CCNA OCI Generative AI Service Questions

On-demand pricing can be expensive at high volumes. Dedicated clusters offer predictable cost per model unit and low-latency dedicated inference, making them more cost-effective for high-volume, latency-sensitive workloads. Pay-as-you-go (on-demand) is suitable for low or variable usage.

RAG allows the LLM to retrieve relevant document sections at inference time, so knowledge stays current without retraining.

A knowledge base must be created and linked to the data source (Object Storage bucket) so the agent can index and retrieve the content. Creating an agent first without a knowledge base would not work. The Embedding API is lower-level; the agent service abstracts this.

OCI Generative AI provides embed-multilingual-v3.0 for multilingual support. The input type 'search_query' is designed for query embeddings. Embed-english-v3.0 is English-only. 'search_document' is for documents, not queries. 'classification' is for classification tasks.

Cohere embed-english-v3.0 is the embedding model for English text. The other options are either generative models or multilingual embedding models.

OCI fine-tuning requires a specific JSONL format with 'prompt' and 'completion' keys. If the keys are named differently (e.g., 'input'/'output'), validation fails. Model units, compartment, and base model are not typically validation issues.

OCI GenAI offers Cohere Command R, Command R+, Meta Llama 3, Cohere Embed models, and Cohere Rerank. GPT-4 is an OpenAI model and is not available in OCI GenAI.

Fine-tuning with T-Few typically requires at least 1000 examples for meaningful learning. The dataset size is likely insufficient.

The 'use' verb on genai-family resources allows inference and use of models/endpoints without permitting management (create/update/delete). This matches the requirement.

OCI GenAI fine-tuning expects a JSONL file with prompt/completion pairs.

In OCI Generative AI Agents, a data source points to Object Storage buckets and indexes the documents. Knowledge bases combine data sources, but the first step is creating the data source.

Dedicated AI clusters provide isolated, low-latency inference for custom fine-tuned models. Shared infrastructure is multi-tenant and may have variable latency; on-demand inference does not support custom models directly.

IAM policies restrict access to data, placing documents in the correct compartment, and creating a knowledge base pointing to that compartment are required. Creating a dedicated cluster and using the Embedding API directly are not necessary steps for the agent.

The system prompt (or preamble) sets the assistant's behavior consistently. Temperature affects randomness but not tone directly.

To ground the agent in provided documents, they should use a knowledge base, set a preamble to restrict knowledge, and disable internet search. Fine-tuning is not needed.

RAG (Retrieval-Augmented Generation) allows the LLM to retrieve relevant document sections at inference time, so knowledge stays current without retraining. The other options either require expensive retraining for each update or lack document grounding.

The 'preamble_override' parameter sets the system-level instruction (e.g., 'You are a formal assistant...') that persists across turns. The other options control generation statistics, not system behavior.

The 'allow group <group_name> to use generative-ai-family in compartment <compartment_name>' policy grants access to all GenAI resources within that compartment. The other options either miss the compartment scope or use incorrect verbs.

The Sessions API is used to manage conversational sessions with OCI GenAI Agents, allowing multi-turn interactions. The Chat API is for direct LLM chat without agent capabilities. The Generate API is for single-turn text generation, and the Embedding API is for vector creation.

The Embeddings API supports input types like 'classification' and 'clustering' which optimize embeddings for those tasks. 'search_document' and 'search_query' are for search. 'text' is not a valid input type.

It uses the 'use' verb to grant the data scientists access to OCI Generative AI resources while adding a condition with 'request.operation != 'CreateDedicatedAiCluster'' to explicitly deny the ability to create Dedicated AI Clusters. In OCI IAM, the 'use' verb includes read and update capabilities but not create or delete, and the condition further restricts the specific create operation, aligning with the requirement to prevent cluster creation.

A Dedicated AI Cluster provides exclusive, low-latency inference with reserved capacity, unlike shared infrastructure where resources are contended.

The 'allow group to use generative-ai-family in compartment' is the standard OCI IAM policy for granting access to all GenAI resources in a compartment. The other options have incorrect resource types or conditions.

Cohere Command R (or R+) supports multilingual input and output natively, so fine-tuning is unnecessary. Using the embed-multilingual-v3.0 model for embedding customer queries enables multilingual semantic search if RAG is used. Embed-english-v3.0 only supports English, and Llama 3 is primarily English-focused.

The Generate API uses 'preamble_override' to set a system instruction for the completion. The 'system' parameter is for the Chat API. 'max_tokens' and 'temperature' are not system instructions.

Frequency penalty penalizes tokens that have already appeared in the text, reducing repetition. Temperature increases randomness, top_p changes nucleus sampling, and max tokens controls length.

OCI Generative AI fine-tuning expects a JSONL file where each line is a JSON object containing a prompt and completion (or response) field. This format pairs input with expected output for supervised fine-tuning.

RAG (Retrieval-Augmented Generation) allows the LLM to retrieve relevant document sections at inference time, so knowledge stays current without retraining. The other options either require expensive retraining for each update or lack document grounding.

The Playground allows interactive testing with parameter adjustment and system prompts. It does not allow fine-tuning or creating dedicated clusters.

T-Few is a parameter-efficient fine-tuning technique that updates only a small fraction of model parameters.

Fine-tuning requires a base model and a training dataset. The other options are optional or configurable later.

The cost of model units per hour and the expected token volume help determine whether dedicated or on-demand is more economical. Cluster provisioning time and streaming availability are not direct cost factors.

Decreasing temperature makes output more deterministic; increasing frequency penalty discourages repetition of phrases.

Cohere embed-multilingual-v3.0 supports multiple languages in a single model, enabling cross-lingual semantic search. embed-english-v3.0 is English-only. Command R and Llama 3 are not embedding models.

The T-Few fine-tuning technique is a parameter-efficient fine-tuning (PEFT) method that updates only a small fraction of the model's parameters, typically by introducing and training adapter layers or using low-rank updates. This approach significantly reduces computational and memory requirements compared to full fine-tuning, making it suitable for adapting large language models with limited resources. In OCI Generative AI, T-Few enables efficient customization without retraining the entire model.

The max_tokens parameter controls the maximum length of the generated output. Increasing it allows longer summaries, preventing truncation.

Cohere Rerank is the OCI Generative AI model family specifically designed for reranking search results to improve relevance. Unlike generation-focused models, Rerank takes a query and a list of candidate documents, scoring each for relevance to the query, thereby enhancing the quality of retrieved results in RAG pipelines.

The 'use' verb allows access to GenAI resources. The policy should target the specific compartment.

OCI Generative AI Agents require a knowledge base to index data sources before creating an agent.

The dataset must be uploaded to an OCI Object Storage bucket so the fine-tuning job can access it. The other options are either optional or not required.

Preamble override allows setting a system message that guides the model's behavior, helping to keep responses on topic. Adjusting it is a low-cost intervention.

In OCI Generative AI, the correct sequence for deploying a fine-tuned model to a dedicated endpoint is: first provision a Dedicated AI Cluster (which provides the isolated compute infrastructure), then deploy the model to that cluster, and finally create an endpoint that exposes the deployed model for inference. This ensures the model is hosted on dedicated resources before the endpoint is created.