How to start the server

[mrobinson-opi]

Hi thanks for all your work. I am trying to get started with this on an RK3588 device. I have ollama installed and cloned the repo and installed as much as I could figure out. but I am getting this error and I'm not sure if I am even trying to do it right. Thank you.

(.venv) mrobinson@orangepi5pro:/MemOS$ poetry run python -m memos.api_server
/home/mrobinson/MemOS/.venv/lib/python3.12/site-packages/qdrant_client/http/models/models.py:758: SyntaxWarning: invalid escape sequence '&'
description="Check that the field is empty, alternative syntax for is_empty: \"field_name\"",
/home/mrobinson/MemOS/.venv/lib/python3.12/site-packages/qdrant_client/http/models/models.py:762: SyntaxWarning: invalid escape sequence '&'
description="Check that the field is null, alternative syntax for is_null: \"field_name\"",
/home/mrobinson/MemOS/.venv/bin/python: No module named memos.api_server
(.venv) mrobinson@orangepi5pro:/MemOS$ poetry run python -m memos.server.main
/home/mrobinson/MemOS/.venv/bin/python: Error while finding module specification for 'memos.server.main' (ModuleNotFoundError: No module named 'memos.server')
(.venv) mrobinson@orangepi5pro:~/MemOS$

[Ki-Seki]

Simply run make serve or the equivalent command poetry run uvicorn memos.api.start_api:app in the MemOS folder to start the server.

[mrobinson-opi]

Thanks for the responce!
Another questions how do I change the port number?

[Ki-Seki]

Sorry, I didn't understand your question. Can you express it in a different way?

[mrobinson-opi]

How to use MemOS with OLLAMA?

[mrobinson-opi]

I feel like I am getting closer
(.venv) mrobinson@orangepi5pro:~/MemOS$ python3 test_v2.py
/home/mrobinson/MemOS/.venv/lib/python3.12/site-packages/ollama/_types.py:81: PydanticDeprecatedSince211: Accessing the 'model_fields' attribute on the instance is deprecated. Instead, you should access this attribute from the model class. Deprecated in Pydantic V2.11 to be removed in V3.0.
if key in self.model_fields:
MemOS client initialized and connected to Ollama!
An error occurred: shapes (0,1536) and (768,) not aligned: 1536 (dim 1) != 768 (dim 0)
Please ensure your Ollama server is running on http://localhost:11434.
You can verify Ollama status by visiting http://localhost:11434/ in a browser on your Orange Pi.
Also, double-check that 'llama3:latest' and 'nomic-embed-text' are present when you run 'ollama list'.

[mrobinson-opi]

/home/mrobinson/MemOS/.venv/lib/python3.12/site-packages/ollama/_types.py:81: PydanticDeprecatedSince211: Accessing the 'model_fields' attribute on the instance is deprecated. Instead, you should access this attribute from the model class. Deprecated in Pydantic V2.11 to be removed in V3.0.
if key in self.model_fields:
MemOS client initialized and connected to Ollama!

[Ki-Seki]

Thanks for all your work getting MemOS and Ollama up and running — looks like you're very close!

From the error message shapes (0,1536) and (768,) not aligned, it seems there's a mismatch between the embedding output from Ollama and what MemOS expects. A few things you can check:

• ✅ Make sure the embedding model (nomic-embed-text) you're using produces 768-dimensional vectors — or adjust MemOS to handle the actual output size if it's different.
• ✅ Try using another embedding model like llama3-embed if it's available in your Ollama setup, which might be more compatible with MemOS.
• ✅ Check if MemOS allows configuring expected embedding dimensions — that could help align the inputs correctly.

Also, really nice work getting MemOS running on a custom port! If you’re planning to integrate it more tightly with Ollama (e.g. inference or embedding pipelines), double-check the API endpoint configuration and see if MemOS lets you customize how it connects to Ollama.

