# Vectara Documentation > Developer documentation for Vectara — for building trusted enterprise AI agents This file contains links to documentation sections following the llmstxt.org standard. ## Table of Contents - [Build with coding agents](https://docs.vectara.com/docs/agent-skills-for-coding-agents.md): Vectara is a headless platform. **Your application is yours** — - [Concepts](https://docs.vectara.com/docs/agents/agent-concepts.md): Agents are autonomous systems that understand natural language and use tools - [Built-in tools](https://docs.vectara.com/docs/agents/agent-tools.md): Tools provide agents with capabilities to interact with data and external - [Quickstart](https://docs.vectara.com/docs/agents/agents-quickstart.md): This guide walks you through creating and configuring a Research - [Agent](https://docs.vectara.com/docs/agents/agents.md): Agents are autonomous systems that understand natural language and use tools - [Alias workflows and best practices](https://docs.vectara.com/docs/agents/alias-patterns.md): An alias puts a stable name in front of your agents and lets a policy decide - [Route sessions with an alias](https://docs.vectara.com/docs/agents/alias-routing.md): Use this guide to put an alias in front of your agents and route sessions - [Agent aliases](https://docs.vectara.com/docs/agents/aliases.md): An agent alias is a stable public name that routes each new session to an - [Artifacts](https://docs.vectara.com/docs/agents/artifacts.md): Artifacts give an agent access to files and documents without storing them in - [Box tools for agents](https://docs.vectara.com/docs/agents/box-tools.md): Seventeen tools let an agent work directly against Box: search and read content, change it, and collaborate on it. They are separate from the [Box ... - [Build with io](https://docs.vectara.com/docs/agents/build-agents-with-io.md): **io** is Vectara's AI assistant for building with the platform. It is available in the [Vectara Console](https://console.vectara.com/signup) and a... - [Compaction](https://docs.vectara.com/docs/agents/compaction.md): **Compaction** keeps a session alive past the model's context window - [Call other tools from lambda tools](https://docs.vectara.com/docs/agents/composable-lambda-tools.md): A [lambda tool](/docs/agents/lambda-tools) can call other tools — searches, - [Confluence tools for agents](https://docs.vectara.com/docs/agents/confluence-tools.md): Nineteen tools let an agent work directly against Confluence Cloud: discover spaces, search and read pages, create content, and edit pages in place... - [Connector authentication patterns](https://docs.vectara.com/docs/agents/connector-authentication.md): Every enterprise integration needs credentials. Google Drive, GitHub, - [Context engineering](https://docs.vectara.com/docs/agents/context-engineering.md): **Context engineering** is the deliberate crafting of everything the LLM - [Conversational AI](https://docs.vectara.com/docs/agents/conversational-ai.md): Build conversational AI without having to choose between accuracy and ease of - [Create and test lambda tools](https://docs.vectara.com/docs/agents/create-a-lambda-tool.md): To create a Lambda Tool with the API: - [Create agent example](https://docs.vectara.com/docs/agents/create-agent-examples.md): Let's create an agent with the API. - [Custom tools](https://docs.vectara.com/docs/agents/custom-tools.md): Custom tools extend agent capabilities. You can create tools once and reuse - [End user sessions](https://docs.vectara.com/docs/agents/end-user-sessions.md): Use end user sessions to let the people using your product talk to an agent - [Glossaries](https://docs.vectara.com/docs/agents/glossaries.md): User messages inside an organization are full of vocabulary the model has no - [Connect agents to Google Chat](https://docs.vectara.com/docs/agents/google-chat-connectors.md): Connect a Vectara agent to Google Chat so messages from a Chat app create or continue agent sessions and the agent replies in the same space or thr... - [Post to Google Chat from an agent](https://docs.vectara.com/docs/agents/google-chat.md): The `gchat_post_message` tool posts a message to a Google Chat space, optionally - [Google Drive tools for agents](https://docs.vectara.com/docs/agents/google-drive-tools.md): Fifteen tools let an agent work directly against Google Drive: find and read files, organize them, manage who has access, and work a file's comment... - [Instructions](https://docs.vectara.com/docs/agents/instructions.md): An agent's behavior is defined by the instructions you provide. The agent uses - [Integrations](https://docs.vectara.com/docs/agents/integrations.md): Integrations with a Vectara agent come in three flavors: feeding data in, giving the agent something it can call mid-turn, and routing messages to ... - [Lambda tools](https://docs.vectara.com/docs/agents/lambda-tools.md): As your AI agents take on more complex workflows, they might need to perform - [Memory](https://docs.vectara.com/docs/agents/memory.md): Most agent turns only see the current session's messages. Real agents - [Model Context Protocol (MCP)](https://docs.vectara.com/docs/agents/model-context-protocol.md): The Model Context Protocol (MCP) is an emerging and rapidly changing standard - [Multi-client steering](https://docs.vectara.com/docs/agents/multi-client-steering.md): This page covers two related capabilities: - [Reminders](https://docs.vectara.com/docs/agents/reminders.md): LLMs have a well-documented recency bias: the most recent tokens in the - [Secrets](https://docs.vectara.com/docs/agents/secrets.md): Secrets are named, encrypted credentials that tools can reference from `argument_override` via `{"$ref": ".secrets."}`. The value is s... - [Sessions](https://docs.vectara.com/docs/agents/sessions.md): Agents keep track of their conversations with sessions. One conversation is - [Skills](https://docs.vectara.com/docs/agents/skills.md): A common mistake when building an agent is to stuff every specialist - [Connect agents to Slack](https://docs.vectara.com/docs/agents/slack-connectors.md): Connect a Vectara agent to Slack channels to respond to mentions, maintain threaded conversations, and use Slack-specific tools. - [Steps](https://docs.vectara.com/docs/agents/steps.md): **Steps** let an agent move through distinct phases of a session while - [Structured indexing tool](https://docs.vectara.com/docs/agents/structured-indexing-tool.md): As agents handle more complex conetnt, they need a way to index structured - [Structured outputs](https://docs.vectara.com/docs/agents/structured-outputs.md): **Structured outputs** let you attach a JSON schema to a step's - [Sub-agents](https://docs.vectara.com/docs/agents/subagents.md): The sub-agent tool enables your agent to delegate specialized tasks to existing - [Tool-output offloading](https://docs.vectara.com/docs/agents/tool-offloading.md): A single oversized tool output — 500 SQL rows, a 3 MB API response, - [Register and configure a tool server](https://docs.vectara.com/docs/agents/tool-servers.md): Use this guide to register an MCP tool server with Vectara by selecting the right - [Tools](https://docs.vectara.com/docs/agents/tools.md): Tools provide agents with capabilities to interact with data and external - [Try our demo agent](https://docs.vectara.com/docs/agents/try-demo-agent.md): Use this guide to launch the **Semiconductor Knowledge Assistant**, a pre-configured agent that answers questions about semiconductors. Vectara cre... - [Tune retrieval for agents](https://docs.vectara.com/docs/agents/tune-retrieval-for-agents.md): This guide walks through how to get high-quality retrieval out of an agent - [Wrap a REST API with web_get](https://docs.vectara.com/docs/agents/web-get-tool.md): This is the no-code path for the **tools** surface described in [Integrations](/docs/agents/integrations): exposing a single third-party REST endpo... - [Connect agents to Zoom Contact Center](https://docs.vectara.com/docs/agents/zoom-connectors.md): Connect a Vectara agent to Zoom Contact Center so it answers customer engagements routed to the Zoom Contact Center chatbot surface. - [API Recipes](https://docs.vectara.com/docs/api-recipes.md): Explore common API patterns and use cases for building with Vectara. Each recipe shows complete request and response examples you can adapt for you... - [Agents APIs](https://docs.vectara.com/docs/api-reference/agent-apis/agent-apis-overview.md): The Vectara Agents APIs enable the development of intelligent agents - [Agent Management APIs](https://docs.vectara.com/docs/api-reference/agent-apis/agent-management.md): The Agent Management APIs enable you to create, configure, and manage Vectara - [Create Agent API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/create-agent.md): The Create Agent API lets you design and deploy smart AI agents capable of - [Delete Agent API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/delete-agent.md): The Delete Agent API enables you to permanently remove an AI agent and its configuration from the Vectara platform, supporting agent lifecycle mana... - [Interact with an Agent API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/event/create-agent-event.md): The Interact with an Agent API enables you to create new inputs to an agent to interact with it. This API serves as the primary interface for conve... - [Get Agent Event API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/event/get-agent-event.md): The Get Agent Event API enables you to retrieve detailed information about a specific interaction event within an agent session, providing comprehe... - [List Agent Events API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/event/list-agent-events.md): The List Agent Events API enables you to retrieve a chronological sequence of all interactions and processing activities within a specific agent se... - [Event Management APIs](https://docs.vectara.com/docs/api-reference/agent-apis/event-management.md): The Event Management APIs handle all interactions within agent sessions. - [Get Agent API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/get-agent.md): The Get Agent API enables you to retrieve the complete configuration and operational details of a specific AI agent, providing comprehensive visibi... - [Create Instruction API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/create-instruction.md): The Create Instruction API enables you to create reusable sets of behavioral guidelines that shape how AI agents reason, respond, and interact with... - [Delete Instruction Version API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/delete-instruction-version.md): The Delete Instruction Version API enables you to permanently remove a specific version of a behavioral instruction. This is useful for managing th... - [Delete Instruction API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/delete-instruction.md): The Delete Instruction API enables you to permanently remove a behavioral instruction from the Vectara platform. This is useful for decommissioning... - [Get Instruction API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/get-instruction.md): The Get Instruction API enables you to retrieve the full definition of a specific behavioral instruction by its ID. This allows you to inspect the ... - [List Instructions API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/list-instructions.md): The List Instructions API enables you to retrieve a paginated list of all behavioral instructions available to the authenticated user. This is usef... - [Test Instruction API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/test-instruction.md): The Test Instruction API enables you to validate the syntax and compilation of an instruction template written in Apache Velocity Template Language... - [Update Instruction API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/instruction/update-instruction.md): The Update Instruction API enables you to modify an existing behavioral instruction. This allows you to iterate on agent behavior, update guideline... - [Instruction Management APIs](https://docs.vectara.com/docs/api-reference/agent-apis/instruction-management.md): The Instruction Management APIs handle reusable instruction templates that - [List Agents API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/list-agents.md): The List Agents API enables you to retrieve a paginated list of all agents - [Replace Agent API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/replace-agent.md): The