The paper introduces Telco-RAG, an open-source Retrieval-Augmented Generation (RAG) framework designed to handle the specific needs of telecommunications standards, particularly 3rd Generation Partnership Project (3GPP) documents. The framework addresses the challenges of implementing RAG pipelines on highly technical content, such as telecom standard documents, by optimizing chunk size, context length, indexing strategies, and query structuring. Key contributions include: 1. **Query Augmentation**: Enhances user queries with technical terms and abbreviations to improve contextual understanding. 2. **RAM Usage Reduction**: Utilizes a neural network (NN) router to selectively load relevant documents, reducing RAM usage. 3. **Prompt Engineering**: Designs a structured, dialogue-oriented prompt to ensure the RAG maintains focus on the user’s question while comprehending the broader context. Experimental results show that Telco-RAG significantly improves the accuracy of LLMs in answering telecom-related questions, outperforming baseline models and other RAG systems. The framework is publicly available and offers guidelines for implementing RAG in other technical domains, contributing to the integration of AI in the telecommunications field.The paper introduces Telco-RAG, an open-source Retrieval-Augmented Generation (RAG) framework designed to handle the specific needs of telecommunications standards, particularly 3rd Generation Partnership Project (3GPP) documents. The framework addresses the challenges of implementing RAG pipelines on highly technical content, such as telecom standard documents, by optimizing chunk size, context length, indexing strategies, and query structuring. Key contributions include: 1. **Query Augmentation**: Enhances user queries with technical terms and abbreviations to improve contextual understanding. 2. **RAM Usage Reduction**: Utilizes a neural network (NN) router to selectively load relevant documents, reducing RAM usage. 3. **Prompt Engineering**: Designs a structured, dialogue-oriented prompt to ensure the RAG maintains focus on the user’s question while comprehending the broader context. Experimental results show that Telco-RAG significantly improves the accuracy of LLMs in answering telecom-related questions, outperforming baseline models and other RAG systems. The framework is publicly available and offers guidelines for implementing RAG in other technical domains, contributing to the integration of AI in the telecommunications field.