[mrobinson-opi]

(.venv) mrobinson@orangepi5pro:~/MemOS/examples/mem_os$ python3 simple_memos.py

All users:

• root (root) - Role: root
• lcy1 (lcy1) - Role: user
  memos.configs.vec_db - WARNING - vec_db.py:34 - set_default_path - No host, port, or path provided for Qdrant. Defaulting to local path: /home/mrobinson/MemOS/examples/mem_os/.memos/qdrant
  Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 6.98it/s]
  memos.vec_dbs.qdrant - WARNING - qdrant.py:32 - init - Qdrant is running in local mode (host and port are both None). In local mode, there may be race conditions during concurrent reads/writes. It is strongly recommended to deploy a standalone Qdrant server (e.g., via Docker: https://qdrant.tech/documentation/quickstart/).
  memos.vec_dbs.qdrant - WARNING - qdrant.py:49 - create_collection - Collection 'Ki-Seki/mem_cube_2' (vector dimension: 768) already exists. Skipping creation.
  Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 12.74it/s]
  Get all results for user : {'para_mem': [], 'act_mem': [], 'text_mem': [{'cube_id': '/home/mrobinson/MemOS/examples/data/mem_cube_2', 'memories': [TextualMemoryItem(id='161cd56b-aebb-470e-96df-9244b2eaf1f4', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='2319d7a2-8734-4ba0-9a23-727aca4a839b', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-14T23:52:39.132623')), TextualMemoryItem(id='53b90aef-7f2d-4e71-a5f9-4e8a5b9487fe', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='9630ecf0-fa74-477d-bfda-b309f3ce159f', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-16T22:26:07.291417')), TextualMemoryItem(id='67653a3e-6cd1-4737-a97f-f4cdeb9633c5', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='42941b99-2d4e-4182-bc28-a55298c2450a', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-16T22:30:34.025515')), TextualMemoryItem(id='8fae5d65-63ff-4336-a80c-07fda044b0e5', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='572cfaaf-7b8a-422a-ac44-7386326fe99d', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-14T23:50:54.494509')), TextualMemoryItem(id='a18c2ce3-7824-41de-9f67-e6ef9d7c66e7', memory='The user loves the Eiffel Tower.', metadata=TextualMemoryMetadata(user_id='user_123', session_id='0c3d29d2-e078-4a03-960b-563bb33ec7ae', status='activated', type='opinion', memory_time='2025-06-03', source='conversation', confidence=100.0, entities=['Eiffel Tower'], tags=['opinions', 'landmarks'], visibility='session', updated_at='2025-06-03T00:00:00')), TextualMemoryItem(id='c20f3f52-c544-4323-80be-25aa9438890b', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='af78baca-7e84-4144-8155-e061e6852403', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-14T23:40:34.423452')), TextualMemoryItem(id='cd0377e4-0280-4ca4-b5ad-1dbc0e7d49c2', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='1ef5761a-841d-4c53-be4f-6bb69339174b', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-16T22:52:33.866958')), TextualMemoryItem(id='fb778a36-e589-4c9d-8eeb-d0a71fd8299d', memory='The user is a professor.', metadata=TextualMemoryMetadata(user_id='user_123', session_id='0c3d29d2-e078-4a03-960b-563bb33ec7ae', status='activated', type='fact', memory_time='2025-06-03', source='conversation', confidence=90.0, entities=['professor'], tags=['academic', 'professors'], visibility='private', updated_at='2025-06-03T17:14:18'))]}]}
  Get memories for user : <ID: 161cd56b-aebb-470e-96df-9244b2eaf1f4 | Memory: I like playing football. | Metadata: user_id=root, session_id=2319d7a2-8734-4ba0-9a23-727aca4a839b, status=activated, source=conversation, updated_at=2025-07-14T23:52:39.132623>
  Search results for user : {'text_mem': [{'cube_id': '/home/mrobinson/MemOS/examples/data/mem_cube_2', 'memories': [TextualMemoryItem(id='cd0377e4-0280-4ca4-b5ad-1dbc0e7d49c2', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='1ef5761a-841d-4c53-be4f-6bb69339174b', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-16T22:52:33.866958')), TextualMemoryItem(id='67653a3e-6cd1-4737-a97f-f4cdeb9633c5', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='42941b99-2d4e-4182-bc28-a55298c2450a', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-16T22:30:34.025515')), TextualMemoryItem(id='53b90aef-7f2d-4e71-a5f9-4e8a5b9487fe', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='9630ecf0-fa74-477d-bfda-b309f3ce159f', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-16T22:26:07.291417')), TextualMemoryItem(id='161cd56b-aebb-470e-96df-9244b2eaf1f4', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='2319d7a2-8734-4ba0-9a23-727aca4a839b', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-14T23:52:39.132623')), TextualMemoryItem(id='8fae5d65-63ff-4336-a80c-07fda044b0e5', memory='I like playing football.', metadata=TextualMemoryMetadata(user_id='root', session_id='572cfaaf-7b8a-422a-ac44-7386326fe99d', status='activated', type=None, memory_time=None, source='conversation', confidence=None, entities=None, tags=None, visibility=None, updated_at='2025-07-14T23:50:54.494509'))]}], 'act_mem': [], 'para_mem': []}
  👤 [You] do I like playing football?

