Version: 2.0

Documentation Changelog

This changelog tracks changes to Vectara's documentation — new and updated guides, context-engineering material, and API reference updates. For product and feature releases, see the Release Notes.

September 2026Latest

Documentation Updates

#UpdatedDocumented streamed tool tests on the Composable lambda tools page, covering stream_response, the heartbeat and terminal result events, and that a budget above 300 seconds requires streaming.
#UpdatedDocumented the raised execution ceiling of 21600 seconds on the Custom tools, Lambda tools, and Composable lambda tools pages, along with the 300-second default a lambda that declares tool_configurations now resolves to when execution_configuration is omitted.

Docs Platform Updates

#Removed the Agent Playground and its walkthrough page. The interactive page at /playground/ and the /docs/platform-architecture/playground guide are gone, and the Platform architecture and Application layer pages no longer point at them. To drive an agent live, use the Console or the io CLI.

August 2026

New Documentation

#Added Wolken Tickets pipeline source documentation covering incident and service request ingestion from a Wolken ServiceDesk instance, one document per ticket with its subject, description, and conversation notes, the backfill_window lookback bound, and the request_types, status_ids, and note_response_type_ids filters.
#Added Docebo pipeline source documentation covering course catalog ingestion from a Docebo LMS instance through the Learn REST API, one document per course with a curriculum outline of its training materials, the published_only flag and the language and category include/exclude filters, and the full-catalog re-enumeration incremental sync performs because Docebo exposes no modified-since filter.
#Added Confluence tools for agents documentation covering all nineteen Confluence Cloud agent tools — space and content discovery, page and attachment reading, content creation, whole-page and in-place editing, and comments and labels — along with the API-token authentication the tools resolve from agent metadata and secrets by default, the markdown-to-storage-format conversion, and the version-based edit model. The page also flags that each tool name carries a date suffix (four different ones across the family) and cross-links the Confluence pipeline source.
#Added Box tools for agents documentation covering all seventeen Box agent tools — search and reading, content changes, and collaboration — along with developer-token and Client Credentials Grant authentication, including the complete per-mode argument_override each one needs and why naming only the arguments for your chosen mode is required rather than optional.
#Added Post to Google Chat from an agent documentation covering the gchat_post_message tool: the space_name, text, cards, and thread_name parameters, the ok, message_name, thread_name, and error response, card sections and link buttons, and credentials from either an attached Google Chat connector or the gchat_service_account_key agent secret.
#Added Google Drive tools for agents documentation covering all fifteen Drive agent tools — finding and reading files, organizing them, managing access, and comments — along with the four-step credential precedence every Google-backed tool shares, the subject_email impersonation argument, and that Drive tool names carry no version suffix unlike Box and Confluence. The page also documents two behaviors that are easy to hit and hard to diagnose: a connector_id resolving to a non-Google connector is ignored rather than rejected, so a Slack- or Zoom-triggered session can still reach Drive, while one resolving to nothing is an error; and a bare service account owns no Drive storage, so creating or copying a file fails unless the destination is a Shared Drive it can write to.
#Added Google Chat connectors documentation covering how the connector works, creating one and configuring the Google Chat app against it, the credentials the Google Chat tools resolve from it, listing, updating, and deleting connectors, and troubleshooting a webhook that returns 401, is rejected, or succeeds without the agent replying.
#Added Zoom connectors documentation covering how the connector works, creating one and configuring Zoom Contact Center against it, listing, updating, and deleting connectors, and troubleshooting a webhook that returns 401, the misconfiguration message Zoom receives, and an undelivered agent response.

Documentation Updates

#UpdatedDocumented the maps content scope on the Fluid Topics pipeline source page, covering whole-publication enumeration, the ignored query, and the reserved id filter key that restricts a run to a single publication.
#UpdatedDocumented the max_body_bytes parameter on the Wrap a REST API with web_get page, covering the UTF-8 byte ceiling it places on the request body, its 1 KB to 4 MB range, its 64 KB default, and the rejection of an oversized body before the request is sent.
#FixedCorrected the Confluence agent tool identifiers in the Release Notes, where nine tools were listed by their lineage family name (such as confluence_fetch) rather than the versioned name you pass when configuring a tool (such as confluence_fetch_20260622).
#Repointed the Google Drive tool entries in the Release Notes at the new Google Drive tools page. The August entry had linked to Connector authentication, which documents per-user OAuth for custom web_get tools rather than the service-account credentials these built-in tools actually use.
#FixedFixed a broken link in the Release Notes entry for the document conversion tool, which pointed at a relative path (docs/agent/sessions#document-upload-and-conversion) with no leading slash, a singular agent segment, and an anchor that does not exist. It now points at the document conversion tool section.
#UpdatedDocumented per-pipeline processing_options on the Pipeline concepts page, covering record_timeout_minutes (1–180, overriding the 30-minute service default for one attempt) and max_concurrent_records (1–64), that a record's total budget across all retries is twice record_timeout_minutes, and that an update replaces the object wholesale rather than merging it field by field.
#UpdatedDocumented the new fetch-then-process model on the Web pipeline source page, covering max_concurrent_fetches (1–4, default 2), the deprecated and now-ignored max_concurrent, the requests_per_second ceiling raised from 20 to 50, that the rate applies to each concurrent fetch independently so the worst case against a host is the product of the two, and the fallback to a live fetch for a page too large to stage.
#UpdatedDocumented the artifacts library on the Lambda tools page, covering artifacts.download(artifact_id, dest_path=None), that it is available without an import inside an agent session, that dest_path is relative to the sandbox scratch directory and defaults to the artifact id, and the ArtifactError raised for an unknown id or a path outside the scratch directory.
#FixedCorrected the set of Python modules a lambda tool can use, on the Lambda tools and Create a lambda tool pages: code can import the Python standard library plus the preinstalled numpy and pandas, replacing the eleven-module list both pages had presented as the complete set.
#UpdatedDocumented parallel tool calls on the Composable lambda tools page, covering tool.<name>.submit(param=value, ...), the handle it returns, handle.result() waiting for that call and re-raising tool.ToolError, and the limit of eight calls running concurrently; also summarized on the Lambda tools page.
#UpdatedDocumented LLM discovery and model capabilities on the Bring your own LLM page, covering the POST /v2/llms/discover request and candidate response, the image_support, context_limit, tool_calling, structured_outputs, and requires_role_alternation capability fields, and the requests_per_second per-model rate limit with its differing create and update semantics.
#UpdatedDocumented what a read of an LLM configuration returns, on the Bring your own LLM page: the auth variant the model was created with, every secret replaced by ****, the non-secret identifiers around it preserved so you can still recognize the credential, and that rotating a credential means submitting a new auth object with a PATCH while omitting auth keeps the existing one.
#UpdatedDocumented the slack_join_channel tool on the Slack connectors page, covering the channel_id argument, the channel fields and already_in_channel in the response, the Slack error codes returned in error, and the channels:join scope it needs.
#UpdatedDocumented the gchat_dm_user tool on the Post to Google Chat from an agent page, covering the user and text arguments, email resolution through the Workspace directory versus a users/USER_ID resource name, and the ok, space_name, message_name, and reachable response — where reachable false means the person has never installed the Chat app and a retry will not help.
#UpdatedDocumented incremental sync on the Fluid Topics pipeline source page, covering the switch to reading dataflow reports since the previous watermark, the administration scope the api_key now requires, the 1000-report window bound that forces a full refresh, and that metadata-only changes are now detected while deletions are still not propagated.
#EnhancedExpanded the Build agents with io page into full io CLI documentation, covering installation and io login, scoping the CLI API key, reviewing proposed changes and answering clarifying questions, running unattended in print mode, the workspace directory with /read and /paste uploads, io design for web applications — including joining agent keys with + for one application spanning several agents, the local proxy that keeps your API key out of the browser page, and that the bring-your-own LLM registration it creates is tenant-wide rather than personal — io preview for an existing agent, and the deployment and LLM requirements for self-managed environments.

API Reference Updates

#Corrected Evaluate factual consistency: the default and recommended model is hhem_v2.3; language is not a request field and the examples no longer show one; the response carries score rather than the p_consistent and p_inconsistent fields the examples had shown; the 422 response for an unsupported language is gone, because text in an untrained language is scored rather than rejected — only eng, deu, fra, spa, por, ara, kor, zho, rus, jpn, and hin should be treated as reliable; and an unrecognized model name returns 400 against body.model_parameters.model_name.
#Documented the optional external_id on an agent text input, up to 255 characters, which makes submitting an input idempotent within a session — a repeat of an id the session already holds adds nothing and returns no error — and is returned on the input's event in InputMessageEvent.messages. See Interact with an agent.
#Documented that reading a configured LLM returns the auth variant it was created with, secrets replaced by **** and non-secret identifiers such as an AWS access key id, a GCP project and region, or a header name preserved, on both Get an LLM and List LLMs.

Deprecations

#Documented the deprecation of max_concurrent on the Web pipeline source, which is no longer read; move any value you set to max_concurrent_fetches, whose ceiling is 4.
#Documented the deprecation of max_memory_mb on a lambda tool's execution configuration, which is now ignored because memory is fixed by the execution environment. See Create a lambda tool.

