Feature Extraction
sentence-transformers
Safetensors
English
multilingual
qwen3
text-embeddings-inference
infinity
Instructions to use michaelfeil/zembed-1-infinity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use michaelfeil/zembed-1-infinity with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("michaelfeil/zembed-1-infinity") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Download infinity_client.py from michaelfeil/zembed-1-infinity: direct link, hf CLI and curl.
- Browser
- Download file 1.13 kB
-
https://huggingface.co/michaelfeil/zembed-1-infinity/resolve/main/infinity_client.py
- Command line
-
hf download hf://michaelfeil/zembed-1-infinity/infinity_client.py
-
curl -L -o infinity_client.py https://huggingface.co/michaelfeil/zembed-1-infinity/resolve/main/infinity_client.py
1.13 kB
| """Supply zembed's saved prompt and terminal suffix to Infinity's /embed API.""" | |
| import json | |
| import urllib.error | |
| import urllib.request | |
| def embed(texts, kind="document", base_url="http://localhost:7997", model="michaelfeil/zembed-1-infinity"): | |
| if isinstance(texts, str): | |
| texts = [texts] | |
| texts = list(texts) | |
| if kind not in ("query", "document") or not texts or any(not isinstance(text, str) for text in texts): | |
| raise ValueError("Provide text strings and kind='query' or kind='document'") | |
| body = { | |
| "model": model, | |
| "inputs": [text + "<|im_end|>\n" for text in texts], | |
| "prompt_name": kind, | |
| "normalize": True, | |
| "truncate": False, | |
| } | |
| request = urllib.request.Request( | |
| base_url.rstrip("/") + "/embed", | |
| data=json.dumps(body).encode(), | |
| headers={"Content-Type": "application/json"}, | |
| ) | |
| try: | |
| with urllib.request.urlopen(request, timeout=300) as response: | |
| return json.load(response) | |
| except urllib.error.HTTPError as error: | |
| raise RuntimeError(f"HTTP {error.code}: {error.read().decode()}") from error | |