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
82 lines
3.2 KiB
Plaintext
82 lines
3.2 KiB
Plaintext
---
|
|
title: Google AI
|
|
description: "Configure Google AI as an embedding provider in Mem0 using Gemini models and the GOOGLE_API_KEY variable."
|
|
---
|
|
|
|
To use Google AI embedding models, set the `GOOGLE_API_KEY` environment variables. You can obtain the Gemini API key from [here](https://aistudio.google.com/app/apikey).
|
|
|
|
### Usage
|
|
|
|
<CodeGroup>
|
|
```python Python
|
|
import os
|
|
from mem0 import Memory
|
|
|
|
os.environ["GOOGLE_API_KEY"] = "key"
|
|
os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
|
|
|
|
config = {
|
|
"embedder": {
|
|
"provider": "gemini",
|
|
"config": {
|
|
"model": "models/gemini-embedding-001",
|
|
}
|
|
}
|
|
}
|
|
|
|
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")
|
|
```
|
|
|
|
```typescript TypeScript
|
|
import { Memory } from 'mem0ai/oss';
|
|
|
|
const config = {
|
|
embedder: {
|
|
provider: "google",
|
|
config: {
|
|
apiKey: process.env["GOOGLE_API_KEY"],
|
|
model: "gemini-embedding-001",
|
|
embeddingDims: 1536,
|
|
},
|
|
},
|
|
};
|
|
|
|
const memory = new Memory(config);
|
|
const 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."}
|
|
]
|
|
await memory.add(messages, { userId: "john" });
|
|
```
|
|
</CodeGroup>
|
|
|
|
### Config
|
|
|
|
Here are the parameters available for configuring Gemini embedder:
|
|
<Tabs>
|
|
<Tab title="Python">
|
|
| Parameter | Description | Default Value |
|
|
| ---------------- | ------------------------------------ | ----------------------- |
|
|
| `model` | The name of the embedding model to use| `models/gemini-embedding-001` |
|
|
| `embedding_dims` | Dimensions of the embedding model | `768` |
|
|
| `api_key` | The Google API key | `None` |
|
|
| `output_dimensionality` | Output dimensionality for the embedding model (Gemini-specific; used when `embedding_dims` is not set) | `None` |
|
|
</Tab>
|
|
<Tab title="TypeScript">
|
|
| Parameter | Description | Default Value |
|
|
| ----------------- | --------------------------------------------- | -------------------------- |
|
|
| `model` | The name of the embedding model to use | `gemini-embedding-001` |
|
|
| `embeddingDims` | Dimensions of the embedding model. When not set, uses the model's native output dimensionality (3072 for `gemini-embedding-001`; MRL truncation to 768, 1536, or 3072 is supported) | `None` |
|
|
| `apiKey` | Google API key | `None` |
|
|
</Tab>
|
|
</Tabs>
|