Docs Platform Updates

#Removed the year filter from the Release Notes and Changelog browsers. Both already group by month and support search, so the filter added a control without adding a way to find anything.
#Fixed broken and outdated links across the documentation, including the API reference, the security and authentication pages, the retrieval tuning guide, and the version 1.0 archive, and updated the redirect table so the old URLs still resolve.

July 2026

New Documentation

#Added Wolken Forms pipeline source documentation covering ingestion of a Wolken ServiceDesk end-user service catalog (incident and service request forms), one document per form, and the optional include_form_details enrichment.
#Added End user sessions documentation covering the dedicated /v2/agent_aliases/{alias_key}/end_user_sessions surface, the agent_end_user role, per-caller session isolation, the messages-only event projection, streaming, and session limits, and cross-linked it from the Sessions page
#Added pipeline source documentation for Box, Confluence, Web, and Wolken KB, refreshed the S3, SharePoint, and Google Drive source pages, and updated the pipeline sources index and session metadata page.
#Documented the slack_get_file tool and bot-token-only credentials (the slack_bot_token agent secret) on the Slack Connectors page.
#Added Fluid Topics pipeline source documentation covering ingestion from a Fluid Topics tenant through the Knowledge Hub REST API and the content_scope content layer selection.
#Added Alias workflows and best practices and a Canary a new agent version tutorial covering putting a stable alias in front of your agents and rolling out a new agent version behind it.
#Added SCIM pipeline source documentation covering user profile ingestion from any SCIM 2.0 service provider through the Users endpoint, directory attributes as filterable metadata, and the incremental_strategy sync options.

Documentation Updates

#FixedFixed the authentication code examples on the API key management and Transport Layer Security pages, where the request host rendered as a literal template placeholder instead of api.vectara.io.

API Reference Updates

#Documented the per-tool tool_output_offloading override on Create tool, which overrides the agent's output-offloading behavior for that tool's outputs.
#Documented the metadata_filter query parameter and the artifact metadata field on List session artifacts, for narrowing the list to artifacts whose metadata matches.
#Documented the per-tool max_execution_time_seconds timeout on Create tool, the maximum wall-clock time before a tool call is aborted.
#Documented the A2A Protocol endpoints (v0.3 and v1) for agent discovery, message send and stream, and task lifecycle.

June 2026

New Documentation

#Added Build with io documentation, introducing the io assistant in the Vectara Console as a conversational way to create and edit platform resources (such as agents, pipelines, and API keys), inspect your account, debug performance, and explore how Vectara works, with the confirmation flow and how to review the generated draft before saving and testing the agent.
#Added Agent Aliases documentation: a concept page covering the routed policy model (ordered rules, single and weighted targets, partition_by hashing, resolution fixed at session creation, and the independent alias and agent key namespaces) and a how-to covering direct aliases, canary rollouts, tenant routing, and policy replacement via /v2/agent_aliases
#Added Call other tools from lambda tools documentation covering the in-sandbox tool module, $ref resolution against the hosting agent's secrets and session metadata, and the privacy of composed tools (no agent-surface exposure, no session events)
#Added Visual data documentation for ingesting image-heavy content, with links to the related chunking, tables, and data-ingestion build guides
#Added SharePoint pipeline source documentation covering Azure AD OAuth configuration and site scoping
#Added Google Drive pipeline source documentation and a pipeline session metadata page
#Documented the glossary_put_entries and glossary_delete_entries agent tools on the Glossaries page
#Documented PATCH support on the web_get tool page
#Added Enable SSO with OpenID Connect (OIDC) documentation for the Vectara SaaS deployment, covering registering an OIDC application with any provider (Okta, Microsoft Entra ID, Google Workspace, Ping Identity, OneLogin, and Keycloak), the parameters you exchange with Vectara, the callback URL, email-domain routing, group-to-access-level mapping, the permission model, and connection verification, alongside a new SaaS deployment guides index
#Documented tool server authentication and credential wiring on the Tool Servers page, covering Bearer token, custom header, and OAuth 2.0 client-credentials authentication, service-account (shared) versus per-user (session-scoped) credentials, and synchronizing, updating, and deleting tool servers

Documentation Updates

#FixedCorrected retrieval access-control claims and contrasted the ingest path with the agent-tools path
#UpdatedDocumented how to quote filter field names that contain special characters
#RemovedRemoved the fabricated "SmartChunk" term from the platform-architecture pages
#FixedFixed the Slack connector create example by dropping the top-level type field

