Llama Embedder
This is a python binding for llama embedder, a purpose-built library for embeddings.
Installation
pip install llama_embedder
Usage
Local Models
This example shows how to use local model to embed texts.
from llama_embedder import Embedder
embedder = Embedder(model_path='./path/to/model.gguf')
# Embed stings
embeddings = embedder.embed_texts(["Hello World!", "My name is Ishmael."])
Hugging Face Models
This example shows how to download and use a model from Hugging Face.
from llama_embedder import Embedder
hf_repo = "ChristianAzinn/snowflake-arctic-embed-s-gguf"
gguf_file = "snowflake-arctic-embed-s-f16.GGUF"
embedder = Embedder(gguf_file, hf_repository=hf_repo)
embeddings = embedder.embed_texts(["Hello, world!", "Another sentence"])
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
llama_embedder-0.0.8.tar.gz
(18.8 MB
view details)
File details
Details for the file llama_embedder-0.0.8.tar.gz.
File metadata
- Download URL: llama_embedder-0.0.8.tar.gz
- Upload date:
- Size: 18.8 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/5.1.1 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
519f09259094440c302fc2549161b49f63c211a818df455692096ae2e2e90ae9
|
|
| MD5 |
b845d8d824f61b082a1e6da6156aa547
|
|
| BLAKE2b-256 |
aeaa37deafd0a01528fc76cb43af26bac5f3e6a8884f21a8c80106504c7a03b1
|
