From Prompts to Programs: A RAG-Based Framework for Code Synthesis

J.P. Nair

doi:10.1007/978-981-96-7508-1_39

From Prompts to Programs: A RAG-Based Framework for Code Synthesis

2026-01-01

0

PRE

AI

DOI：10.1007/978-981-96-7508-1_39

Original

Original request for help

Save

Abstract

En 中文

The increasing demand for AI-driven solutions in development has encouraged people to conduct various research into generating code from natural language prompts. My paper presents a Retrieval-Augmented Generation (RAG) pipeline for code generation, making use of embedding models, contextual retrieval and advanced language models such as Mistral and CodeLLama. This approach incorporates document indexing and metadata extraction to create context-aware code snippets and at the end of the process, we get a python file with the generated code present in it.

Keywords:

RAG

LLamaCloud

ReActAgent

LLamaParse

VectorStoreIndex

QueryEngineTool

QueryPipeline

Codellama

From Prompts to Programs: A RAG-Based Framework for Code Synthesis

Abstract

Journal

Organization

Cited Papers