Replace Agent API enables you to completely replace an existing agent's configuration, including its corpora, tools, and generation presets. Th... - [Create Agent Session API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/session/create-agent-session.md): The Create Agent Session API enables you to initialize a new conversational session between users and AI agents, establishing the contextual contai... - [Delete Agent Session API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/session/delete-agent-session.md): The Delete Agent Session API enables you to permanently remove a conversational session and all its associated events and interaction history from ... - [Get Agent Session API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/session/get-agent-session.md): The Get Agent Session API enables you to retrieve detailed information about a specific conversational session, including its configuration, metada... - [List Agent Sessions API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/session/list-agent-sessions.md): The List Agent Sessions API enables you to retrieve a paginated collection of conversational sessions associated with a specific AI agent, providin... - [Update Agent Session API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/session/update-agent-session.md): The Update Agent Session API enables you to modify session metadata, descriptions, and operational status during active conversations, supporting d... - [Session Management APIs](https://docs.vectara.com/docs/api-reference/agent-apis/session-management.md): The Session Management APIs handle conversation contexts between users and - [Delete Tool API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool/delete-tool.md): The Delete Tool API enables you to remove a specific tool from the Vectara platform's tool catalog, supporting tool lifecycle management and cleanu... - [Get Tool API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool/get-tool.md): The Get Tool API enables you to retrieve the complete definition and configuration details of a specific tool discovered from Model Context Protoco... - [List Tools API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool/list-tools.md): The List Tools API enables you to retrieve and browse all available tools discovered from registered Model Context Protocol (MCP) compliant tool se... - [Update Tool API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool/update-tool.md): The Update Tool API enables you to modify the configuration of existing tools discovered from MCP servers. Currently, this API supports enabling or... - [Tool Management APIs](https://docs.vectara.com/docs/api-reference/agent-apis/tool-management.md): The Tool Management APIs handle individual tools available to agents, including both built-in tools and those discovered from MCP tool servers. - [Create Tool Server API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server/create-tool-server.md): The Create Tool Server API enables you to register Model Context Protocol (MCP) compliant servers that expose tools for use by AI agents. Tool serv... - [Delete Tool Server API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server/delete-tool-server.md): The Delete Tool Server API enables you to permanently remove a Model Context Protocol (MCP) server from your Vectara account. This action cascades ... - [Get Tool Server API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server/get-tool-server.md): The Get Tool Server API enables you to retrieve detailed information about a specific Model Context Protocol (MCP) server registered in your Vectar... - [List Tool Servers API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server/list-tool-servers.md): The List Tool Servers API enables you to retrieve and browse all registered Model Context Protocol (MCP) servers in your Vectara account. This API ... - [Sync Tool Server API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server/sync-tool-server.md): The Sync Tool Server API enables you to trigger synchronization of a registered MCP server to discover and update its available tools. This API ens... - [Update Tool Server API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server/update-tool-server.md): The Update Tool Server API enables you to modify the configuration of registered Model Context Protocol (MCP) servers. This API supports updating c... - [Tool Server Management APIs](https://docs.vectara.com/docs/api-reference/agent-apis/tool-server-management.md): The Tool Server Management APIs handle Model Context Protocol (MCP) tool - [Update Agent API Definition](https://docs.vectara.com/docs/api-reference/agent-apis/update-agent.md): The Update Agent API enables you to modify an existing AI agent's configuration, including tool assignments, behavioral instructions, model paramet... - [Chunking strategies](https://docs.vectara.com/docs/build/chunking-strategies.md): A chunking strategy controls how Vectara splits a **document** into **parts** during indexing. Each part is the unit of retrieval. It is what gets ... - [Data ingestion](https://docs.vectara.com/docs/build/data-ingestion.md): Preparing data powers effective search, retrieval, and operations in Vectara - [Data Types](https://docs.vectara.com/docs/build/prepare-data/metadata-filters/data-types.md): This section provides a list of the various data types supported by Vectara, - [Functions and Operators](https://docs.vectara.com/docs/build/prepare-data/metadata-filters/func-opr.md): Most operators in have the same precedence and are left-associative. - [Metadata Examples and Use Cases](https://docs.vectara.com/docs/build/prepare-data/metadata-filters/metadata-examples-and-use-cases.md): Metadata filters enable highly versatile and granular control over query - [Metadata filters](https://docs.vectara.com/docs/build/prepare-data/metadata-filters.md): This section helps you learn about metadata filter expressions and how to - [Vectara Ingest](https://docs.vectara.com/docs/build/prepare-data/vectara-ingest.md): Vectara Ingest crawls datasets from pre-built crawlers (websites, RSS feeds, - [Resource addressing](https://docs.vectara.com/docs/build/resource-addressing.md): When enterprises integrate Vectara into real business workflows, they need - [Visual data](https://docs.vectara.com/docs/build/visual-data.md): Vectara makes visual content, such as pictures, charts, and diagrams, retrievable in two ways: by indexing a **text representation** of the image, ... - [Table data](https://docs.vectara.com/docs/build/working-with-tables.md): Tables in PDFs are hard to query, because their structure is unpredictable and - [Build](https://docs.vectara.com/docs/build.md): To start building with Vectara, review the following sections: - [Documentation Changelog (Legacy)](https://docs.vectara.com/docs/changelog-legacy.md): This changelog tracks changes to Vectara's documentation. For product and feature releases, see the [Release Notes](/docs/release-notes). - [Documentation Changelog](https://docs.vectara.com/docs/changelog.md): This changelog tracks changes to Vectara's documentation — new and updated - [Chatbot Tutorials](https://docs.vectara.com/docs/chatbot-tutorials.md): Learn how to build intelligent chatbots with Vectara through hands-on tutorials. - [Console quickstart](https://docs.vectara.com/docs/console-quickstart.md): New users often find it challenging to get started with a new product and - [Vectara Admin Center](https://docs.vectara.com/docs/console-ui/admin-center.md): The Vectara Admin Center enables enterprise users to manage their on-premise - [Create an Agent](https://docs.vectara.com/docs/console-ui/agents/create-an-agent.md): This section provides a step-by-step procedure for creating a custom AI agent - [Example Agents](https://docs.vectara.com/docs/console-ui/agents/example-agents.md): This section provides example agents that you can create for your enterprise, - [Use Agents](https://docs.vectara.com/docs/console-ui/agents/use-agents.md): After creating an agent, you can chat with it directly in the Vectara Console. - [Types of API Keys](https://docs.vectara.com/docs/console-ui/api-access-overview-old.md): provides a comprehensive authorization system that accommodates a wide - [App Clients for OAuth](https://docs.vectara.com/docs/console-ui/app-clients.md): App clients provide the necessary pieces of information to [generate a JWT token](/docs/security/authentication/oauth-2#generate-a-jwt-token) - [Chat with Your Data](https://docs.vectara.com/docs/console-ui/chat-with-your-data.md): The Query tab of a corpus lets you enable chat with your corpus data. - [Configure Queries](https://docs.vectara.com/docs/console-ui/configure-queries.md): When you add data to a corpus, the **Query** tab lets you experiment with - [Upload Data to Corpus](https://docs.vectara.com/docs/console-ui/corpora/upload-data-to-corpus.md): You can upload data to the corpus from the **Data** tab. - [Create a Corpus](https://docs.vectara.com/docs/console-ui/creating-a-corpus.md): To begin searching your data, you first have to create a corpus. A corpus - [Configure Server Access to a Corpus](https://docs.vectara.com/docs/console-ui/configure-server-access-to-corpus.md): Follow the steps below to configure server access to a corpus. This access is - [Configure Default Read Access to a Corpus](https://docs.vectara.com/docs/console-ui/corpus-default-read-access.md): Sometimes, you’ll want to make a corpus searchable by any authenticated user. - [Delete Account](https://docs.vectara.com/docs/console-ui/delete-account.md): You can delete your account from the Manage account page or [this link](https://console.vectara.com/console/profile/deleteAccount). - [Index and Query API Keys](https://docs.vectara.com/docs/console-ui/index-and-query-api-keys.md): Index API Keys and Query API Keys enable user-facing applications to either - [Evaluate Queries](https://docs.vectara.com/docs/console-ui/evaluate-queries.md): Developers often struggle to understand why certain queries fall short of - [Manage Agents](https://docs.vectara.com/docs/console-ui/manage-agents.md): The Agents page displays all created agents, allowing you to monitor their - [API Authorization Methods](https://docs.vectara.com/docs/console-ui/api-access-overview.md): Vectara provides a comprehensive authorization system that accommodates a wide - [Conversations Overview](https://docs.vectara.com/docs/console-ui/conversations-overview.md): The Query tab le - [Manage Documents](https://docs.vectara.com/docs/console-ui/manage-documents.md): The Data view provides information about each document ingested into - [Manage Team Members](https://docs.vectara.com/docs/console-ui/manage-user.md): This section lets you add team members and manage the access levels of these - [Personal API Keys](https://docs.vectara.com/docs/console-ui/personal-api-key.md): The **Personal API Key** provides a broad range of functionality related to - [Delete Corpus, Disable Corpus, and Clear Corpus Data](https://docs.vectara.com/docs/console-ui/reset-or-delete-corpus.md): If you decide to stop using a corpus, you have three options on the corpus - [Manage Payments](https://docs.vectara.com/docs/console-ui/update-credit-card.md): The Billing page provides information about your product usage and current - [Vectara Console Overview](https://docs.vectara.com/docs/console-ui/vectara-console-overview.md): The Vectara Console enables you to create corpora, manage data and API access, - [Vectara Chat](https://docs.vectara.com/docs/console-ui/vectara-chat-overview.md): Vectara Chat provides an interactive user experience that enables you to build - [Definitions](https://docs.vectara.com/docs/definitions.md) - [Authentication and Authorization in Vectara](https://docs.vectara.com/docs/deploy-and-scale/authentication/authentication-authorization-vectara.md): Vectara’s authentication and authorization framework secures access to our - [Transport Layer Security (TLS)](https://docs.vectara.com/docs/deploy-and-scale/authentication/transport-layer-security.md): All communication to and from the API endpoints take place using an encrypted - [Private deployment options](https://docs.vectara.com/docs/deployments/deployment-options.md): A private deployment of Vectara is designed to work with your existing - [Enable SSO using Okta with OIDC](https://docs.vectara.com/docs/deployments/guides/vectara-okta-oidc.md): This guide explains how to enable Single Sign-On (SSO) to the Vectara Platform - [Private deployment guides](https://docs.vectara.com/docs/deployments/guides.md): Step-by-step guides for configuring and integrating your private deployment - [Private deployment evaluation process](https://docs.vectara.com/docs/deployments/onprem-evaluation-process.md): Ready to deploy Vectara in your infrastructure? [Contact us](https://www.vectara.com/contact-us) to get started. - [On prem and VPC deployment](https://docs.vectara.com/docs/deployments/private-deployment-overview.md): A Vectara private, on prem or VPC deployment provides the same platform capabilities - [Private deployment use cases](https://docs.vectara.com/docs/deployments/use-cases.md): Who deploys Vectara privately and why. - [Private Deployment](https://docs.vectara.com/docs/deployments.md): A private deployment of Vectara brings the full power of our agentic - [Summarize Tables with Custom Prompts](https://docs.vectara.com/docs/generation/custom-prompt-templates-customization.md): Vectara supports table summarization using LLMs during document upload. This - [Generation](https://docs.vectara.com/docs/generation.md): Generative AI, within the RAG context, empowers organizations to create precise, - [Generative Prompts](https://docs.vectara.com/docs/generative-prompts.md): Vectara provides powerful tools to design and customize prompt templates for - [JWTFetcher.cs](https://docs.vectara.com/docs/getting-started-samples/JWTFetcher.cs.