https://github.com/patw/breadvec
Text vectorizer using a SOTA mixedbread.ai embedding model
https://github.com/patw/breadvec
cosine-similarity mixedbread vectors
Last synced: 6 months ago
JSON representation
Text vectorizer using a SOTA mixedbread.ai embedding model
- Host: GitHub
- URL: https://github.com/patw/breadvec
- Owner: patw
- License: mit
- Created: 2024-03-15T20:44:27.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-03-18T15:22:56.000Z (over 1 year ago)
- Last Synced: 2025-04-15T20:12:47.273Z (6 months ago)
- Topics: cosine-similarity, mixedbread, vectors
- Language: Python
- Homepage:
- Size: 4.88 KB
- Stars: 4
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# BreadVec
A small vector API service for generating mixedbred.ai vectors. It's currently using the mxbai-embed-large-v1 model.
## Local Installation
```
pip install -r requirements.txt
```
## Local Running
```
uvicorn main:app --host 0.0.0.0 --port 3006
```
**Warning**: The first run will be VERY slow to load
Visit `http://localhost:3006/docs` in a browser once it's loaded
Call it in python like this:
```
# Function to call the text embedder
def embed(text):
response = requests.get(embedder["embedding_endpoint"], params={"text":text, "instruction": "Represent this text for retrieval:" }, headers={"accept": "application/json"})
vector_embedding = response.json()
return vector_embedding
```