Using ChatGPT Plugins with LLaMA

• nanoGPT

  69 32,050 5.4 Python

  The simplest, fastest repository for training/finetuning medium-sized GPTs.

Just playing casually with NanoGPT (https://github.com/karpathy/nanoGPT) with a desktop holding a 2080ti, it's really really really clear to me that the path to get to a pre-fine-tuned LLM is remarkably easy. RLHF is the piece above this which appears to also be surprisingly easy (if Sam Altman is to be believed). The juice is making these tools incredibly easy.

I think the barrier to entry here is low. OpenAI is ahead now, but I doubt that lives forever.

• chatgpt-retrieval-plugin

  52 20,859 6.1 Python

  The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

  

Found the answer here:

https://github.com/openai/chatgpt-retrieval-plugin#retrieval...

    The plugin uses OpenAI's text-embedding-ada-002 embeddings model to generate embeddings of document chunks, and then stores and queries them using a vector database on the backend. As an open-source and self-hosted solution, developers can deploy their own Retrieval Plugin and register it with ChatGPT. The Retrieval Plugin supports several vector database providers, allowing developers to choose their preferred one from a list.

• 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.

  

• llama-retrieval-plugin

  14 322 4.3 Python

  LLaMa retrieval plugin script using OpenAI's retrieval plugin

  

Author here. This section of the readme has more information: https://github.com/lastmile-ai/llama-retrieval-plugin#retrie...

It does use a vector database (pinecone, weaviate, etc.) to store embeddings. The embeddings are created using OpenAI's text-embedding-ada-002 model, but that's not a requirement. In fact we are looking at embeddings generation through BERT or RoBERTa to benchmark performance.

At prompt time, the plugin retrieves the nearest embeddings to the prompt, and inserts them into a more complete prompt before sending it to the model.

• manticoresearch

  33 8,350 9.9 C++

  Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK soon

  

It's not open source since 2017. The open source fork is https://github.com/manticoresoftware/manticoresearch

Suggest a related project