Squeak-SemanticText

ChatGPT, embedding search, and retrieval-augmented generation for Squeak/Smalltalk. The package aims to make semantic context accessible in Squeak/Smalltalk by providing the following features:

• OpenAI API client: Currently supports chat completions and embeddings. Includes tools for managing rate limits, tracking expenses, and estimating prices for queries.
• SemanticConversation: Framework for conversational agents like ChatGPT.
• ChatGPT: Conversational GUI for Squeak. Supports streaming responses, editing conversations, and defining system messages.
• SemanticCorpus: Framework for semantic search, similarity search, and retrieval-augmented generation (RAG, aka “chat with your data”) through the power of text embeddings. Implements a simple yet functional vector database.
• Experimental tools such as an integration of semantic search and RAG into Squeak’s Help Browser or Squeak’s mailing list.

Check out the work that Christoph Thiede is doing at https://github.com/LinqLover/Squeak-SemanticText.

Feedback and contributions are welcome!