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [JwtFetcher.java](https://docs.vectara.com/docs/getting-started-samples/JwtFetcher.java.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestApiKeyQueries.cs](https://docs.vectara.com/docs/getting-started-samples/RestApiKeyQueries.cs.md): This is a complete example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at o... - [RestApiKeyQueries.java](https://docs.vectara.com/docs/getting-started-samples/RestApiKeyQueries.java.md): This is a complete example... - [RestCreateCorpus.java](https://docs.vectara.com/docs/getting-started-samples/RestCreateCorpus.java.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestDeleteCorpus.cs](https://docs.vectara.com/docs/getting-started-samples/RestDeleteCorpus.cs.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestDeleteDocument.cs](https://docs.vectara.com/docs/getting-started-samples/RestDeleteDocument.cs.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestDeleteDocument.java](https://docs.vectara.com/docs/getting-started-samples/RestDeleteDocument.java.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestIndex.java](https://docs.vectara.com/docs/getting-started-samples/RestIndex.java.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestIndexData.cs](https://docs.vectara.com/docs/getting-started-samples/RestIndexData.cs.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestQuery.java](https://docs.vectara.com/docs/getting-started-samples/RestQuery.java.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestQueryData.cs](https://docs.vectara.com/docs/getting-started-samples/RestQueryData.cs.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestResetCorpus.cs](https://docs.vectara.com/docs/getting-started-samples/RestResetCorpus.cs.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [RestUploadFile.java](https://docs.vectara.com/docs/getting-started-samples/RestUploadFile.java.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [app.js](https://docs.vectara.com/docs/getting-started-samples/app.js.md): This is a complete example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at o... - [createCorpus.php](https://docs.vectara.com/docs/getting-started-samples/createCorpus.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [create_corpus.js](https://docs.vectara.com/docs/getting-started-samples/create_corpus.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [deleteCorpus.php](https://docs.vectara.com/docs/getting-started-samples/deleteCorpus.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [deleteDocument.php](https://docs.vectara.com/docs/getting-started-samples/deleteDocument.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [delete_corpus.js](https://docs.vectara.com/docs/getting-started-samples/delete_corpus.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [delete_document.js](https://docs.vectara.com/docs/getting-started-samples/delete_document.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [getJwtToken.php](https://docs.vectara.com/docs/getting-started-samples/getJwtToken.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [indexDocument.php](https://docs.vectara.com/docs/getting-started-samples/indexDocument.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [index_document.js](https://docs.vectara.com/docs/getting-started-samples/index_document.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [query.js](https://docs.vectara.com/docs/getting-started-samples/query.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [queryData.php](https://docs.vectara.com/docs/getting-started-samples/queryData.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [queryDataApiKey.php](https://docs.vectara.com/docs/getting-started-samples/queryDataApiKey.php.md): This is a complete example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at o... - [resetCorpus.php](https://docs.vectara.com/docs/getting-started-samples/resetCorpus.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [reset_corpus.js](https://docs.vectara.com/docs/getting-started-samples/reset_corpus.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_api_key_queries.py](https://docs.vectara.com/docs/getting-started-samples/rest_api_key_queries.py.md): This is a complete example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at o... - [rest_create_corpus.py](https://docs.vectara.com/docs/getting-started-samples/rest_create_corpus.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_delete_corpus.py](https://docs.vectara.com/docs/getting-started-samples/rest_delete_corpus.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_delete_document.py](https://docs.vectara.com/docs/getting-started-samples/rest_delete_document.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_index_document.py](https://docs.vectara.com/docs/getting-started-samples/rest_index_document.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_query.py](https://docs.vectara.com/docs/getting-started-samples/rest_query.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_reset_corpus.py](https://docs.vectara.com/docs/getting-started-samples/rest_reset_corpus.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_upload_file.py](https://docs.vectara.com/docs/getting-started-samples/rest_upload_file.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [rest_util.py](https://docs.vectara.com/docs/getting-started-samples/rest_util.py.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [uploadFile.php](https://docs.vectara.com/docs/getting-started-samples/uploadFile.php.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [upload_file.js](https://docs.vectara.com/docs/getting-started-samples/upload_file.js.md): This is an example of using the platform via REST. For more sample code, including any dependencies this file has, please have a look at our GitHu... - [Getting started](https://docs.vectara.com/docs/getting-started.md): Welcome to Vectara! This section will help you choose the right starting path, create your first working application, and learn how Vectara support... - [Hallucination evaluation](https://docs.vectara.com/docs/hallucination-and-evaluation/hallucination-evaluation.md): Vectara uses the `Hughes Hallucination Evaluation Model` (HHEM) to assess the - [Vectara Open Eval Framework](https://docs.vectara.com/docs/hallucination-and-evaluation/open-eval-framework.md): The [Vectara Open RAG Eval framework](https://github.com/vectara/open-rag-eval) is an open-source Python - [Query observability](https://docs.vectara.com/docs/hallucination-and-evaluation/query-observability.md): As developers build generative AI applications, one of the biggest challenges - [Hallucination correction](https://docs.vectara.com/docs/hallucination-and-evaluation/vectara-hallucination-corrector.md): Hallucinations remain one of the most pressing challenges in deploying Large - [Community collaborations and partnerships](https://docs.vectara.com/docs/integrations/community-collaborations-and-partnerships.md): In collaboration with the larger generative AI community, Vectara integrates - [REST APIs](https://docs.vectara.com/docs/integrations/rest.md): The Vectara REST APIs give you programmatic access to the platform. All endpoints - [Vectara and Airbyte](https://docs.vectara.com/docs/integrations/vectara-and-airbyte.md): Vectara now functions as a [destination connector in Airbyte](https://docs.airbyte.com/integrations/destinations/vectara). Leveraging Airbyte’s sup... - [Vectara Kafka Connect Plugin](https://docs.vectara.com/docs/integrations/vectara-and-confluent.md): The **Vectara Kafka Connect Plugin** seamlessly integrates [Confluent Cloud](https://confluent.cloud/) - [Vectara and DataVolo](https://docs.vectara.com/docs/integrations/vectara-and-datavolo.md): DataVolo, powered by Apache NiFi, is designed for continuous, event-driven - [Vectara and Flowise](https://docs.vectara.com/docs/integrations/vectara-and-flowise.md): Flowise is an open-source UI tool that lets you build personalized LLM flows - [Vectara and LangChain](https://docs.vectara.com/docs/integrations/vectara-and-langchain.md): LangChain serves as an orchestration framework for building LLM-powered - [Vectara and LangFlow](https://docs.vectara.com/docs/integrations/vectara-and-langflow.md): LangFlow is a leading open-source no-code platform for building LLM-powered - [Vectara and LlamaIndex](https://docs.vectara.com/docs/integrations/vectara-and-llamaindex.md): LlamaIndex is an LLM orchestration framework that focuses more on the data - [Vectara and Speechmatics](https://docs.vectara.com/docs/integrations/vectara-and-speechmatics.md): Speechmatics provides real-time speech-to-text transcription with low latency - [Vectara and Unstructured.io](https://docs.vectara.com/docs/integrations/vectara-and-unstructured.md): Unstructured is a well known Python package for parsing and dealing with - [Tutorial Intro](https://docs.vectara.com/docs/intro.md): Let's discover **Docusaurus in less than 5 minutes**. - [AI Agents](https://docs.vectara.com/docs/learn/ai-agents.md): AI agents are autonomous systems that understand natural language, reason - [Structure your data](https://docs.vectara.com/docs/learn/document-data-structuring.md): Munging files into a structured data format helps preserve relationships - [Keyword search](https://docs.vectara.com/docs/learn/enable-keyword-text-matching.md): In some specialized fields such as legal, compliance, and technical - [Configure query summarization](https://docs.vectara.com/docs/learn/grounded-generation/configure-query-summarization.md): Summarization provides a chatbot-like experience to your users by enhancing - [Retrieval Augmented Generation (RAG)](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-overview.md): Retrieval Augmented Generation (RAG) ensures that generated content is both - [Response Languages](https://docs.vectara.com/docs/learn/grounded-generation/grounded-generation-response-languages.md): The `response_language` field in allows control of the language - [LLM selection](https://docs.vectara.com/docs/learn/grounded-generation/model-selection.md): Selecting the right model for your application helps you meet specific use - [Generation presets](https://docs.vectara.com/docs/learn/grounded-generation/select-a-summarizer.md): Extracting concise, relevant information from large sets of search results - [Default Metadata Filters](https://docs.vectara.com/docs/learn/metadata-search-filtering/ootb-metadata-filters.md): A few pieces of metadata expressions are filterable out of the box, including - [Mockingbird 2: Vectara's Advanced LLM for RAG](https://docs.vectara.com/docs/learn/mockingbird-llm.md): Generating accurate and reliable summaries from large datasets is a challenge. - [Querying table data](https://docs.vectara.com/docs/learn/querying-table-data.md): Tables in PDFs are hard to query, because their structure is unpredictable and - [Semantic Search Fundamentals](https://docs.vectara.com/docs/learn/semantic-search/semantic-search-overview.md): Vectara lets you