Submit a resource

Navigation

Back to directory

Fleming

A set of Databricks scripts that build a corpus from GitHub repository content, train and serve a semantic search model on CPU, and summarize repository code with the Azure OpenAI API.

Visit website (opens in a new tab)github.com
Fleming

Fleming is the open-source "brain" behind an internal AI Discovery Tool. It provides scripts to build a text corpus from a dataframe, and to train, register, serve, and query a semantic search model on Databricks, running on CPU rather than GPU to reduce cost.

A separate class ingests files from a list of GitHub repositories in an organization and tokenizes their contents into a dataframe, and another class sends that content to the Azure OpenAI API with a documentation prompt to generate a code summary.

Databricks handles model training and serving, combined with GitHub data ingestion, to provide an end-to-end pipeline for discovering and analyzing repository content.

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.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy