Oracle Updated 1z0-1157-26 Exam Questions and Answers by damien

For production OCI Enterprise AI workloads, Oracle recommends OCI IAM-based authentication rather than long-lived development credentials. The uploaded source identifies OCI IAM authentication with signed requests and IAM policies as the correct production architecture.

Oracle's OCI Responses API authentication documentation distinguishes service API keys used for testing and early development from IAM authentication intended for production and OCI-managed environments. IAM-based authentication uses OCI identity principals and request-signing mechanisms and allows authorization to be controlled through centralized IAM policies. Oracle specifically recommends IAM when applications execute in services such as OCI Functions or Oracle Kubernetes Engine, when long-lived API keys should be avoided, or when fine-grained centralized access control is required.

IAM policies also implement least privilege by defining exactly which users, groups, resource principals, or workloads can access individual Generative AI resource types.

Browser cookies, anonymous tenancy access, and credentials committed into source repositories violate standard enterprise security practices and significantly increase credential-exposure risk.

Therefore, A is the only production-grade authentication approach among the choices.

Study Guide reference/topic: OCI Enterprise AI Agents — OCI IAM, signed requests, policies, principals, least privilege, and production authentication.

===============

Oracle AI Vector Search defines VECTOR_DISTANCE as the primary SQL function for calculating the distance between two vectors. When the function is called without explicitly specifying a distance metric, Oracle specifies COSINE as the default metric for ordinary, non-BINARY vectors. Cosine distance measures the angular relationship between vector representations and is widely used for semantic similarity because embeddings with similar meaning tend to point in similar directions in vector space. Oracle treats BINARY vectors differently: their default metric is HAMMING. Euclidean, or L2, distance is supported but must be selected when required; it is not the general default. Levenshtein distance applies to string-edit comparisons, while bitwise XOR is not the default Oracle vector-distance metric. Therefore, for the scenario stated in the question, option C is the verified answer. Oracle Docs

===============

StrOutputParser is a LangChain output parser used to convert a language-model response into a standard Python string. In an LCEL pipeline such as prompt | model | StrOutputParser() , the prompt prepares the model input, the model generates an AIMessage or equivalent model output, and StrOutputParser extracts the textual content so downstream application code receives plain text.

LangChain's official documentation demonstrates this exact pattern by composing a prompt, chat model, and StrOutputParser() into a chain and then invoking the resulting runnable. The parser therefore operates after model inference ; it does not send the request to the model and does not maintain agent or tool history.

The uploaded source presents the chain fragment across separate lines and explicitly identifies “It extracts plain text from the model response” as the correct response.

This output-parsing stage is especially useful because it isolates application code from provider-specific response-object structures and provides a predictable string output from a LangChain runnable.

Study Guide reference/topic: LangChain for AI Agents — LCEL chains, Runnable composition, model output handling, and StrOutputParser.

===============

OCI Enterprise AI Agents supports a defined set of OpenAI-compatible agent tools through the OCI Responses API. Oracle's current documentation identifies File Search, Code Interpreter, Function Calling, and MCP Calling as supported tool categories.

File Search allows an agent to retrieve relevant information from indexed content and vector stores. Code Interpreter provides a controlled environment for computational or programmatic analysis. Function Calling lets the model request execution of application-defined functions with structured parameters. MCP Calling enables the agent to discover and invoke capabilities made available by remote Model Context Protocol servers. Together, these mechanisms allow an LLM to move beyond text generation and perform retrieval, computation, application actions, and standardized external-system integration.

Oracle additionally provides supporting agent resources such as Files, Vector Stores, Containers, Conversations, Projects, and memory capabilities, while SQL Search/NL2SQL is available as an OCI-native agent capability.

SSH, FTP, RDP, VCN routing, load balancing, SMS, and fax are not the four built-in tool categories identified in the OCI Enterprise AI Agents curriculum. Consequently, A is correct and agrees with the uploaded question set.

Study Guide reference/topic: OCI Enterprise AI Agents — File Search, Code Interpreter, Function Calling, MCP Calling, Vector Stores, and agent tools.

===============