JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ts-sdk): add HuggingFace embedding provider (#6027)

Browse Source 
Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>
This commit is contained in:
Bartok
2026-07-08 08:13:53 -06:00
committed by GitHub
parent 22f70d50e1
commit fbdbab805d
6 changed files with 271 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/components/embedders/models/huggingface.mdx
+38 -4
View File
@@ -5,6 +5,10 @@ description: "Configure Hugging Face as an embedding provider in Mem0 for local
You can use embedding models from Huggingface to run Mem0 locally.
<Note>
The TypeScript SDK supports Hugging Face only through a hosted [Text Embeddings Inference (TEI)](#using-text-embeddings-inference-tei) endpoint, or any OpenAI-compatible Hugging Face endpoint. The local `sentence-transformers` mode shown first is Python-only.
</Note>
### Usage
```python
@@ -34,9 +38,10 @@ m.add(messages, user_id="john")
### Using Text Embeddings Inference (TEI)
You can also use Hugging Face's Text Embeddings Inference service for faster and more efficient embeddings:
You can also use Hugging Face's Text Embeddings Inference service for faster and more efficient embeddings. This is the mode the TypeScript SDK uses.
```python
<CodeGroup>
```python Python
import os
from mem0 import Memory
@@ -56,6 +61,24 @@ m = Memory.from_config(config)
m.add("This text will be embedded using the TEI service.", user_id="john")
```
```typescript TypeScript
import { Memory } from 'mem0ai/oss';
// Point at a running TEI server, or any OpenAI-compatible HF endpoint
const config = {
embedder: {
provider: 'huggingface',
config: {
huggingfaceBaseUrl: 'http://localhost:3000/v1',
},
},
};
const memory = new Memory(config);
await memory.add("This text will be embedded using the TEI service.", { userId: "john" });
```
</CodeGroup>
To run the TEI service, you can use Docker:
```bash
@@ -66,11 +89,22 @@ docker run -d -p 3000:80 -v huggingfacetei:/data --platform linux/amd64 \
### Config
Here are the parameters available for configuring Huggingface embedder:
Here are the parameters available for configuring the Hugging Face embedder:
<Tabs>
<Tab title="Python">
| Parameter | Description | Default Value |
| --- | --- | --- |
| `model` | The name of the model to use | `multi-qa-MiniLM-L6-cos-v1` |
| `embedding_dims` | Dimensions of the embedding model | `selected_model_dimensions` |
| `model_kwargs` | Additional arguments for the model | `None` |
| `huggingface_base_url` | URL to connect to Text Embeddings Inference (TEI) API | `None` |
| `huggingface_base_url` | URL to connect to Text Embeddings Inference (TEI) API | `None` |
</Tab>
<Tab title="TypeScript">
| Parameter | Description | Default Value |
| --- | --- | --- |
| `huggingfaceBaseUrl` | TEI or OpenAI-compatible endpoint URL. Required; falls back to `baseURL`, `url`, then the `HUGGINGFACE_BASE_URL` env var | `None` |
| `model` | Model name sent to the endpoint (TEI ignores it) | `tei` |
| `apiKey` | API key for the endpoint; falls back to the `HUGGINGFACE_API_KEY` env var | `"hf"` |
</Tab>
</Tabs>