LLM now provides tools for working with embeddings

• llm-cluster

  3 59 4.9 Python

  LLM plugin for clustering embeddings

There's a lot of stuff in this release.

Don't miss the new llm-cluster plugin, which can both calculate clusters from embeddings and use another LLM call to generate a name for each cluster: https://github.com/simonw/llm-cluster

Example usage:

Fetch all issues, embed them and store the embeddings and content in SQLite:

    paginate-json 'https://api.github.com/repos/simonw/llm/issues?state=all&filter=all' \

• llm-gpt4all

  3 180 6.9 Python

  Plugin for LLM adding support for the GPT4All collection of models

I'm still iterating on that. Plugins get complete control over the prompts, so they can handle the various weirdnesses of them. Here's some relevant code:

https://github.com/simonw/llm-gpt4all/blob/0046e2bf5d0a9c369...

https://github.com/simonw/llm-mlc/blob/b05eec9ba008e700ecc42...

https://github.com/simonw/llm-llama-cpp/blob/29ee8d239f5cfbf...

I'm not completely happy with this yet. Part of the problem is that different models on the same architecture may have completely different prompting styles.

I expect I'll eventually evolve the plugins to allow them to be configured in an easier and more flexible way. Ideally I'd like you to be able to run new models on existing architectures using an existing plugin.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• llm-mlc

  3 172 5.1 Python

  LLM plugin for running models using MLC

I'm still iterating on that. Plugins get complete control over the prompts, so they can handle the various weirdnesses of them. Here's some relevant code:

https://github.com/simonw/llm-gpt4all/blob/0046e2bf5d0a9c369...

https://github.com/simonw/llm-mlc/blob/b05eec9ba008e700ecc42...

https://github.com/simonw/llm-llama-cpp/blob/29ee8d239f5cfbf...

I'm not completely happy with this yet. Part of the problem is that different models on the same architecture may have completely different prompting styles.

I expect I'll eventually evolve the plugins to allow them to be configured in an easier and more flexible way. Ideally I'd like you to be able to run new models on existing architectures using an existing plugin.

• llm-llama-cpp

  1 133 7.2 Python

  LLM plugin for running models using llama.cpp

I'm still iterating on that. Plugins get complete control over the prompts, so they can handle the various weirdnesses of them. Here's some relevant code:

https://github.com/simonw/llm-gpt4all/blob/0046e2bf5d0a9c369...

https://github.com/simonw/llm-mlc/blob/b05eec9ba008e700ecc42...

https://github.com/simonw/llm-llama-cpp/blob/29ee8d239f5cfbf...

I'm not completely happy with this yet. Part of the problem is that different models on the same architecture may have completely different prompting styles.

I expect I'll eventually evolve the plugins to allow them to be configured in an easier and more flexible way. Ideally I'd like you to be able to run new models on existing architectures using an existing plugin.

• datasette-faiss

  1 32 10.0 Python

  Maintain a FAISS index for specified Datasette tables

I experimented with that a few months ago. Building a fresh FAISS index for a few thousand matches is really quick, so o think it's often better to filter first, build a scratch index and then use that for similarity: https://github.com/simonw/datasette-faiss/issues/3

• DP_means

  1 45 1.7 C++

  Dirichlet Process K-means

I found one implementation here: https://github.com/vsmolyakov/DP_means

Alternatively, there is a Bayesian GMM in sklearn. When you restrict it to diagonal Covariance matrices, you should be fine in high dimensions

Suggest a related project