build a semantic, LLM-powered search application. Semantic - [REST API 1.0 to 2.0 Migration](https://docs.vectara.com/docs/migration-guide-api-v2.md): :::warning Deprecation Notice - [Evaluate quality](https://docs.vectara.com/docs/observability.md): Vectara’s observability tools reveal detailed insights into query behavior, - [Dead letters](https://docs.vectara.com/docs/pipelines/dead-letters.md): When a record fails processing during a pipeline run, it's added to the - [Concepts](https://docs.vectara.com/docs/pipelines/pipeline-concepts.md): A pipeline has six parts: a **source** (where data comes from), a - [Quickstart](https://docs.vectara.com/docs/pipelines/pipelines-quickstart.md): A pipeline is an automated flow that pulls data from a source system — - [Session metadata](https://docs.vectara.com/docs/pipelines/session-metadata.md): When a pipeline run processes a source record, it creates a new agent session and - [Box](https://docs.vectara.com/docs/pipelines/sources/box.md): Ingest files from a Box enterprise, inheriting collaborations as document ACL. - [Confluence](https://docs.vectara.com/docs/pipelines/sources/confluence.md): Ingest pages from Confluence Cloud or Data Center, inheriting read restrictions as ACL. - [Docebo](https://docs.vectara.com/docs/pipelines/sources/docebo.md): Ingest a Docebo LMS course catalog, with each course's curriculum outline, skills, and category as filterable metadata. - [Fluid Topics](https://docs.vectara.com/docs/pipelines/sources/fluidtopics.md): Ingest documents, topics, or maps from a Fluid Topics tenant through the Knowledge Hub REST API. - [Google Drive](https://docs.vectara.com/docs/pipelines/sources/google-drive.md): Ingest files from Google Drive shared drives and My Drive folders. - [Amazon S3](https://docs.vectara.com/docs/pipelines/sources/s3.md): Ingest objects from an Amazon S3 bucket or any S3-compatible service. - [SCIM](https://docs.vectara.com/docs/pipelines/sources/scim.md): Ingest user profiles from any SCIM 2.0 service provider, with directory attributes as filterable metadata. - [SharePoint](https://docs.vectara.com/docs/pipelines/sources/sharepoint.md): Ingest files from a SharePoint site using Azure AD app-only credentials. - [Web](https://docs.vectara.com/docs/pipelines/sources/web.md): Ingest pages from a website by sitemap, crawl, or both. - [Wolken Forms](https://docs.vectara.com/docs/pipelines/sources/wolken-forms.md): Ingest end-user service catalog forms from a Wolken ServiceDesk instance. - [Wolken Knowledge Base](https://docs.vectara.com/docs/pipelines/sources/wolken-kb.md): Ingest knowledge-base articles from a Wolken ServiceDesk instance. - [Wolken ServiceDesk Sources](https://docs.vectara.com/docs/pipelines/sources/wolken-servicedesk.md): Ingest knowledge-base articles, service catalog forms, and tickets from a Wolken ServiceDesk instance. - [Wolken Tickets](https://docs.vectara.com/docs/pipelines/sources/wolken-tickets.md): Ingest incidents and service requests from a Wolken ServiceDesk instance. - [Sources](https://docs.vectara.com/docs/pipelines/sources.md): A source is where a pipeline reads records from. Each record is fed to a new agent - [Verification](https://docs.vectara.com/docs/pipelines/verification.md): By default, any agent session that completes without throwing an exception - [Agent anatomy](https://docs.vectara.com/docs/platform-architecture/agent-anatomy.md): An agent groups together a set of parts that each do one job. **This - [The application layer](https://docs.vectara.com/docs/platform-architecture/application-layer.md): Vectara is a headless platform. The **application layer** sits between the end user - [Context and memory](https://docs.vectara.com/docs/platform-architecture/context-and-memory.md): LLMs answer best when the right context is in their window at the right - [Knowledge](https://docs.vectara.com/docs/platform-architecture/knowledge.md): The agent's **knowledge** is everything you want it to know up front: - [The platform stack](https://docs.vectara.com/docs/platform-architecture/platform-stack.md): The Vectara platform is a stack of layers. Every application you build - [Request lifecycle](https://docs.vectara.com/docs/platform-architecture/request-lifecycle.md): What happens when a user sends a message to an agent? This page walks - [Tools and connectors](https://docs.vectara.com/docs/platform-architecture/tools-and-connectors.md): A Vectara agent reaches the outside world through three integration - [Workflows](https://docs.vectara.com/docs/platform-architecture/workflows.md): An agent is not limited to responding to a single prompt and can move through - [Understanding Vectara](https://docs.vectara.com/docs/platform-architecture.md): Vectara is an **API-first Agentic Platform**. The - [Custom Prompts with Metadata](https://docs.vectara.com/docs/prompts/custom-prompts-with-metadata.md): Vectara handles the system and user prompts automatically, but if you want to - [Prompts and templates](https://docs.vectara.com/docs/prompts/vectara-prompt-engine.md): The Vectara Prompt Engine empowers our users to customize templates using - [Quick Starts](https://docs.vectara.com/docs/quick-starts.md): Get started with Vectara in minutes. Choose the path that best fits your needs. - [Quickstart](https://docs.vectara.com/docs/quickstart.md): Build your first RAG application with Vectara in about five minutes. You create a corpus, upload a document, run a query, and get an AI-generated a... - [UserFn expression language](https://docs.vectara.com/docs/reference/userfn-language.md): UserFn is Vectara's small expression language for computing values - [Vectara Release Notes (Legacy)](https://docs.vectara.com/docs/release-notes-legacy.md): Keep up to date with all the latest features and product updates and - [Vectara Release Notes](https://docs.vectara.com/docs/release-notes.md): Here's where we keep you up to date with all the latest features and product - [A2A Protocol](https://docs.vectara.com/docs/rest-api/a-2-a-protocol.md): A2A Protocol - [Agent Aliases](https://docs.vectara.com/docs/rest-api/agent-aliases.md): Agent Aliases - [Agent Analytics](https://docs.vectara.com/docs/rest-api/agent-analytics.md): Agent Analytics - [Agent Connectors](https://docs.vectara.com/docs/rest-api/agent-connectors.md): Agent Connectors - [Agent End User Sessions](https://docs.vectara.com/docs/rest-api/agent-end-user-sessions.md): Agent End User Sessions - [Agent Identity](https://docs.vectara.com/docs/rest-api/agent-identity.md): Agent Identity - [Agent Schedules](https://docs.vectara.com/docs/rest-api/agent-schedules.md): Agent Schedules - [Agent Secrets](https://docs.vectara.com/docs/rest-api/agent-secrets.md): Agent Secrets - [Agent Sessions](https://docs.vectara.com/docs/rest-api/agent-sessions.md): Agent Sessions - [Agents](https://docs.vectara.com/docs/rest-api/agents.md): Agents - [API Keys](https://docs.vectara.com/docs/rest-api/api-keys.md): API Keys - [Vectara REST API v2](https://docs.vectara.com/docs/rest-api/rest-api.md): The Vectara Platform to context engineer Enterprise Agents. - [Application Clients](https://docs.vectara.com/docs/rest-api/application-clients.md): Application Clients - [Authentication](https://docs.vectara.com/docs/rest-api/authentication.md): Authentication - [Bootstrap widget visitor](https://docs.vectara.com/docs/rest-api/bootstrap-widget.md): Returns the widget's presentation configuration and, when the widget admits anonymous visitors, a signed anonymous visitor id. - [Bulk delete documents from a corpus](https://docs.vectara.com/docs/rest-api/bulk-delete-corpus-documents.md): Initiates an asynchronous bulk delete operation for documents in a corpus. - [Bulk update document metadata](https://docs.vectara.com/docs/rest-api/bulk-update-corpus-document-metadata.md): Initiates an asynchronous bulk metadata update for documents in a corpus. - [Cancel A2A v0.3 task](https://docs.vectara.com/docs/rest-api/cancel-a-2-a-v-03-task.md): Cancels a running task. Returns the canonical state of the task after cancellation. If the task is already terminal, returns `409`. - [Cancel A2A v1 task](https://docs.vectara.com/docs/rest-api/cancel-a-2-a-v-1-task.md): Cancels a running task. Returns its state after cancellation in the v1 wire format. Returns `409` if the task is not currently running. - [Cancel pipeline run](https://docs.vectara.com/docs/rest-api/cancel-pipeline-run.md): Requests cancellation of an in-progress pipeline run. The run stops at the next checkpoint. It may take a moment to transition to the cancelled sta... - [Chats](https://docs.vectara.com/docs/rest-api/chats.md): Chats - [Compute the current size of a corpus](https://docs.vectara.com/docs/rest-api/compute-corpus-size.md): Computes the current size of a corpus. The size includes the number of documents, parts, and characters. The `corpus_key` uniquely identifies the c... - [Corpora](https://docs.vectara.com/docs/rest-api/corpora.md): Corpora - [Correct hallucinations in generated text](https://docs.vectara.com/docs/rest-api/correct-hallucinations.md): Detects and corrects factual inaccuracies, commonly referred to as hallucinations, in generated summaries or responses. The platform compares a use... - [Create an alias](https://docs.vectara.com/docs/rest-api/create-agent-alias.md): Creates an alias. An alias maps a public name to one or more underlying agents under a configurable policy. When you create a session through an al... - [Create agent connector](https://docs.vectara.com/docs/rest-api/create-agent-connector.md): Creates a connector for an agent to receive events from an external platform such as Slack, Google Chat, or Zoom Contact Center. - [Interact with an agent](https://docs.vectara.com/docs/rest-api/create-agent-input.md): Creates a new input event in the session to interact with the agent. - [Create agent schedule](https://docs.vectara.com/docs/rest-api/create-agent-schedule.md): Creates a schedule that runs an agent automatically at specified intervals. Each execution creates a new session with the configured message and me... - [Create agent session](https://docs.vectara.com/docs/rest-api/create-agent-session.md): Creates a new session for interacting with an agent. A session maintains state across all events, tool use, and agent responses produced during the... - [Create agent](https://docs.vectara.com/docs/rest-api/create-agent.md): Creates an agent. An agent is defined by three things: the **instructions** it follows, the **steps** it executes when it receives an input, and th... - [Submit input to alias-routed session](https://docs.vectara.com/docs/rest-api/create-alias-routed-input.md): Submits an input event to a session originally created via this alias. The session's resolved agent processes the event. - [Create session via alias](https://docs.vectara.com/docs/rest-api/create-alias-routed-session.md): Creates a session by routing through an alias. The alias's policy selects the underlying agent that owns the session. Subsequent operations on the ... - [Create an API key](https://docs.vectara.com/docs/rest-api/create-api-key.md): Creates an API key. You can bind the key to one or more corpora. A `personal` key has the same permissions as its owner; any other key carries exac... - [Create an App Client](https://docs.vectara.com/docs/rest-api/create-app-client.md): Creates an App Client. An App Client is used for OAuth 2.0 authentication when calling Vectara APIs. - [Create a chat completion](https://docs.vectara.com/docs/rest-api/create-chat-completion.md): Creates a chat completion for a multi-turn chat through an OpenAI-compatible interface. Applications built for the OpenAI Chat Completions format c... - [Create a new turn in the chat](https://docs.vectara.com/docs/rest-api/create-chat-turn.md): Creates a new turn in the chat. Each chat has a series of `turn` objects. Each turn is a message and response pair in the dialog. - [Start a chat](https://docs.vectara.com/docs/rest-api/create-chat.md): Creates a chat. The request specifies the default retrieval parameters that the prompt uses. - [Add a document to a corpus](https://docs.vectara.com/docs/rest-api/create-corpus-document.md): Adds a document to a corpus for indexing. Indexing makes the document content available for search, retrieval, and generation. This endpoint suppor... - [Create a corpus](https://docs.vectara.com/docs/rest-api/create-corpus.md): Creates a corpus to store and manage your documents. A corpus is a container for documents