Rolling two

Which statement best describes the core functionality and benefit of Retrieval Augmented Generation (RAG) in Oracle Database 23ai?. It allows users to train their own specialized LLMs directly within the Oracle Database environment using their internal data, thereby reducing the reliance on external Al providers. It primarily aims to optimize the performance and efficiency of LLMs by using advanced data retrieval techniques, thus minimizing response times, and reducing computational overhead. It empowers LLMs to interact with private enterprise data stored within the database, leading to more context-aware and precise responses to user queries. It enables Large Language Models (LLMs) to access and process real-time data streams from diverse sources to generate the most up-to-date insights.

What are the key advantages and considerations of using Retrieval Augmented Generation (RAG) in the context of Oracle Al Vector Search?. It leverages existing database security and access controls, thereby enabling secure and controlled access to both the database content and the LLM. It excels at optimizing the performance and efficiency of LLM inference through advanced caching and precomputation techniques, leading to faster response times but potentially increasing storage requirements. It focuses on training specialized LLMs within the database environment for specific tasks, offering greater control over model behavior and data privacy but potentially requiring more developer effort. It prioritizes real-time data extraction and summarization from various sources to ensure the LLM always has the most up-to-date information.

In the following Python code, what is the significance of prepending the source filename to each text chunk before storing it in the vector database? … Docs = [('text': filename + ‘ | ’ + section, 'path': filename) for filename, sections in faqs.items() for section in sections] # Sample the resulting data docs [:2] …. It speeds up the vectorization process by providing a unique identifier for each chunk. It helps differentiate between chunks from different files but has no impact on vectorization. It improves the accuracy of the LLM by providing additional training data. It preserves context and aids in the retrieval process by associating each vectorized chunk with its original source file.

How does an application use vector similarity search to retrieve relevant information from a database, and how is this information then integrated into the generation process?. Clusters similar text chunks and randomly selects one from the most relevant cluster. Encodes the question and database chunks into vectors, finds the most similar using cosine similarity, and includes them in the LLM prompt. Trains a separate LLM on the database and uses it to answer, ignoring the general LLM. Converts the question to keywords, searches for matches, and inserts the text into the response.

Which Python library is used to vectorize text chunks and the user's question in the following example? … import oracledb connection = oracledb.connect (user=un, password=pw, dsn=cs) table_name = 'faqs' with connection.cursor () as cursor: #Create the table create_table_sql = f””” CREATE TABLE IF NOT EXISTS (table_name) ( id NUMBER PRIMARY KEY, payload CLOB CHECK (payload IS JSON), vector VECTOR )””” try: cursor.execute (create_table_sql) except oracledb.DatabaseError as e: raise connection.autocommit True from sentence_transformers import SentenceTransformer encoder = SentenceTransformer ('all-MiniLM-L12-v2') …. sentence_transformers. oci. json. oracledb.

What is the function of the COSINE parameter in the SQL query used to retrieve similar vectors? … topK = 3 sql =f"""select payload, vector_distance (vector, :vector, COSINE) as score from (table_name} order by score fetch approx first (topK) rows on …. It filters out vectors with a cosine similarity below a certain threshold. It converts the vectors to a format compatible with the SQL database. It specifies the type of vector encoding used in the database. It indicates that the cosine distance metric should be used to measure similarity between vectors.

Which Oracle Cloud Infrastructure (OCI) service is directly integrated with Select AI?. OCI Languaje. OCI Data Science. OCI Generative AI. OCI Vision.

In the context of Select Al, what is an "Al Profile," and what purpose does it serve?. It is a machine learning model trained on specific data sets to enhance the accuracy of natural language query processing. It encapsulates connection information for an Al provider, including security credentials, provider name, model name, and a list of target tables. It is a user profile that stores preferences for data visualization and reporting in Select Al applications. It is a security feature that restricts access to sensitive data within Select Al applications.

