项目文件夹

文件
wehub-resource-sync 555e282cc4
pi-agent-plugin checks / lint (push) Has been cancelled
pi-agent-plugin checks / test (20) (push) Has been cancelled
pi-agent-plugin checks / test (22) (push) Has been cancelled
pi-agent-plugin checks / build (push) Has been cancelled
TypeScript SDK CI / check_changes (push) Has been cancelled
TypeScript SDK CI / changelog_check (push) Has been cancelled
ci / changelog_check (push) Has been cancelled
ci / check_changes (push) Has been cancelled
ci / build_mem0 (3.10) (push) Has been cancelled
ci / build_mem0 (3.11) (push) Has been cancelled
ci / build_mem0 (3.12) (push) Has been cancelled
CLI Node CI / lint (push) Has been cancelled
CLI Node CI / test (20) (push) Has been cancelled
CLI Node CI / test (22) (push) Has been cancelled
CLI Node CI / build (push) Has been cancelled
CLI Python CI / lint (push) Has been cancelled
CLI Python CI / test (3.10) (push) Has been cancelled
CLI Python CI / test (3.11) (push) Has been cancelled
CLI Python CI / test (3.12) (push) Has been cancelled
CLI Python CI / build (push) Has been cancelled
openclaw checks / lint (push) Has been cancelled
openclaw checks / test (20) (push) Has been cancelled
openclaw checks / test (22) (push) Has been cancelled
openclaw checks / build (push) Has been cancelled
opencode-plugin checks / build (push) Has been cancelled
TypeScript SDK CI / build_ts_sdk (20) (push) Has been cancelled
TypeScript SDK CI / build_ts_sdk (22) (push) Has been cancelled
TypeScript SDK CI / integration_ts_sdk (20) (push) Has been cancelled
TypeScript SDK CI / integration_ts_sdk (22) (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:03:45 +08:00

42 行
1.4 KiB
Plaintext

---
title: "LM Studio"
description: "Configure LM Studio as an embedding provider in Mem0 for local embedding generation with models like nomic-embed-text."
---
You can use embedding models from LM Studio to run Mem0 locally.
### Usage
```python
import os
from mem0 import Memory
os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
config = {
"embedder": {
"provider": "lmstudio",
"config": {
"model": "nomic-ai/nomic-embed-text-v1.5-GGUF"
}
}
}
m = Memory.from_config(config)
messages = [
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="john")
```
### Config
Here are the parameters available for configuring LM Studio embedder:
| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the LM Studio model to use | `nomic-ai/nomic-embed-text-v1.5-GGUF` |
| `embedding_dims` | Dimensions of the embedding model | `1536` |
| `lmstudio_base_url` | Base URL for LM Studio connection | `http://localhost:1234/v1` |