{"id":492,"date":"2026-09-24T10:15:00","date_gmt":"2026-09-24T08:15:00","guid":{"rendered":"https:\/\/www.lukaswojcik.com\/?p=492"},"modified":"2026-10-26T12:42:57","modified_gmt":"2026-10-26T11:42:57","slug":"building-a-rag-knowledge-base-with-google-cloud-vertex-ai-bigquery","status":"publish","type":"post","link":"https:\/\/www.lukaswojcik.com\/blog\/en\/cloud-ai\/tutorials-en-cloud-ai\/building-a-rag-knowledge-base-with-google-cloud-vertex-ai-bigquery\/","title":{"rendered":"Building a RAG Knowledge Base with Google Cloud Vertex AI & BigQuery"},"content":{"rendered":"

Retrieval-Augmented Generation (RAG) adds relevant passages from a document collection to a model request. This can help answer questions about internal manuals or technical procedures. RAG can reduce incorrect answers, but does not guarantee accuracy or complete evidence. Document quality, retrieval quality and answer verification remain essential.<\/p>\n

1. Two workflows: preparing documents and answering questions<\/h2>\n

Preparation splits documents into passages, creates numerical vectors called embeddings, and stores each passage, source and vector in BigQuery. An embedding is a list of numbers representing features of a text. Similar lists can help find passages about similar topics. A question receives another embedding. Search retrieves similar passages, and Gemini uses the retrieved context to compose an answer. Cloud Storage is one possible location for source files, not a prerequisite for the SQL examples below.<\/p>\n

Tokens are the units of text processed by the model, often whole words or parts of words. Overlap repeats some text at the boundary between neighboring passages so that a sentence or explanation is less likely to lose its context. Chunks of roughly 500 to 1000 tokens with some overlap are a starting point for experiments, not a universal optimum. Headings, tables, language changes and the embedding model’s token limit affect suitable boundaries. gemini-embedding-001<\/code> supports multilingual text. Questions and documents need embeddings from the same model, with the same number of values in each vector. The task types are RETRIEVAL_DOCUMENT<\/code> for passages and RETRIEVAL_QUERY<\/code> for questions.<\/p>\n

\"Preparing
Document preparation and answering remain separate. Content changes require maintenance; retrieval and a model prompt do not guarantee evidence.<\/figcaption><\/figure>\n

2. Embedding generation and error checks before release<\/h2>\n

This example is an initial setup in a dedicated test dataset. Project and table names are placeholders. The dataset, a BigQuery Cloud resource connection and the required APIs must already exist. CREATE MODEL<\/code> uses an existing connection; the statement does not create a connection. The dataset and connection use us-central1<\/code>. The connection’s service account needs access to the embedding model, commonly through Vertex AI User.<\/p>\n

The input table contains doc_id<\/code>, chunk_id<\/code>, content_text<\/code> and source_url<\/code> for each passage. This simplified example requires the entire corpus to be approved for every permitted request. A shared service account does not automatically enforce an application’s individual document permissions. Different access rights require verified authorization before retrieved passages reach Gemini.<\/p>\n

SQL<\/span>