What is the purpose of the policy created in the Select Al practice environment setup?. To enforce data encryption protocols. To define backup and recovery procedures. To enable access to OCI Generative Al.

You need to prioritize accuracy over speed in a similarity search for a dataset of images. Which approach should you use?. Approximate similarity search with IVF indexing and target accuracy of 70%. Exact similarity search using a full table scan. Approximate similarity search with HNSW indexing and target accuracy of 70%. Multivector similarity search with partitioning.

What is the advantage of using Euclidean Squared Distance rather than Euclidean Distance in similarity search queries?. It guarantees higher accuracy than Euclidean Distance. It is simpler and faster because it avoids square-root calculations. It supports hierarchical partitioning of vectors. It is the default distance metric for Oracle Al Vector Search.

Which SQL query would retrieve the top-10 vectors based on Euclidean distance using exact similarity search?. SELECT docID FROM vector_tab ORDER BY VECTOR_DISTANCE (embedding, :query_vector, EUCLIDEAN) FETCH EXACT FIRST 10 ROWS ONLY;. SELECT docID FROM vector_tab ORDER BY VECTOR_DISTANCE (embedding, :query_vector, COSINE) FETCH EXACT FIRST 10 ROWS ONLY;. SELECT docID FROM vector_tab WHERE VECTOR DISTANCE (embedding, :query_vector, EUCLIDEAN) < 10;. SELECT docID FROM vector_tab GROUP BY VECTOR_DISTANCE (embedding, :query_vector, EUCLIDEAN) FETCH FIRST 10 ROWS ONLY;.

What is the primary purpose of a similarity search in Oracle Database 23ai?. To compute distances between all data points in a database. To retrieve the most semantically similar entries using distance metrics between different vectors. To optimize relational database operations. To find exact matches in BLOB data.

Which is NOT a feature or capability related to Al and Vector Search in Exadata?. Native Support for Vector Search Only within the Database Server. Vector Replication with GoldenGate. Loading Vector Data using SQL*Loader. Al Smart Scan.

Which SQL statement correctly adds a VECTOR column named v with 4 dimensions and FLOAT32 format to an existing table named my_table?. ALTER TABLE my_table ADD v VECTOR (4, FLOAT32). ALTER TABLE my_table MODIFY (v VECTOR (4, FLOAT32)). ALTER TABLE my_table ADD (v VECTOR (4, FLOAT32)). UPDATE my_table SET v = VECTOR (4, FLOAT32).

Which DDL operation is NOT permitted on a table containing a VECTOR column in Oracle Database 23ai?. Dropping an existing VECTOR column from the table. Modifying the data type of an existing VECTOR column to a non-VECTOR type. Adding a new VECTOR column to the table. Creating a new table using CTAS CREATE TABLE AS SELECT that includes the VECTOR column from the original table.

A machine learning team is using IVF indexes in Oracle Database 23ai to find similar images in a large dataset. During testing, they observe that the search results are often incomplete, missing relevant images. They suspect the issue lies in the number of partitions probed. How should they improve the search accuracy?. Increase the VECTOR_MEMORY_SIZE initialization parameter. Change the index type to HNSW for better accuracy. Re-create the index with a higher EFCONSTRUCTION value. Add the TARGET ACCURACY clause to the query with a higher value for the accuracy.

What happens when querying with an IVF index if you increase the value of the NEIGHBOR PARTITION PROBES parameter?. Index creation time is reduced. Accuracy decreases. The number of centroids decreases. More partitions are probed, improving accuracy, but also increasing query latency.

What is a key advantage of generating vector embeddings outside the database?. Reduced storage requirements. Improved data security. Flexibility in choosing specialized embedding models. Simplified data management.

You are working with vector search in Oracle Database 23ai and need to ensure the integrity of your vector data during storage and retrieval. Which factor is crucial for maintaining the accuracy and reliability of your vector search results?. Regularly updating vector embeddings to reflect changes in the source data. The physical storage location of the vector data. The specific distance algorithm employed for vector comparisons. Using the same embedding model for both vector creation and similarity search.

