Class that splits pages into smaller chunks. This is required because embedding models may not be able to analyze an entire page at once

A single page from a document Attributes: page_num (int): Page number (0-indexed) offset (int): If the text of the entire Do

Class to manage a search service. It can create indexes, and update or remove sections stored in these indexes To learn more, please visit ht

Represents a file stored either locally or in a data lake storage account This file might contain access control information about which user

Parses simple text into a Page object.

Helper that lazily creates a media describer and captions figures on demand.

Semantic chunk emitted by the splitter (may originate wholly within one page or be the result of a cross-page merge / trailing fragment carry-forw

Client wrapper that handles batching, retries, and token accounting.

Concrete strategy for listing files that are located in a local filesystem

Manually enable document level access control on a search index and manually set access control values using the [manageacl.ps1](./scripts/manage

Concrete parser that can parse CSV into Page objects. By default, each row becomes its own Page object. When ``max_chars_per_page`` is s

Class representing a connection to a search service To learn more, please visit https://learn.microsoft.com/azure/search/search-what-is-azure

A section of a page that is stored in a search service. These sections are used as context by Azure OpenAI service

Concrete parser backed by Azure AI Document Intelligence that can parse many document formats into pages To learn more, please visit https://

Class to manage uploading and deleting blobs containing citation information from a blob storage account

Class for using image embeddings from Azure AI Vision To learn more, please visit https://learn.microsoft.com/azure/ai-services/computer-visi

Parses HTML text into Page objects.

Class that splits pages into smaller chunks based on a max object length. It is not aware of the content of the page. This is required becaus

Supported OpenAI hosting styles. OPENAI: Public OpenAI API. AZURE: Standard Azure OpenAI (service name becomes endpoint). AZ

Manager for Azure Data Lake Storage blob operations, particularly for user-specific file operations. Documents are stored directly in the use

Sets up a Data Lake Storage Gen 2 account with sample data and access control

A multi-step approach that first uses OpenAI to turn the user's question into a search query, then uses Azure AI Search to retrieve relevant

Concrete parser that can parse JSON into Page objects. A top-level object becomes a single Page, while a top-level array becomes multiple Page ob

Concrete parser backed by PyPDF that can parse PDFs into pages To learn more, please visit https://pypi.org/project/pypdf/

Builds OpenAI response messages from Jinja2 templates.

Migrator class for CosmosDB data migration.

Strategy for ingesting documents into a search service from files stored either locally or in a data lake storage account

Results from agentic retrieval including activities, documents, web results, SharePoint results, and optional answer.

Properties of a blob, with optional fields for content settings

Ingestion strategy that wires Azure Function custom skills into an indexer.

Represents a batch of text that is going to be embedded.

Harm severity levels reported by the Azure AI Evaluator service. These constants have been copied from the azure-ai-evaluation package, where

Strategy for ingesting and vectorizing documents into a search service from files stored storage account

Helper class to mock an async page from CosmosDB