🤖 [Assistant] It seems you have a strong affinity for playing football! You've mentioned it multiple times, and I'm excited to hear more about your passion for the sport. What's your favorite part about playing or watching football?

👤 [You]

---

{
"user_id": "root",
"chat_model": {
"backend": "ollama",
"config": {
"model_name_or_path": "llama3:latest",
"temperature": 0.1,
"remove_think_prefix": true,
"max_tokens": 4096
}
},
"mem_reader": {
"backend": "simple_struct",
"config": {
"llm": {
"backend": "ollama",
"config": {
"model_name_or_path": "qwen3:0.6b",
"temperature": 0.0,
"remove_think_prefix": true,
"max_tokens": 8192
}
},
"embedder": {
"backend": "ollama",
"config": {
"model_name_or_path": "nomic-embed-text:latest"
}
},
"chunker": {
"backend": "sentence",
"config": {
"tokenizer_or_token_counter": "gpt2",
"chunk_size": 512,
"chunk_overlap": 128,
"min_sentences_per_chunk": 1
}
}
}
},
"max_turns_window": 20,
"top_k": 5,
"enable_textual_memory": true,
"enable_activation_memory": false,
"enable_parametric_memory": false
}

---

from memos.configs.mem_os import MOSConfig
from memos.mem_os.main import MOS

init MOSConfig

mos_config = MOSConfig.from_json_file("/home/mrobinson/MemOS/examples/data/config/simple_memos_config.json")
mos = MOS(mos_config)

create user id

user_id = "lcy1"
mos.create_user(user_id=user_id)
users = mos.list_users()
print("\nAll users:")
for user in users:
print(f" - {user['user_name']} ({user['user_id']}) - Role: {user['role']}")

load exist mem_cube from local

mos.register_mem_cube("/home/mrobinson/MemOS/examples/data/mem_cube_2", user_id=user_id)

mos.add(memory_content="I like playing football.", user_id=user_id)

get_all_results = mos.get_all(user_id=user_id)
print(f"Get all results for user : {get_all_results}")

get_results = mos.get(
mem_cube_id="/home/mrobinson/MemOS/examples/data/mem_cube_2",
memory_id=get_all_results["text_mem"][0]["memories"][0].id,
user_id=user_id,
)
print(f"Get memories for user : {get_results}")

search_results = mos.search(query="my favorite football game", user_id=user_id)
print(f"Search results for user : {search_results}")

while True:
user_input = input("👤 [You] ").strip()
print()
response = mos.chat(user_input, user_id=user_id)
print(f"🤖 [Assistant] {response}\n")
print("📢 [System] MemChat has stopped.")

[Ki-Seki]

If you ask a different question, you should open a new post.