When generating vector embeddings outside the database, what is the most suitable option for storing the embeddings for later use?. In a CSV file. In a binary FVEC file with the relational data in a CSV file. In the database as BLOB (Binary Large Object) data. In a dedicated vector database.

Which SQL operation is NOT supported when working with VECTOR columns in Oracle Database 23ai?. INSERT INTO statements. Loading data with SQL*Loader. Distance computations using custom distance functions. JOIN conditions.

Which SQL statement will successfully insert a vector into a table named my table with a single VECTOR column named v?. INSERT INTO my_table (v) VALUES (1.1, 2.2, 3.3). INSERT INTO my_table VALUES ((1.1, 2.2, 3.3)). INSERT INTO my_table (v) VALUES ('[1.1, 2.2, 3.3]'). INSERT INTO my_table VALUES ('(1.1, 2.2, 3.3}').

A retail company uses an Oracle Database 23ai HNSW vector index to recommend products to customers based on their browsing history. The database administrator notices that the after restarting the database, product recommendations are slower. What steps should the administrator take to resolve the issue?. Adjust the NEIGHBOR PARTITION PROBES parameter for improved accuracy. Modify the distance metric to DOT. Decrease the VECTOR_MEMORY_SIZE parameter. Rebuild the HNSW index or enable automatic reload.

Which parameter is used to define the number of closest vector candidates considered during HNSW index creation?. NEIGHBORS. TARGET_ACCURACY. EFCONSTRUCTION. VECTOR_MEMORY_SIZE.

What is the purpose of the Vector Pool in Oracle Database 23ai?. To enable longer SQL execution. To manage database partitioning. To store non-vector data types. To store HNSW vector indexes and IVF index metadata.

Which is NOT a valid distance metric for vector indexing in Oracle Database 23ai?. Cosine. Hamming. Euclidean. Binary Search.

Which vector index available in Oracle Database 23ai is known for its speed and accuracy, making it a preferred choice for vector search?. Inverted File System (IFS) index. Hierarchical Navigable Small World (HNSW) index. Full-Text (FT) index. Binary Tree (BT) index.

What is the primary difference between the HNSW and IVF vector indexes in Oracle Database 23ai?. HNSW is partition based, whereas IVF uses neighbor graphs for indexing. HNSW guarantees accuracy, whereas IVF sacrifices performance for accuracy. HNSW uses an in-memory neighbor graph for faster approximate searches, whereas IVF use the buffer cache with partitions. Both operate identically but differ in memory usage.

What is one type of notebook used for interacting with Select Al?. Wyde Rule Notebooks. Oracle Machine Learning (OML) Notebooks. ROCE Notebooks.

What does a target accuracy of 80% in an approximate similarity search imply?. The search will process 80% of the dataset. 80% of the query results will match the exact search results. 80% accuracy seen in the index calculated distances. Only 80% of the indexed vectors are used.

Which is a characteristic of an approximate similarity search in Oracle Database 23ai?. It always guarantees 100% accuracy. It trades off accuracy for faster performance. It compares every vector in the dataset. It is slower than exact similarity search.

You need to generate a vector from the string '[1.2, 3.4]' in FLOAT32 format with 2 dimensions. Which function will you use?. FROM_VECTOR. TO_VECTOR. VECTOR_SERIALIZE. VECTOR_DISTANCE.

What does the VECTOR_NORM function return?. The negated dot product of two vectors. The number of dimensions of a vector. The angle between two vectors. The Euclidean norm or distance between the vector and the origin.

What is the primary purpose of the VECTOR_EMBEDDING function in Oracle Database 23ai?. To serialize vectors into a string. To calculate vector distances. To generate a single vector embedding for data. To calculate vector dimensions.