and their associated metadata. You can set the corpus ke... - [Create an encoder](https://docs.vectara.com/docs/rest-api/create-encoder.md): Creates a new encoder. - [Create end user input for alias](https://docs.vectara.com/docs/rest-api/create-end-user-alias-routed-input.md): Sends a message, an interrupt, or a client tool output to a session the caller owns, addressed by the alias it was created through. - [Create end user session for alias](https://docs.vectara.com/docs/rest-api/create-end-user-alias-routed-session.md): Creates a session owned by the calling end user, routed through this alias's policy. The session's owning principal is the caller's authenticated i... - [Create a generation preset](https://docs.vectara.com/docs/rest-api/create-generation-preset.md): Creates a custom generation preset for use in query and chat requests. A generation preset bundles a prompt template, an LLM, and model parameters ... - [Create glossary](https://docs.vectara.com/docs/rest-api/create-glossary.md): Creates a new glossary. A glossary is a reusable mapping of abbreviations, acronyms, and shorthand to their expansions. When terms in a user input ... - [Create instruction](https://docs.vectara.com/docs/rest-api/create-instruction.md): Creates an instruction that defines how an agent behaves, reasons, and responds. Instructions act as system-level guidelines that shape the agent's... - [Create an LLM](https://docs.vectara.com/docs/rest-api/create-llm.md): Creates a connection to an external Large Language Model (LLM) for Retrieval Augmented Generation (RAG) and chat. You can connect OpenAI API-compat... - [Create dead letter](https://docs.vectara.com/docs/rest-api/create-pipeline-dead-letter-entry.md): Manually adds a source record to the dead letter queue for reprocessing. Use this to force a record through the pipeline again, for example when th... - [Create pipeline](https://docs.vectara.com/docs/rest-api/create-pipeline.md): Creates a new pipeline that continuously ingests data from a source system and sends each record to an agent for processing. Each source record cre... - [Create tool server](https://docs.vectara.com/docs/rest-api/create-tool-server.md): Creates a tool server that exposes tools for use by agents. - [Create tool](https://docs.vectara.com/docs/rest-api/create-tool.md): Creates a tool that agents can call. Tools give agents capabilities to interact with external systems, process data, query corpora, or run custom l... - [Register trusted token issuer](https://docs.vectara.com/docs/rest-api/create-trusted-token-issuer.md): Registers a customer identity provider as a trusted issuer of end-user sign-in tokens. - [Create a user](https://docs.vectara.com/docs/rest-api/create-user.md): Creates a user in the current customer account. Use this endpoint to add users programmatically, assign roles, and set up access permissions. - [CustomerMetrics](https://docs.vectara.com/docs/rest-api/customer-metrics.md): CustomerMetrics - [Delete an alias](https://docs.vectara.com/docs/rest-api/delete-agent-alias.md): Deletes an alias. The underlying agents the alias points at are not affected. A platform-generated alias fronted by a widget connector cannot be de... - [Delete agent connector](https://docs.vectara.com/docs/rest-api/delete-agent-connector.md): Deletes an agent connector and all of its configuration. A widget connector's platform-generated alias is deleted with it. The deletion is permanent. - [Delete event](https://docs.vectara.com/docs/rest-api/delete-agent-event.md): Permanently deletes an event from a session. The event is erased and cannot be recovered. Unlike a hidden event, a deleted event cannot be restored. - [Delete agent schedule](https://docs.vectara.com/docs/rest-api/delete-agent-schedule.md): Deletes an agent schedule. This stops all future executions of the schedule. - [Delete agent session](https://docs.vectara.com/docs/rest-api/delete-agent-session.md): Permanently deletes an agent session. This action cannot be undone. - [Delete agent](https://docs.vectara.com/docs/rest-api/delete-agent.md): Deletes an agent and its configuration. Deletion is permanent. If active sessions or other constraints block the deletion, the request returns an e... - [Delete event on alias-routed session](https://docs.vectara.com/docs/rest-api/delete-alias-routed-event.md): Deletes a single event of a session originally created via this alias. - [Delete alias-routed session](https://docs.vectara.com/docs/rest-api/delete-alias-routed-session.md): Deletes a session originally created via this alias. - [Delete an API key](https://docs.vectara.com/docs/rest-api/delete-api-key.md): Deletes an API key. Delete a key when it is no longer needed or when it is compromised. - [Delete an App Client](https://docs.vectara.com/docs/rest-api/delete-app-client.md): Deletes an App Client from the customer account. - [Delete a turn](https://docs.vectara.com/docs/rest-api/delete-chat-turn.md): Deletes a turn from a chat. This also deletes all subsequent turns in the chat. - [Delete a chat](https://docs.vectara.com/docs/rest-api/delete-chat.md): Deletes a chat and all its turns permanently. - [Delete a document](https://docs.vectara.com/docs/rest-api/delete-corpus-document.md): Permanently deletes a document from a corpus. The unique `document_id` identifies the document. This operation cannot be undone, so use it with cau... - [Delete a corpus and all its data](https://docs.vectara.com/docs/rest-api/delete-corpus.md): Permanently deletes a corpus and all its associated data. The `corpus_key` uniquely identifies the corpus. - [Delete end user session for alias](https://docs.vectara.com/docs/rest-api/delete-end-user-alias-routed-session.md): Permanently deletes a session the caller owns, addressed by the alias it was created through. Returns 403 if the session belongs to a different pri... - [Delete a generation preset](https://docs.vectara.com/docs/rest-api/delete-generation-preset.md): Deletes an existing custom generation preset. - [Delete glossary entries](https://docs.vectara.com/docs/rest-api/delete-glossary-entries.md): Deletes entries from a glossary by term in bulk. The platform rebuilds the glossary index after the delete. Agents use the updated glossary after t... - [Delete glossary](https://docs.vectara.com/docs/rest-api/delete-glossary.md): Deletes a glossary and all its entries. - [Delete instruction version](https://docs.vectara.com/docs/rest-api/delete-instruction-version.md): Deletes the specified version of the instruction permanently. This action cannot be undone. - [Delete instruction](https://docs.vectara.com/docs/rest-api/delete-instruction.md): Deletes an instruction and all its associated configuration permanently. - [Delete an LLM](https://docs.vectara.com/docs/rest-api/delete-llm.md): Deletes a custom Large Language Model (LLM) configuration from the account. The deletion is permanent. Built-in LLMs cannot be deleted, so core sys... - [Delete dead letter](https://docs.vectara.com/docs/rest-api/delete-pipeline-dead-letter-entry.md): Deletes a dead letter from the queue. Use this to dismiss a known failure that does not need retrying. - [Delete pipeline](https://docs.vectara.com/docs/rest-api/delete-pipeline.md): Permanently deletes a pipeline and its run history. This cancels any in-progress runs. This does not delete agent sessions created by the pipeline. - [Delete tool server](https://docs.vectara.com/docs/rest-api/delete-tool-server.md): Deletes a tool server and all of its configuration and tools. The deletion is permanent. - [Delete tool](https://docs.vectara.com/docs/rest-api/delete-tool.md): Deletes a tool and its configuration permanently. This action cannot be undone. Agent calls to a deleted tool fail. Update agent configurations bef... - [Delete trusted token issuer](https://docs.vectara.com/docs/rest-api/delete-trusted-token-issuer.md): Deletes a trusted token issuer registration. - [Delete a user](https://docs.vectara.com/docs/rest-api/delete-user.md): Deletes a user from the account. - [Discover LLMs](https://docs.vectara.com/docs/rest-api/discover-ll-ms.md): Probes an external LLM provider endpoint and returns the model configurations most likely to work. The provider type and API dialect are inferred f... - [Documents](https://docs.vectara.com/docs/rest-api/documents.md): Documents - [Encoders](https://docs.vectara.com/docs/rest-api/encoders.md): Encoders - [Evaluate factual consistency](https://docs.vectara.com/docs/rest-api/evaluate-factual-consistency.md): Evaluates the factual consistency of a generated text (like a summary) against source documents. The evaluation determines how accurately the gener... - [Factual Consistency Evaluation](https://docs.vectara.com/docs/rest-api/factual-consistency-evaluation.md): Factual Consistency Evaluation - [Generation Presets](https://docs.vectara.com/docs/rest-api/generation-presets.md): Generation Presets - [Get A2A agent card (v0.3 RPC)](https://docs.vectara.com/docs/rest-api/get-a-2-a-v-03-agent-card-rpc.md): Returns the same v0.3 Agent Card as `.well-known/agent-card.json`, served at the v0.3 RPC URL `GET /v1/card`. - [Get A2A agent card (well-known)](https://docs.vectara.com/docs/rest-api/get-a-2-a-v-03-agent-card-well-known.md): Returns the A2A v0.3 [Agent Card](https://a2a-protocol.org) for the specified agent at the canonical `.well-known/agent-card.json` discovery URL. S... - [Get A2A v0.3 task](https://docs.vectara.com/docs/rest-api/get-a-2-a-v-03-task.md): Returns the current state of an A2A task, including its status, conversation history, and any produced artifacts. - [Get A2A v1 agent card (well-known)](https://docs.vectara.com/docs/rest-api/get-a-2-a-v-1-agent-card-well-known.md): Returns the v1 [Agent Card](https://a2a-protocol.org) at the well-known discovery URL `/.well-known/a2a/v1/agent-card.json`. The card lists every s... - [Get A2A v1 extended agent card](https://docs.vectara.com/docs/rest-api/get-a-2-a-v-1-extended-agent-card.md): Returns the v1 [Agent Card](https://a2a-protocol.org) for authenticated callers. The response body is identical to the well-known v1 card. - [Get A2A v1 task](https://docs.vectara.com/docs/rest-api/get-a-2-a-v-1-task.md): Returns the current state of an A2A task in the v1 wire format, including its status, conversation history, and any produced artifacts. - [Get an alias](https://docs.vectara.com/docs/rest-api/get-agent-alias.md): Returns the alias, including its policy. - [Get agent connector](https://docs.vectara.com/docs/rest-api/get-agent-connector.md): Returns an agent connector by its ID, including its configuration and status. - [Get event in agent session](https://docs.vectara.com/docs/rest-api/get-agent-event.md): Returns the details of a specific event in an agent session. - [Get agent identity](https://docs.vectara.com/docs/rest-api/get-agent-identity.md): Returns the identity associated with an agent. The identity is the service account the agent uses when executing tools. - [Get agent schedule](https://docs.vectara.com/docs/rest-api/get-agent-schedule.md): Returns the full details of a specific agent schedule using its unique schedule key. The response includes the schedule's configuration, execution ... - [Get agent secrets](https://docs.vectara.com/docs/rest-api/get-agent-secrets.md): Returns the agent's secrets. Values are always masked (`****`). Plaintext is never exposed on read. - [Get agent session](https://docs.vectara.com/docs/rest-api/get-agent-session.md): Returns the full details of a specific agent session, identified by its unique session key. The response includes the session's configuration, meta... - [Get agent](https://docs.vectara.com/docs/rest-api/get-agent.md): Returns the complete configuration of an agent, including its tools, instructions, model parameters, and metadata. - [Get event on alias-routed session](https://docs.vectara.com/docs/rest-api/get-alias-routed-event.md): Returns a single event of a session originally created via this alias. - [Get artifact on alias-routed session](https://docs.vectara.com/docs/rest-api/get-alias-routed-session-artifact.md): Returns an artifact stored in a session originally created via this alias, including metadata and base64-encoded file content. - [Get alias-routed session](https://docs.vectara.com/docs/rest-api/get-alias-routed-session.md): Returns a session originally created via this alias. - [Get an API key](https://docs.vectara.com/docs/rest-api/get-api-key.md): Returns an API key. The response shows the corpora