Describe the bug
When mounting a config file into kubernetes pod at /root/.memgpt/config, program exits because it cannot write to the config file.
ubuntu@terraform:~/workspace/home-ops-prod/cluster/apps/home/localai/memgpt(β|prod:home)$ kcl memgpt-776b89b584-gh5km -c main
Starting MEMGPT server...
server :: loading configuration from '/root/.memgpt/config'
Traceback (most recent call last):
File "/app/.venv/bin/uvicorn", line 8, in <module>
sys.exit(main())
^^^^^^
File "/app/.venv/lib/python3.11/site-packages/click/core.py", line 1157, in _call
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/.venv/lib/python3.11/site-packages/click/core.py", line 1078, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
...
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 690, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 940, in exec_module
File "<frozen importlib._bootstrap>", line 241, in callwith_frames_removed
File "/memgpt/server/rest_api/server.py", line 46, in <module>
server: SyncServer = SyncServer(default_interface=interface)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/memgpt/server/server.py", line 222, in __init
self.config.save()
File "/memgpt/config.py", line 272, in save
with open(self.config_path, "w", encoding="utf-8") as f:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
OSError: [Errno 30] Read-only file system: '/root/.memgpt/config'
Additional context
Comment from Swooders in Discord:
swooders. β Today at 11:00 AM
We did something a bit hacky to get the enviornment variable configuration (for postgres) to work for the docker container with minimal changes, where we override the config to point to the provided envs for postgres (basically so we could keep using the config file for DB configuration) -- but I think we need to change this and migrate to using envs everywhere else in the code istead fo reading the config file
MemGPT Config
Please attach your ~/.memgpt/config file or copy past it below.
[defaults]
preset = memgpt_chat
persona = sam_pov
human = basic
[model]
model = neuralhermes-2.5-7b
model_endpoint = http://localai.home.svc.cluster.local:8080/v1
model_endpoint_type = openai
model_wrapper = null
context_window = 8192
[embedding]
embedding_endpoint_type = openai
embedding_endpoint = http://localai.home.svc.cluster.local:8080/v1
embedding_model = bert-embeddings
embedding_dim = 1536
embedding_chunk_size = 300
[archival_storage]
type = postgres
path = /root/.memgpt/chroma
uri = postgresql+pg8000://memgpt:adsfjkh*&^wer13@localhost:5432/memgpt
[recall_storage]
type = postgres
path = /root/.memgpt
uri = postgresql+pg8000://memgpt:adsfjkh*&^wer13@localhost:5432/memgpt
[metadata_storage]
type = postgres
path = /root/.memgpt
uri = postgresql+pg8000://memgpt:adsfjkh*&^wer13@localhost:5432/memgpt
[client]
anon_clientid = 00000000-0000-0000-0000-000000000000
If you're not using OpenAI, please provide additional information on your local LLM setup:
Local LLM details
If you are trying to run MemGPT 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?)
Describe the bug When mounting a config file into kubernetes pod at /root/.memgpt/config, program exits because it cannot write to the config file.
Please describe your setup
Additional context Comment from Swooders in Discord:
MemGPT Config Please attach your
~/.memgpt/config
file or copy past it below.If you're not using OpenAI, please provide additional information on your local LLM setup:
Local LLM details
If you are trying to run MemGPT with local LLMs, please provide the following information:
dolphin-2.1-mistral-7b.Q6_K.gguf
)