Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Stay organized with collections
Save and categorize content based on your preferences.
After a document is ingested, Vertex AI RAG Engine runs a set of transformations to
prepare the data for indexing. You can control your use cases using the
following parameters:
Parameter
Description
chunk_size
When documents are ingested into an index, they're split into chunks. The chunk_size parameter (in tokens) specifies the size of the chunk. The default chunk size is 1,024 tokens.
chunk_overlap
By default, documents are split into chunks with a certain amount of overlap to improve relevance and retrieval quality. The default chunk overlap is 256 tokens.
A smaller chunk size means the embeddings are more precise. A larger chunk size
means that the embeddings might be more general but might miss specific details.
For example, if you convert 1,000 words into an embedding array that was meant
for 200 words, you might lose details. The embedding capacity is fixed for each
chunk. A large chunk of text may not fit into a small-window model.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Fine-tune RAG transformations\n\n| The [VPC-SC security controls](/vertex-ai/generative-ai/docs/security-controls) and\n| CMEK are supported by Vertex AI RAG Engine. Data residency and AXT security controls aren't\n| supported.\n\nAfter a document is ingested, Vertex AI RAG Engine runs a set of transformations to\nprepare the data for indexing. You can control your use cases using the\nfollowing parameters:\n\nA smaller chunk size means the embeddings are more precise. A larger chunk size\nmeans that the embeddings might be more general but might miss specific details.\n\nFor example, if you convert 1,000 words into an embedding array that was meant\nfor 200 words, you might lose details. The embedding capacity is fixed for each\nchunk. A large chunk of text may not fit into a small-window model.\n\nWhat's next\n-----------\n\n- Use [Document AI layout parser with Vertex AI RAG Engine](/vertex-ai/generative-ai/docs/layout-parser-integration)."]]