the key can access and with what permissions. - [Get an App Client](https://docs.vectara.com/docs/rest-api/get-app-client.md): Returns the App Client with the specified ID. - [Get a turn](https://docs.vectara.com/docs/rest-api/get-chat-turn.md): Returns a specific turn from a chat. A turn is a message and response pair from the conversation. - [Get a chat](https://docs.vectara.com/docs/rest-api/get-chat.md): Returns a chat summary that shows what started the chat, but not subsequent turns. - [Retrieve a document](https://docs.vectara.com/docs/rest-api/get-corpus-document.md): Returns the content and metadata of a specific document in a corpus. The unique `document_id` identifies the document. The response includes the fu... - [Retrieve metadata about a corpus](https://docs.vectara.com/docs/rest-api/get-corpus.md): Returns metadata about a corpus without performing a search. This operation does not search the corpus contents. Specify the `corpus_key` to identi... - [Get end user session for alias](https://docs.vectara.com/docs/rest-api/get-end-user-alias-routed-session.md): Returns a session the caller owns, addressed by the alias it was created through. Returns 403 if the session belongs to a different principal. - [Get filter attribute statistics for corpus metadata](https://docs.vectara.com/docs/rest-api/get-filter-attribute-stats.md): Returns statistics and value distributions for the filter attributes in a corpus. Use these statistics to understand the available filter values an... - [Get glossary](https://docs.vectara.com/docs/rest-api/get-glossary.md): Returns the metadata of a glossary. - [Retrieve an image from a document](https://docs.vectara.com/docs/rest-api/get-image.md): Returns a specific image that is embedded within a document. The `image_id` uniquely identifies the image within the document. Use this endpoint to... - [Get instruction](https://docs.vectara.com/docs/rest-api/get-instruction.md): Returns the full definition of an instruction, including its template, metadata, enabled status, and version. Instruction templates may contain Vel... - [Get a job by ID](https://docs.vectara.com/docs/rest-api/get-job.md): Returns the job with the specified `job_id`. Jobs are background processes, such as replacing the filterable metadata attributes. - [Get an LLM](https://docs.vectara.com/docs/rest-api/get-llm.md): Returns the details of a Large Language Model (LLM) configured within the platform. The details include the name, description, model type, API endp... - [Query a metric time series](https://docs.vectara.com/docs/rest-api/get-metric.md): Returns a time series of aggregated metric values for the named metric within the requested time range. - [Request an access token](https://docs.vectara.com/docs/rest-api/get-o-auth-token.md): Exchanges client credentials for an OAuth 2.0 access token. - [Get dead letter](https://docs.vectara.com/docs/rest-api/get-pipeline-dead-letter-entry.md): Returns a dead letter by its ID. - [Get pipeline run](https://docs.vectara.com/docs/rest-api/get-pipeline-run.md): Returns details of a pipeline run, including record counts, session keys, and status. - [Get pipeline](https://docs.vectara.com/docs/rest-api/get-pipeline.md): Returns a pipeline by its key, including its current status, watermark, and configuration. - [List query histories](https://docs.vectara.com/docs/rest-api/get-query-histories.md): Lists the history of previous queries. Use this API to track query performance and to debug individual queries. - [Get a query history](https://docs.vectara.com/docs/rest-api/get-query-history.md): Returns the detailed history of a specific query made against a corpus. The response includes the query latency, the execution time, and the stages... - [Get session artifact raw bytes](https://docs.vectara.com/docs/rest-api/get-session-artifact-content.md): Returns the raw bytes of an artifact. Unlike `getSessionArtifact`, which returns a JSON wrapper with base64-encoded data, this endpoint returns the... - [Get session artifact](https://docs.vectara.com/docs/rest-api/get-session-artifact.md): Returns a specific artifact by its unique `artifact_id`, including metadata and base64-encoded file content. - [Get tool server](https://docs.vectara.com/docs/rest-api/get-tool-server.md): Returns a tool server by its ID. - [Get tool](https://docs.vectara.com/docs/rest-api/get-tool.md): Returns the full details of a tool, including its description, input schema, metadata, and capabilities. Tools may represent structured search func... - [Get span in a trace](https://docs.vectara.com/docs/rest-api/get-trace-span.md): Returns the details of a specific span within a trace. - [Get agent trace](https://docs.vectara.com/docs/rest-api/get-trace.md): Returns the summary of a specific agent trace by its trace ID. - [Get trusted token issuer](https://docs.vectara.com/docs/rest-api/get-trusted-token-issuer.md): Returns a trusted token issuer registration. - [Get a user](https://docs.vectara.com/docs/rest-api/get-user.md): Returns a user with details such as the email, username, and associated roles. - [Glossaries](https://docs.vectara.com/docs/rest-api/glossaries.md): Glossaries - [Hallucination Correctors](https://docs.vectara.com/docs/rest-api/hallucination-correctors.md): Hallucination Correctors - [Hide event](https://docs.vectara.com/docs/rest-api/hide-agent-event.md): Hides an event in a session. Sets hide_reason to 'manual'. - [Hide event on alias-routed session](https://docs.vectara.com/docs/rest-api/hide-alias-routed-event.md): Hides an event on a session originally created via this alias. Sets hide_reason to 'manual'. - [Index](https://docs.vectara.com/docs/rest-api/index.md): Index - [Instructions](https://docs.vectara.com/docs/rest-api/instructions.md): Instructions - [Jobs](https://docs.vectara.com/docs/rest-api/jobs.md): Jobs - [Large Language Models](https://docs.vectara.com/docs/rest-api/large-language-models.md): Large Language Models - [List A2A v1 tasks](https://docs.vectara.com/docs/rest-api/list-a-2-a-v-1-tasks.md): Lists the agent's tasks. Results are paginated. Optional query parameters filter by conversation context and lifecycle state. - [List aliases](https://docs.vectara.com/docs/rest-api/list-agent-aliases.md): Lists aliases. Results are paginated. - [List agent connectors](https://docs.vectara.com/docs/rest-api/list-agent-connectors.md): Lists all connectors for an agent, with optional filtering and pagination. - [List events in agent session](https://docs.vectara.com/docs/rest-api/list-agent-events.md): Lists all events in a specific agent session, with optional pagination. - [List agent schedule executions](https://docs.vectara.com/docs/rest-api/list-agent-schedule-executions.md): Lists all execution attempts for a schedule, ordered by most recent first. - [List agent schedules](https://docs.vectara.com/docs/rest-api/list-agent-schedules.md): Lists all schedules for the specified agent. Returns high-level information about each schedule, including execution status and next scheduled exec... - [List agent sessions](https://docs.vectara.com/docs/rest-api/list-agent-sessions.md): Lists all sessions for the specified agent. Returns high-level information about each session, with optional filtering and pagination. Use this ope... - [List agents](https://docs.vectara.com/docs/rest-api/list-agents.md): Lists all agents available to the authenticated user. Results are paginated. - [List events on alias-routed session](https://docs.vectara.com/docs/rest-api/list-alias-routed-events.md): Lists events of a session originally created via this alias. - [List outstanding client tool calls on alias-routed session](https://docs.vectara.com/docs/rest-api/list-alias-routed-outstanding-client-tool-calls.md): Lists the client tool calls that a session originally created via this alias waits on the caller to fulfill. Each entry carries the fully materiali... - [List artifacts on alias-routed session](https://docs.vectara.com/docs/rest-api/list-alias-routed-session-artifacts.md): Lists artifacts stored in a session originally created via this alias. Artifacts are files uploaded by the user or generated within the session. - [List sessions routed via this alias](https://docs.vectara.com/docs/rest-api/list-alias-routed-sessions.md): Lists sessions originally created via this alias (sessions whose `alias_key` matches). Sessions are also reachable under their resolved agent's URL... - [List API keys](https://docs.vectara.com/docs/rest-api/list-api-keys.md): Lists the API keys the caller can access. The response shows the corpora each key can access and with what permissions. - [List App Clients](https://docs.vectara.com/docs/rest-api/list-app-client.md): Lists the App Clients configured for the customer account. - [List turns in a chat](https://docs.vectara.com/docs/rest-api/list-chat-turns.md): Lists all turns in a chat. Each turn is a message and response pair in the dialog. - [List chats](https://docs.vectara.com/docs/rest-api/list-chats.md): Lists previous chats in the account. - [List corpora](https://docs.vectara.com/docs/rest-api/list-corpora.md): Lists the corpora in your account. Results are paginated. Each corpus object contains basic information about the corpus. These objects contain les... - [List the documents in the corpus](https://docs.vectara.com/docs/rest-api/list-corpus-documents.md): Lists the documents stored in a corpus. The response includes an overview of document metadata, including document IDs, tables (if table extraction... - [List encoders](https://docs.vectara.com/docs/rest-api/list-encoders.md): Lists the available encoders used to embed documents and queries. - [List end user events for alias](https://docs.vectara.com/docs/rest-api/list-end-user-alias-routed-events.md): Lists the visible events in a session the caller owns, addressed by the alias it was created through, with optional pagination. - [List end user sessions for alias](https://docs.vectara.com/docs/rest-api/list-end-user-alias-routed-sessions.md): Lists the calling end user's own sessions created through this alias. The response never includes sessions owned by another principal. - [List generation presets](https://docs.vectara.com/docs/rest-api/list-generation-presets.md): Lists the generation presets used for [query](/docs/rest-api/queries) requests. The platform creates and maintains predefined generation presets. A... - [List glossaries](https://docs.vectara.com/docs/rest-api/list-glossaries.md): Lists all glossaries available to the authenticated user. - [List glossary entries](https://docs.vectara.com/docs/rest-api/list-glossary-entries.md): Lists the entries in a glossary. - [List hallucination correctors](https://docs.vectara.com/docs/rest-api/list-hallucination-correctors.md): Lists the available hallucination correctors. These models detect and correct hallucinations in AI-generated content. The platform provides these m... - [List instructions](https://docs.vectara.com/docs/rest-api/list-instructions.md): Lists all instructions available to the authenticated user, with optional filtering and pagination. The response includes high-level information ab... - [List jobs](https://docs.vectara.com/docs/rest-api/list-jobs.md): Lists jobs for the account. Jobs are background processes, such as replacing the filterable metadata attributes. - [List LLMs](https://docs.vectara.com/docs/rest-api/list-ll-ms.md): Lists LLMs that you can use with query and chat endpoints. A query does not specify the LLM directly. Instead, it uses a `generation_preset_name`. ... - [List available metrics](https://docs.vectara.com/docs/rest-api/list-metrics.md): Returns the catalog of registered metrics that you can query via `/v2/metrics/{metric_name}`. Use it to discover metric names, types, and supported... - [List outstanding client tool calls for an agent session](https://docs.vectara.com/docs/rest-api/list-outstanding-client-tool-calls.md): Lists the client tool calls the session is waiting for the caller to fulfill. Each entry carries the originating `tool_input` event ID, the tool na... - [List dead letters](https://docs.vectara.com/docs/rest-api/list-pipeline-dead-letter-entries.md): Lists dead letters for a pipeline, with optional filtering by status or run. - [List pipeline run events](https://docs.vectara.com/docs/rest-api/list-pipeline-run-events.md): Lists the timeline of events for a pipeline run, keyed by `run_id`. Events report what the run did — records discovered, records processed, agent