In Oracle Database 23ai, which SQL function is used to split text into words, sentences, or paragraphs for vector embedding preparation?. VECTOR_NORM. VECTOR_EMBEDDING. VECTOR_CHUNKS. VECTOR_DISTANCE.

You are tasked with finding the closest matching sentences across books, where each book has multiple paragraphs and sentences. Which SQL structure should you use?. A nested query with ORDER BY. Exact similarity search with a single query vector. FETCH PARTITIONS BY clause. GROUP BY with vector operations.

An application needs to fetch the top-3 matching sentences from a dataset of books while ensuring a balance between speed and accuracy. Which query structure should you use?. Approximate similarity search with the VECTOR_DISTANCE function. A combination of relational filters and similarity search. Exact similarity search with Euclidean distance. Multivector similarity search with approximate fetching and target accuracy.

What is the significance of using local ONNX models for embedding within the database?. Reduced embedding dimensions for faster processing. Enhanced security because data remains within the database. Support for legacy SQL*Plus clients. Improved accuracy compared to external models.

What is the primary function of an embedding model in the context of vector search?. To execute similarity search operations within a database. To define the schema for a vector database. To transform text or data into numerical vector representations. To store vectors in a structured format for efficient retrieval.

In Oracle Database 23ai, which SQL function calculates the distance between two vectors using the Euclidean metric?. L2_DISTANCE. L1_DISTANCE. COSINE_DISTANCE. HAMMING DISTANCE.

What is the default distance metric used by the VECTOR DISTANCE function if none is specified?. Cosine. Manhattan. Hamming. Euclidean.

Which statement best describes the capability of Oracle Data Pump for handling vector data in the context of vector search applications?. Because of the complexity of vector data, Data Pump requires a specialized plug-in to handle the export and import operations involving vector data types. Data Pump treats vector embeddings as regular text strings, which can lead to data corruption or loss of precision when transferring vector data for vector search. Data Pump can only export and import vector data if the vector embeddings are stored as BLOB (Binary Large Object) data types in the database. Data Pump provides native support for exporting and importing tables containing vector data types, facilitating the transfer of vector data for vector search applications.

In Oracle Database 23ai, which data type is used to store vector embeddings for similarity search?. VARCHAR2. VECTOR. VECTOR2. BLOB.

Why would you choose to NOT define a specific size for the VECTOR column during development?. Different external embedding models produce vectors with varying dimensions and data types. It impacts the accuracy of similarity searches. It restricts the database to a single embedding model. It limits the length of text that can be vectorized.

When using SQL*Loader to load vector data for search applications, what is a critical consideration regarding the formatting of the vector data within the input CSV file?. Use sparse format for vector data. Rely on SQL*Loader's automatic normalization of vector data. As FVEC is a binary format and the vector dimensions have a know width, fixed offsets can be used to make parsing the vectors fast and efficient. Enclose vector components in curly braces ({}).

Which SQL function is used to create a vector embedding for a given text string in Oracle Database 23ai?. VECTOR_EMBEDDING. CREATE_VECTOR_EMBEDDING. EMBED_TEXT. GENERATE_EMBEDDING.

Which PL/SQL package is primarily used for interacting with Generative Al services in Oracle Database 23ai?. DBMS_ML. DBMS_GENAI. DBMS_VECTOR CHAIN. DBMS_AI.

What is the primary purpose of the DBMS_VECTOR_CHAIN.UTL_TO_CHUNKS package in a RAG application?. To generate vector embeddings from a text document. To convert a document into a single, large text string. To split a large document into smaller chunks to improve vector quality by minimizing token truncation. To load a document into the database.

Which PL/SQL function converts documents such as PDF, DOC, JSON, XML, or HTML to plain text?. DBMS_VECTOR.TEXT_TO_PLAIN. DBMS_VECTOR_CHAIN.UTIL_TO_CHUNKS. DBMS_VECTOR.CONVERT_TO_TEXT. DBMS_VECTOR_CHAIN.UTL_TO_TEXT.