? operating system? remote RunPod?)