Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/sukhbinder/llm-embed-ollama
Ollama provides Few embedding models. This plugin enables the usage of those models using Ollama.
https://github.com/sukhbinder/llm-embed-ollama
cli embedding llm llm-plugin ollama
Last synced: 3 months ago
JSON representation
Ollama provides Few embedding models. This plugin enables the usage of those models using Ollama.
- Host: GitHub
- URL: https://github.com/sukhbinder/llm-embed-ollama
- Owner: sukhbinder
- License: apache-2.0
- Created: 2024-07-26T08:02:11.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-08-08T08:00:58.000Z (5 months ago)
- Last Synced: 2024-09-30T10:40:59.455Z (3 months ago)
- Topics: cli, embedding, llm, llm-plugin, ollama
- Language: Python
- Homepage:
- Size: 44.9 KB
- Stars: 9
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# llm-embed-ollama
[](https://pypi.org/project/llm-embed-ollama/)
[](https://github.com/sukhbinder/llm-embed-ollama/releases)
[](https://github.com/sukhbinder/llm-embed-ollama/actions?query=workflow%3ATest)
[](https://github.com/sukhbinder/llm-embed-ollama/blob/main/LICENSE)
[LLM](https://llm.datasette.io/) plugin providing access to embedding models running on local [Ollama](https://ollama.ai) server.
## Installation
Install this plugin in the same environment as [LLM](https://llm.datasette.io/).
llm install llm-embed-ollama
## Background
Ollama provides Few embedding models. This plugin enables the usage of those models using llm and ollama embeddings..
To utilize these models, you need to have an instance of the Ollama server running.
See also [Embeddings: What they are and why they matter](https://simonillison.net/2023/Oct/23/embeddings/) for background on embeddings and an explanation of the LLM embeddings tool.
See also [Ollama Embeddings Models Blog](https://ollama.com/blog/embedding-models)
## Usage
This plugin adds support for the following embedding models available in ollama:
- all-minilm
- nomic-embed-text
- mxbai-embed-large
- bge-large: Embedding model from BAAI mapping texts to vectors.
- bge-m3: BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
The models needs to be downloaded. Using `ollama pull the first time you try to use them.
See [the LLM documentation](https://llm.datasette.io/en/stable/embeddings/index.html) for everything you can do.
To get started embedding a single string, run the following:
Make sure you have the appropriate ollama model.
```bash
ollama pull all-minilm
```
```bash
llm embed -m all-minilm -c 'Hello world'
```
This will output a JSON array of 384 floating point numbers to your terminal.
To calculate and store embeddings for every README in the current directory (try this somewhere with a `node_modules` directory to get lots of READMEs) run this:
```bash
llm embed-multi ollama-readmes \
-m all-minilm \
--files . '**/README.md' --store
```
Then you can run searches against them like this:
```bash
llm similar ollama-readmes -c 'utility functions'
```
Add `| jq` to pipe it through [jq](https://jqlang.github.io/jq/) for pretty-printed output, or ` | jq .id` to just see the matching filenames.
## Development
To set up this plugin locally, first checkout the code. Then create a new virtual environment:
```bash
cd llm-embed-ollama
python3 -m venv venv
source venv/bin/activate
```
Now install the dependencies and test dependencies:
```bash
llm install -e '.[test]'
```
To run the tests:
```bash
pytest
```