Reusable retrieval-augmented generation pipelines

A computer-implemented method, comprising:

• accessing, by a computer processor of an enterprise Retrieval-Augmented Generation (“RAG”) pipeline engine within a Generative Artificial Intelligence (“GenAI”) launchpad platform associated with at least one Large Language Model (“LLM”), information in a RAG pipeline data store associated with a first RAG pipeline that was created by a first tenant, the RAG pipeline data store contains electronic records that represent RAG pipelines, each record including a pipeline identifier and at least one tuning parameter;
• receiving from a user an adjustment to tuning parameters of the first RAG pipeline associated with:
• (i) a document ingestion tuning parameter, (ii) a chunk tuning parameter, (iii) an embed tuning parameter, (iv) a similarity search tuning parameter, and (v) a context tuning parameter;
• automatically calculating an overall pipeline credibility score for the adjusted first RAG pipeline, including:
• (i) a retrieval accuracy metric, (ii) a context relevance metric, and (iii) an output coherence metric;
• displaying the overall pipeline credibility score to the user;
• and
• storing information about the adjusted first RAG pipeline into the RAG pipeline data store.

One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by a computing system, cause the computing system to perform operations, comprising:

• accessing, by a computer processor of an enterprise Retrieval-Augmented Generation (“RAG”) pipeline engine within a Generative Artificial Intelligence (“GenAI”) launchpad platform associated with at least one Large Language Model (“LLM”), information in a RAG pipeline data store associated with a first RAG pipeline that was created by a first tenant, the RAG pipeline data store contains electronic records that represent RAG pipelines, each record including a pipeline identifier and at least one tuning parameter;
• receiving from a user an adjustment to a tuning parameter of the first RAG pipeline;
• automatically calculating an overall pipeline credibility score for the adjusted first RAG pipeline;
• displaying the overall pipeline credibility score to the user;
• and
• storing information about the adjusted first RAG pipeline into the RAG pipeline data store.