s... - [List pipeline runs](https://docs.vectara.com/docs/rest-api/list-pipeline-runs.md): Lists execution runs for a pipeline, with optional filtering by status. - [List pipelines](https://docs.vectara.com/docs/rest-api/list-pipelines.md): Lists all pipelines with optional filtering by source type, status, or enabled state. - [List rerankers](https://docs.vectara.com/docs/rest-api/list-rerankers.md): Lists the available rerankers. Rerankers improve the ranking and ordering of search results. - [List session artifacts](https://docs.vectara.com/docs/rest-api/list-session-artifacts.md): Lists all artifacts stored in a specific agent session, with cursor-based pagination. Artifacts are files that the user uploads or that the agent g... - [List supported table extractors](https://docs.vectara.com/docs/rest-api/list-table-extractors.md): Lists the table extractors that are available for indexing. Table extractors extract tabular data from documents during indexing. - [List tool servers](https://docs.vectara.com/docs/rest-api/list-tool-servers.md): Lists the tool servers in the account. A tool server exposes tools that agents can use. - [List tools](https://docs.vectara.com/docs/rest-api/list-tools.md): Lists all tools available to the authenticated user. Supports filtering and pagination. Tools represent capabilities that agents can invoke during ... - [List spans in a trace](https://docs.vectara.com/docs/rest-api/list-trace-spans.md): Returns the flat list of spans for a given trace. Each span includes its parent_span_id so you can reconstruct the tree. - [List agent traces](https://docs.vectara.com/docs/rest-api/list-traces.md): Lists agent traces with optional filtering by agent, session, status, and time range. - [List trusted token issuers](https://docs.vectara.com/docs/rest-api/list-trusted-token-issuers.md): Lists the customer's trusted token issuer registrations. - [List users](https://docs.vectara.com/docs/rest-api/list-users.md): Lists all users in the customer account. The response shows each user's corpus access and customer-level authorizations. - [LLM Chat Completions](https://docs.vectara.com/docs/rest-api/llm-chat-completions.md): LLM Chat Completions - [Metadata Query](https://docs.vectara.com/docs/rest-api/metadata-query.md): Metadata Query - [Pipeline Dead Letters](https://docs.vectara.com/docs/rest-api/pipeline-dead-letters.md): Pipeline Dead Letters - [Pipeline Runs](https://docs.vectara.com/docs/rest-api/pipeline-runs.md): Pipeline Runs - [Pipelines](https://docs.vectara.com/docs/rest-api/pipelines.md): Pipelines - [Process dead letters](https://docs.vectara.com/docs/rest-api/process-pipeline-dead-letter-entries.md): Processes dead letters by creating a new pipeline run. The run re-fetches the specified records from the source and sends them through the agent. A... - [Queries](https://docs.vectara.com/docs/rest-api/queries.md): Queries - [Query a corpus with advanced options](https://docs.vectara.com/docs/rest-api/query-corpus.md): Queries a specific corpus with full control over retrieval and generation. Returns relevant results, generated summaries, and highlighted snippets.... - [Query History](https://docs.vectara.com/docs/rest-api/query-history.md): Query History - [Query across metadata fields in a corpus](https://docs.vectara.com/docs/rest-api/query-metadata.md): Queries documents in a corpus with fuzzy matching across the specified metadata fields. The search first applies any exact metadata filters to narr... - [Query multiple corpora](https://docs.vectara.com/docs/rest-api/query.md): Queries one or more corpora and generates a response with Retrieval Augmented Generation (RAG). Similar to the [advanced single corpus query](https... - [Replace an alias's routing policy](https://docs.vectara.com/docs/rest-api/replace-agent-alias-policy.md): Replaces the alias's routing policy and stickiness configuration in one atomic operation. The replacement is whole-object. Partial merging is not s... - [Replace agent secrets](https://docs.vectara.com/docs/rest-api/replace-agent-secrets.md): Replaces the agent's secrets. The submitted map fully replaces the previous set. Names not in the request are removed. - [Replace agent](https://docs.vectara.com/docs/rest-api/replace-agent.md): Replaces the complete configuration of an existing agent, including its steps, instructions, tool configurations, and model. Unlike Update agent, w... - [Replace the document metadata](https://docs.vectara.com/docs/rest-api/replace-corpus-document-metadata.md): Replaces the metadata of a document in a corpus. The unique `document_id` identifies the document. - [Replace the filter attributes of a corpus](https://docs.vectara.com/docs/rest-api/replace-filter-attributes.md): Replaces the filter attributes of a corpus. The replacement does not happen immediately. This operation creates a job that completes asynchronously... - [Replace a generation preset](https://docs.vectara.com/docs/rest-api/replace-generation-preset.md): Replaces an existing custom generation preset. This is a full replacement of the preset configuration. - [Replace pipeline](https://docs.vectara.com/docs/rest-api/replace-pipeline.md): Replaces a pipeline's configuration. Provide the full pipeline definition. - [Replace trusted token issuer](https://docs.vectara.com/docs/rest-api/replace-trusted-token-issuer.md): Replaces a trusted token issuer registration in full. - [Rerankers](https://docs.vectara.com/docs/rest-api/rerankers.md): Rerankers - [Remove all documents and data in a corpus](https://docs.vectara.com/docs/rest-api/reset-corpus.md): Resets a corpus. This removes all documents and data from the corpus but keeps the corpus itself. The `corpus_key` uniquely identifies the corpus. ... - [Reset a user password](https://docs.vectara.com/docs/rest-api/reset-user-password.md): Resets the password for a user. - [Query a corpus with query parameters](https://docs.vectara.com/docs/rest-api/search-corpus.md): Queries a single corpus with a simple request. The [**Query APIs**](/docs/rest-api/queries) support Retrieval Augmented Generation (RAG). They sear... - [Send A2A v0.3 streaming message](https://docs.vectara.com/docs/rest-api/send-a-2-a-v-03-message-stream.md): Sends a message to the agent and streams task lifecycle events as Server-Sent Events. Each SSE `data:` line is a JSON `A2aV03StreamResponse` carryi... - [Send A2A v0.3 message](https://docs.vectara.com/docs/rest-api/send-a-2-a-v-03-message.md): Sends a message to the agent. Blocks until the agent reaches a terminal or interrupted state. Returns the resulting `task`, or a direct `message` r... - [Send A2A v1 streaming message](https://docs.vectara.com/docs/rest-api/send-a-2-a-v-1-message-stream.md): Sends a message to the agent using the A2A v1 wire format and streams task lifecycle events as Server-Sent Events. Each SSE `data:` line is a JSON ... - [Send A2A v1 message](https://docs.vectara.com/docs/rest-api/send-a-2-a-v-1-message.md): Sends a message to the agent using the A2A v1 wire format. Blocks until the agent reaches a terminal or interrupted state. Returns the resulting `t... - [Subscribe to A2A v0.3 task updates](https://docs.vectara.com/docs/rest-api/subscribe-a-2-a-v-03-task.md): Attaches to a running task and streams subsequent lifecycle updates as Server-Sent Events. If the task is already terminal, streams the final task ... - [Subscribe to A2A v1 task updates](https://docs.vectara.com/docs/rest-api/subscribe-a-2-a-v-1-task.md): Attaches to a running task and streams subsequent lifecycle updates as Server-Sent Events in the v1 wire format. If the task is already terminal, s... - [Summarize a document](https://docs.vectara.com/docs/rest-api/summarize-corpus-document.md): Generates a concise summary of a single document. The summary captures essential insights without requiring you to review the entire document manua... - [Synchronize tool server](https://docs.vectara.com/docs/rest-api/sync-tool-server.md): Synchronizes the tool server to refresh its list of tools. - [Table Extractors](https://docs.vectara.com/docs/rest-api/table-extractors.md): Table Extractors - [Test instruction](https://docs.vectara.com/docs/rest-api/test-instruction.md): Tests an instruction template with supplied context and available tools. The endpoint evaluates Velocity expressions such as `$tools`, `${session.m... - [Test Lambda tool without creation](https://docs.vectara.com/docs/rest-api/test-lambda-tool-without-creation.md): Tests a Lambda tool without creating it. - [Test Lambda tool](https://docs.vectara.com/docs/rest-api/test-tool.md): Tests an existing Lambda tool by executing it with test inputs. - [Tool Servers](https://docs.vectara.com/docs/rest-api/tool-servers.md): Tool Servers - [Tools](https://docs.vectara.com/docs/rest-api/tools.md): Tools - [Trigger pipeline](https://docs.vectara.com/docs/rest-api/trigger-pipeline.md): Triggers a pipeline run manually, outside of the normal schedule. The pipeline fetches new data from the source and processes it through the agent.... - [Trusted Token Issuers](https://docs.vectara.com/docs/rest-api/trusted-token-issuers.md): Trusted Token Issuers - [Unhide event](https://docs.vectara.com/docs/rest-api/unhide-agent-event.md): Unhides a hidden event in a session. Clears the hide_reason. - [Unhide event on alias-routed session](https://docs.vectara.com/docs/rest-api/unhide-alias-routed-event.md): Unhides a hidden event on a session originally created via this alias. Clears the hide_reason. - [Update an alias's metadata](https://docs.vectara.com/docs/rest-api/update-agent-alias.md): Updates an alias's metadata fields (name, description, enabled, metadata). Setting `enabled` to false on a platform-generated alias fronted by a wi... - [Update agent connector](https://docs.vectara.com/docs/rest-api/update-agent-connector.md): Updates an agent connector's configuration, status, or other properties. - [Update agent identity](https://docs.vectara.com/docs/rest-api/update-agent-identity.md): Updates the agent's identity. You can change the role management mode, the roles, or both. - [Update agent schedule](https://docs.vectara.com/docs/rest-api/update-agent-schedule.md): Updates an existing agent schedule. All fields are optional. The update changes only the provided fields (PATCH semantics). - [Update agent secrets](https://docs.vectara.com/docs/rest-api/update-agent-secrets.md): Updates the agent's secrets. Names present in the map are added or replaced. Names absent from the map are left unchanged. - [Update agent session](https://docs.vectara.com/docs/rest-api/update-agent-session.md): Updates the configuration of an existing agent session. You can modify fields such as the name, description, or metadata. - [Update agent](https://docs.vectara.com/docs/rest-api/update-agent.md): Updates part of an agent's configuration, including its tools, instructions, model parameters, and metadata. - [Update alias-routed session](https://docs.vectara.com/docs/rest-api/update-alias-routed-session.md): Updates a session originally created via this alias. - [Update an API key](https://docs.vectara.com/docs/rest-api/update-api-key.md): Updates an API key. Enable or disable the key to temporarily remove access without deleting the key. This is useful for maintenance windows, or whe... - [Update an App Client](https://docs.vectara.com/docs/rest-api/update-app-client.md): Updates the configuration of an existing App Client. - [Update a turn](https://docs.vectara.com/docs/rest-api/update-chat-turn.md): Updates a turn to disable or enable it. - [Update a document, merging its metadata](https://docs.vectara.com/docs/rest-api/update-corpus-document.md): Updates a document in a corpus. The unique `document_id` identifies the document. The platform merges the request body metadata with the existing m... - [Update a corpus](https://docs.vectara.com/docs/rest-api/update-corpus.md): Enables, disables, or updates the name and description of a corpus. Use this endpoint to manage the availability of data, such as taking a corpus o... - [Update glossary](https://docs.vectara.com/docs/rest-api/update-glossary.md): Updates the metadata of a glossary. - [Update instruction](https://docs.vectara.com/docs/rest-api/update-instruction.md): Updates an existing instruction's template, metadata, and configuration. Updated templates may include Velocity variables such as `$tools` or metad... - [Update an LLM](https://docs.vectara.com/docs/rest-api/update-llm.md): Updates an existing LLM's