Data Preparation

A Generative AI Engineer is preparing a knowledge base of long-form product manuals for a RAG chatbot. During evaluation, users report that answers frequently seem 'cut off' or miss information that spans across paragraph boundaries. The team is using fixed-size chunking of 500 tokens with zero overlap. Which adjustment to the chunking strategy is MOST likely to resolve this issue while keeping chunk sizes manageable?

A Generative AI Engineer is preparing a corpus of long-form product manuals (avg 40 pages each) for a RAG application. They plan to use an embedding model with a maximum input context of 512 tokens. During testing, they notice that chunks frequently exceed this limit and are silently truncated, causing the tail of each chunk's content to be excluded from the embedding. What is the most appropriate action to ensure complete content is represented in the vector index?

You are building a RAG application over a customer support knowledge base composed of thousands of short FAQ entries. Each entry is a self-contained question paired with a concise answer, and entries are typically 2-4 sentences long. Retrieval accuracy is currently poor because chunks frequently split a question from its answer or merge multiple unrelated FAQs together. Which chunking strategy best fixes this?

You are preparing a large internal knowledge base for a RAG application. The documents are Markdown files with clear hierarchical headers (H1 for product areas, H2 for features, H3 for individual procedures). Users typically ask specific procedural questions like 'How do I reset the API key for the billing service?'. You want each retrieved chunk to be self-contained and topically coherent so the LLM has focused context. Which chunking approach best fits these documents?

You are building a RAG system over a corpus of customer support tickets. The tickets vary widely in length: many are short one-paragraph questions, but some are long multi-issue threads spanning several distinct problems. Users query for solutions to specific individual problems. You want each retrieved chunk to represent a coherent, self-contained unit so that retrieval returns focused answers without mixing unrelated issues. Which chunking approach best fits this requirement?

You are building a RAG pipeline over quarterly financial reports delivered as PDFs. Each report contains long narrative sections interspersed with large tabular data (balance sheets, income statements). During testing, users ask questions about specific line-item values, but retrieved chunks frequently return partial tables where column headers are separated from their data rows, producing wrong or unanswerable results. Which document preparation approach best addresses this problem?

You are building a RAG application over a large corpus of software engineering documentation that mixes prose explanations with fenced code blocks and API tables. During testing, users complain that when they ask 'show me the function that validates tokens,' the retrieved chunks return only the surrounding explanation text and cut code samples in half, making the answers useless. You are currently using a fixed-size character chunker with 500-character chunks and no overlap. Which change to your chunking strategy will most directly improve retrieval of complete, coherent code examples?

A Generative AI Engineer is building a RAG application over a corpus of internal support articles that were exported from three different systems. During data profiling, they discover that roughly 30% of the articles are near-duplicates (same content with minor formatting differences) because articles were migrated multiple times. Early retrieval tests show that the top-k results are frequently filled with several copies of the same article, crowding out other relevant content. What is the most effective step to improve retrieval quality before generating embeddings?

A Generative AI Engineer must embed 4 million product-description records stored in a Delta table before creating a Databricks Vector Search index. They plan to call a Databricks Model Serving endpoint hosting an embedding model. Initial testing shows the job is extremely slow because each row is sent to the endpoint one at a time in a Python loop. Which change will most improve embedding throughput while remaining a supported Databricks pattern?

A Generative AI Engineer built a RAG application on Databricks. They embedded a corpus of 50,000 product manual chunks using the 'bge-large-en' embedding model and stored the vectors in a Databricks Vector Search index. During testing, retrieval quality is poor even for queries that clearly match documents in the corpus. On inspection, the engineer discovers that the query embeddings at search time are being generated by a different model ('all-MiniLM-L6-v2') than the one used to build the index. Which action correctly resolves the root cause of the poor retrieval?

A Generative AI Engineer is building a RAG application over a company's internal knowledge base. Stakeholders require that every generated answer include a citation showing the document title, section heading, and a link back to the original source page. The engineer is designing the document preparation pipeline that produces chunks for embedding and indexing in Databricks Vector Search. What is the most effective approach to satisfy the citation requirement?

A Generative AI Engineer has built a RAG pipeline over a corpus of internal knowledge base articles. During evaluation, users report that retrieved chunks are often topically related to the query but frequently lack the specific detail needed to answer the question, forcing the LLM to say it cannot find the answer. Inspection shows each chunk is 1500 tokens with no overlap, and many chunks combine an FAQ heading with several unrelated sub-answers. What is the most effective first change to improve retrieval relevance?

A Generative AI Engineer has built a RAG application over an internal knowledge base and wants to quantitatively evaluate whether the vector search retriever is returning relevant documents before investing in prompt tuning. The team can manually label a small set of representative questions with the specific source chunks that should be retrieved for each. Which evaluation approach best measures retrieval relevance in this situation?

A Generative AI Engineer is building a RAG system over an internal knowledge base exported from a wiki. During inspection of the chunked output, they notice many chunks contain only navigation breadcrumbs, page footers with copyright notices, empty table cells, or single-word headers with no surrounding content. These chunks are being embedded and indexed alongside meaningful content, and retrieval quality has degraded because irrelevant chunks are frequently returned. What is the most effective step to take before generating embeddings and populating the Vector Search index?

You are building a RAG application for a SaaS platform that serves multiple client companies. Each client's internal documents are embedded and stored in a single Databricks Vector Search index. A strict requirement is that when an employee from Company A submits a query, the retrieval step must NEVER return chunks belonging to Company B, even if those chunks are semantically more similar. Which approach best satisfies this requirement during data preparation and retrieval?

A Generative AI Engineer is building a RAG application over a knowledge base assembled by scraping the company's public support website. During testing, retrieved chunks frequently contain navigation menus, cookie-consent banners, repeated footer text, and broken HTML tags, which pollute the context passed to the LLM and degrade answer quality. The engineer wants to improve retrieval and generation quality before embeddings are generated. Which action best addresses the root cause?

A Generative AI Engineer is building a RAG application on Databricks. They created a self-managed Delta Sync Vector Search index and populated an embeddings column by calling a model serving endpoint that produces 1024-dimensional vectors. At query time, the retrieval step consistently returns errors or nonsensical results. The engineer confirms the index was created successfully and documents were synced. What is the MOST likely root cause of the poor retrieval behavior?

A Generative AI Engineer is building a RAG application on Databricks. The source documents are stored and chunked in a Delta table that receives incremental updates several times per day as new documents are ingested. The engineer wants to create a Vector Search index that automatically stays in sync with the chunk table as rows are added or modified, while minimizing operational overhead and avoiding the need to manually manage embedding generation. Which approach should the engineer choose?

You are building a RAG application on Databricks. Your source data lives in a Delta table with a text column containing pre-chunked passages, but you have NOT computed embeddings yourself and prefer not to manage the embedding pipeline. You want Databricks Vector Search to automatically compute and keep embeddings in sync as the Delta table changes. Which configuration should you choose when creating the Vector Search index?

You are building a RAG application over a Delta table of internal knowledge base articles. The articles are edited frequently throughout the day by the support team, and the business requires that the vector index reflect edits within a few minutes without manual intervention. Your team has already enabled Change Data Feed on the source Delta table and set up a Databricks Vector Search endpoint. Which index configuration best meets these requirements?