Back to directory

Squeak-SemanticText

A Squeak/Smalltalk package that adds an OpenAI API client, conversational agents, a ChatGPT GUI, and a built-in vector database for semantic search and RAG.

Squeak-SemanticText

Squeak-SemanticText brings ChatGPT, embedding search and retrieval-augmented generation to Squeak/Smalltalk. It provides an OpenAI API client covering chat completions, embeddings and speech transcription and synthesis, with tools for managing rate limits, tracking expenses and estimating query prices.

A SemanticConversation framework supports conversational agents like ChatGPT as well as autonomous agents with function calling, and a ChatGPT conversational GUI supports streaming responses, editing conversations and defining system messages. A SemanticCorpus framework implements a functional vector database for semantic search, similarity search and retrieval-augmented generation over text embeddings.

Experimental integrations add semantic search and RAG to Squeak's Help Browser and its mailing list. The project suggests installing the package and reading its class comments and code for further detail.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.