configuration. This endpoint supports partial updates. Provide only the fields you want to change. Only the name field is... - [Update pipeline](https://docs.vectara.com/docs/rest-api/update-pipeline.md): Partially updates a pipeline's configuration. Omitted fields keep their current values. - [Update tool server](https://docs.vectara.com/docs/rest-api/update-tool-server.md): Updates the configuration of a tool server. - [Update tool](https://docs.vectara.com/docs/rest-api/update-tool.md): Updates an existing tool’s configuration, including its metadata, enabled status, or other properties. Updating a tool changes how agents invoke it... - [Update a user](https://docs.vectara.com/docs/rest-api/update-user.md): Updates details of a user such as role names. - [Upload a file to the corpus](https://docs.vectara.com/docs/rest-api/upload-file.md): Uploads a file to a corpus for automatic text extraction, chunking, and indexing. Use this endpoint for unstructured documents when you want the pl... - [Upload](https://docs.vectara.com/docs/rest-api/upload.md): Upload - [Upsert glossary entries](https://docs.vectara.com/docs/rest-api/upsert-glossary-entries.md): Upserts entries into a glossary in bulk. Entries with existing terms are updated. New terms are inserted. The platform rebuilds the glossary index ... - [Users](https://docs.vectara.com/docs/rest-api/users.md): Users - [Vectara REST API v2](https://docs.vectara.com/docs/rest-api/vectara-rest-api-v-2.md): Vectara is a platform for building and operating enterprise agents. The REST API gives you server-side control with enterprise-grade RBAC, multi-te... - [Widgets](https://docs.vectara.com/docs/rest-api/widgets.md): Widgets - [Enable SSO with OpenID Connect (OIDC)](https://docs.vectara.com/docs/saas/guides/vectara-sso-oidc.md): Use this guide to enable Single Sign-On (SSO) to the Vectara SaaS deployment - [SaaS deployment guides](https://docs.vectara.com/docs/saas/guides.md): Step-by-step guides for configuring and integrating the Vectara SaaS deployment - [SaaS deployment](https://docs.vectara.com/docs/saas.md): The Vectara SaaS (cloud) deployment runs the platform as a fully managed, - [Vectara demos and applications](https://docs.vectara.com/docs/sample-vectara-apps.md): The platform enables you to build generative AI and Retrieval - [Agents](https://docs.vectara.com/docs/sdk/python/agents.md): This guide covers the Vectara Python SDK for creating and managing AI agents - [API Keys](https://docs.vectara.com/docs/sdk/python/api_keys.md): The Vectara Python SDK enables you to manage API keys for authenticating API - [Chats](https://docs.vectara.com/docs/sdk/python/chats.md): This guide covers the Vectara Python SDK for managing chat conversations, - [Corpora](https://docs.vectara.com/docs/sdk/python/corpus.md): This guide covers the Vectara Python SDK for managing corpora, which are - [Indexing Documents](https://docs.vectara.com/docs/sdk/python/documents.md): Manage document data efficiently by addressing challenges like data sprawl and - [Generation Presets](https://docs.vectara.com/docs/sdk/python/generation_presets.md): The Vectara SDK's Generation Presets module empowers enterprise developers to - [Metadata and Filtering](https://docs.vectara.com/docs/sdk/python/metadata.md): Metadata lets you tag documents and document parts with structured - [A Quick Guide to Error Handling in the Vectara Python SDK](https://docs.vectara.com/docs/sdk/python/python-error-handling.md): When using the Vectara Python SDK, errors can occur at three distinct stages - [Vectara Python SDK Quick Start](https://docs.vectara.com/docs/sdk/python/python-quickstart.md): Get up and running with the Vectara Python SDK in minutes. This quick start - [Queries](https://docs.vectara.com/docs/sdk/python/query.md): This guide covers the Vectara Python SDK for querying corpora, enabling search - [Rerankers](https://docs.vectara.com/docs/sdk/python/rerankers.md): Rerankers enhance the relevance of search results by refining and reordering them - [Build a Customer Support Knowledge Base with Vectara](https://docs.vectara.com/docs/sdk/python/tutorials/customer-support-kb.md): In this tutorial, you'll build a powerful support assistant that can instantly - [Upload Files](https://docs.vectara.com/docs/sdk/python/upload.md): This guide demonstrates how to upload files (PDFs, DOCX, and more) to a - [Users](https://docs.vectara.com/docs/sdk/python/users.md): The Vectara Python SDK provides methods to manage users in your account, - [Vectara Python SDK](https://docs.vectara.com/docs/sdk/vectara-python-sdk.md): The Vectara Python SDK enables you to access Vectara’s semantic search, - [Bring your own LLM](https://docs.vectara.com/docs/search-and-retrieval/bring-your-own-llm.md): Organizations often need to integrate multiple Large Language Models (LLMs) - [Build a search UI](https://docs.vectara.com/docs/search-and-retrieval/build-search-ui.md): Building a custom search interface from scratch can be time-consuming. To help - [Citations in Search and Retrieval](https://docs.vectara.com/docs/search-and-retrieval/citations.md): Citations provide important source attribution in query results, enabling - [Filters](https://docs.vectara.com/docs/search-and-retrieval/filters.md): Metadata filters restrict search results to only the document chunks that - [Fuzzy matching](https://docs.vectara.com/docs/search-and-retrieval/fuzzy-metadata-search.md): The tech preview of Fuzzy Metadata Search combines exact filtering with - [Hybrid search](https://docs.vectara.com/docs/search-and-retrieval/hybrid-search.md): Hybrid search blends semantic matching (meaning) and traditional keyword - [Chain reranker](https://docs.vectara.com/docs/search-and-retrieval/rerankers/chain-reranker.md): When refining query results where relevance and diversity are critical to - [Knee reranker](https://docs.vectara.com/docs/search-and-retrieval/rerankers/knee-reranking.md): Retrieval Augmented Generation (RAG) systems often struggle with determining - [Limits and cutoffs](https://docs.vectara.com/docs/search-and-retrieval/rerankers/limits-and-cutoffs.md): After reranking is applied, you can use the `cutoff` and `limit` parameters to - [Maximal Marginal Relevance (MMR) reranker](https://docs.vectara.com/docs/search-and-retrieval/rerankers/mmr-reranker.md): The Maximal Marginal Relevance (MMR) reranker enables you to diversify search - [User Defined Function reranker](https://docs.vectara.com/docs/search-and-retrieval/rerankers/user-defined-function-reranker.md): Our out-of-the-box rerankers are effective for general use cases, but - [Vectara multilingual reranker](https://docs.vectara.com/docs/search-and-retrieval/rerankers/vectara-multi-lingual-reranker.md): Generative AI applications often struggle with ranking the most relevant - [Reranking](https://docs.vectara.com/docs/search-and-retrieval/reranking.md): Initial search results often fail to capture nuanced relevance or diversity, - [Quickstart](https://docs.vectara.com/docs/search-and-retrieval/search-quick-start.md): The fastest way to experience Vectara immediately is by querying our pre-built - [Tune retrieval](https://docs.vectara.com/docs/search-and-retrieval/tune-retrieval.md): This guide is for any caller that constructs Vectara query requests - [Search and retrieval](https://docs.vectara.com/docs/search-and-retrieval.md): Vectara provides a powerful, end-to-end search that retrieves relevant answers - [API key management](https://docs.vectara.com/docs/security/authentication/api-key-management.md): API Keys enable controlled, anonymous access to several administrative tasks, - [Authentication Overview](https://docs.vectara.com/docs/security/authentication/authentication-overview.md): Vectara's authentication and authorization framework secures access to our - [Choose authentication method](https://docs.vectara.com/docs/security/authentication/choose-auth-method.md): Vectara supports two main methods for authenticating API requests: [**API keys**](/docs/security/authentication/api-key-management) - [Use OAuth 2.0](https://docs.vectara.com/docs/security/authentication/oauth-2.md): Personal API keys enable rapid application development in a testing - [Authentication methods and authorization levels](https://docs.vectara.com/docs/security/authentication/auth-overview.md): Vectara has robust authentication and authorization methods in place to secure - [Attribute-based access control](https://docs.vectara.com/docs/security/authorization/attribute-based-access-control.md): Vectara does not currently offer native field-level or document-level access - [Authorization Overview](https://docs.vectara.com/docs/security/authorization/authorization-overview.md): Control access to your Vectara resources with role-based, attribute-based, and multi-tenant access control. - [Combine access control with application filters](https://docs.vectara.com/docs/security/authorization/combine-access-control-with-app-filters.md): In most applications, you need to control both who can access specific data - [Multi-tenant corpus isolation](https://docs.vectara.com/docs/security/authorization/multi-tenant-corpus-isolation.md): Without isolation, a compromised key could lead to unauthorized access across - [Role-based access control](https://docs.vectara.com/docs/security/authorization/role-based-access-control.md): Vectara uses Role-Based Access Control (RBAC) with four tiers of roles: - [Enterprise access patterns](https://docs.vectara.com/docs/security/authorization/personas-and-access-patterns.md): Understanding **who** interacts with Vectara, and **how** they interact with it, - [Data encryption](https://docs.vectara.com/docs/security/data-privacy/encryption.md): When you send documents to the - [Security and data privacy](https://docs.vectara.com/docs/security/data-privacy/privacy-overview.md): At , we treat your data with the utmost privacy: - [Textless Mode](https://docs.vectara.com/docs/security/data-privacy/textless.md): When you create a corpus, you have the option to **not** store - [Security](https://docs.vectara.com/docs/security.md): Secure your Vectara applications with enterprise-grade authentication, authorization, and data privacy controls. This section covers how to authent... - [Custom dimensions](https://docs.vectara.com/docs/tutorials/add-custom-dimensions.md): Many search scenarios require considering factors beyond the text content - [Build a chatbot](https://docs.vectara.com/docs/tutorials/build-a-chatbot.md): Learn how to build a chatbot using our Agent APIs. In this tutorial, we - [Build a Financial Research Agent](https://docs.vectara.com/docs/tutorials/build-a-financial-research-agent.md): This tutorial demonstrates how to create custom Lambda Tools with different - [Build a parallel sub-agent fan-out](https://docs.vectara.com/docs/tutorials/build-a-parallel-subagent-fanout.md): This tutorial builds a parallel sub-agent composition: one parent agent calls - [Tutorial: Canary a new agent behind an alias](https://docs.vectara.com/docs/tutorials/canary-an-agent-version.md): This tutorial walks the full lifecycle of shipping a new agent behind an alias: - [FAQ and Q&A matching](https://docs.vectara.com/docs/tutorials/faq-and-qna-matching.md): FAQ and Question-and-Answer (Q&A) matching leverages our neural retrieval - [Intelligent query rewriting](https://docs.vectara.com/docs/tutorials/intelligent-query-rewriting.md): The tech preview release of Intelligent Query Rewriting enhances search - [Use Direct HTTPS or the OpenAI SDK with External Applications](https://docs.vectara.com/docs/tutorials/use-external-applications-sdk.md): To integrate with external applications, you can use either the direct HTTP - [Use OpenAI SDK with Vectara Chat Completions API](https://docs.vectara.com/docs/tutorials/use-openai-libraries-with-vectara.md): This tutorial demonstrates how to use Vectara's Chat Completions API through - [Use Case Exploration](https://docs.vectara.com/docs/use-case-exploration.md): The **Retrieval Augmented Generation as-a-Service - [Vectara Postman Collection](https://docs.vectara.com/docs/vectara-postman-collection.md): The [Vectara Postman Collection](https://www.postman.com/vectara) provides a convenient way - [Vectara Python SDK](https://docs.vectara.com/docs/vectara-python-sdk.md): - [About Vectara](https://docs.vectara.com/docs/welcome.md): Vectara is an **API-first Agentic Platform** for building production-grade AI agents and assistants that retrieve knowledge, reason over