May 2026

New Documentation

#Added a standalone UserFn language reference covering the shared expression language used by UDF rerankers, agent step transitions, and pipeline verification. Adds documentation for extract_datetime_part and the knee(sensitivity, early_bias) form, clarifies that seconds/minutes/hours are bidirectional, calls out the lack of then/ternary syntax, and summarizes each caller's context schema in one place
#Added Agent Secrets documentation covering the /v2/agents/{agent_key}/secrets resource, the {"$ref": "agent.secrets.<name>"} pattern in argument_override, masking on read and in tool_input events, and migrating credentials off agent.metadata
#Added Slack Connectors documentation
#Added chunking strategies guide and related docs links

Documentation Updates

#UpdatedDocumented fire_every and skip_first on templated reminders, including the late-conversation reminding pattern for combating context rot and the post-compaction counter reset
#UpdatedAdded a Tool Output Transform section covering jq projection of tool responses, with real web_search / web_get shapes and a search → fetch pairing example
#UpdatedPromoted tool-output gate pattern in agents/steps docs
#UpdatedAdded 'The platform' section explaining architecture, agents, and how to build
#UpdatedAdded integration-points concept doc and web_get how-to
#ChangedMoved Integrations documentation under Agents and cross-linked
#Documentation updates for agents, security, and evaluation
#ClarificationRefined onboarding pages and removed edit page links

April 2026

New Documentation

#Added Glossaries documentation covering term-to-expansion mappings, matching behavior, and attaching glossaries to agent steps via glossary_expansion reminders
#Added Pipelines documentation (quickstart, concepts, sources, verification, dead letters) for automated bulk processing of external data through agents
#Added Multi-Client Steering documentation covering multi-device session consumption, behavior: steer vs follow_up, and mid-turn interrupts
#Added Agent Skills for coding agents docs page
#Added Python SDK Agents documentation
#Added a dedicated Context Engineering section with an opinionated overview and deep-dive pages for Compaction, Reminders, Skills, Tool-Output Offloading, and Steps
#Overview covers the pillars of a well-engineered agent: retrieval, instructions, tool configuration, sub-agent delegation, long-session management, tool-output protection, and monitoring

API Reference Updates

#Updated the API Reference spec with all features released January–April 2026
#Replaced x-supported-api-key-type annotations with x-required-roles on all 133 endpoints, showing exactly which API roles, corpus roles, and agent roles grant access
#Each endpoint page now shows role badges in the authorization section

Documentation Updates

#UpdatedReorganized API Reference sidebar into grouped sections (Agents, Data, Search and Retrieval, Access Control, Analytics, Platform, Quality and Evaluation)
#UpdatedRewrote Role-Based Access Control documentation to cover all four role tiers: API roles (13 account-level roles), corpus roles (viewer/editor/administrator/owner), agent roles (agent_user/agent_viewer/agent_developer/agent_administrator), and platform roles
#UpdatedAdded API conventions and authentication documentation to the API Reference introduction page
#UpdatedAdded retrieval tuning guides and cleaned up search-and-retrieval docs
#UpdatedAdded llms.txt support for docs site
#UpdatedAdded structured output usage guide

March 2026

New Documentation

#Added Context Compaction documentation covering automatic context summarization, session forking, and token limit management
#Added Tool Versioning and Metadata documentation covering category, lineage, version, tool group metadata, and experimental tool marking
#Added Tool-Output Offloading documentation covering configurable thresholds, session artifacts, and artifact_read / artifact_grep / artifact_jq tools

February 2026

New Documentation

#Added Agent Reminders documentation covering re-injection of instructions into user inputs and tool outputs for long-session context management
#Added Multi-Step Agent Workflows documentation covering named steps, step-specific instructions, tools, reminders, and configurable transition conditions
#Added Agent Schedules documentation covering scheduled agent execution at specified intervals, session creation, and execution history
#Added Agent Skills documentation covering named skills for explicit capability invocation and deterministic tool control
#Added Concurrent Agent Sessions documentation covering multi-client interaction, interrupt handling, and collaborative workflows

January 2026

Documentation Updates

#EnhancedEnhance Agents content with updated quickstart, concepts, instructions, and tools

December 2025

New Documentation

#Add new integration between Vectara and Speechmatics
#Enhance agents with configurable, autonomous subagents
#Enhance agent sessions with artifact storage

Documentation Updates

#UpdatedAdd a tutorial about how to build a chatbot with the Agent APIs
#Misc documentation and link fixes
#UpdatedUpdate Vectara trial page
#UpdatedAdd List metadata types and IN operator syntax examples
#UpdatedRestructure API Reference sidebar categories

November 2025

API Reference Updates

#Enhance API Reference with Supported API Key Types for Each Endpoint
#Enhance API Reference endpoint descriptions
#Update the API Reference with Lambda Tool and Artifact enhancements

Documentation Updates

#EnhancedEnhance search and retrieval section

Docs Platform Updates

#Enhance navbar design and convert markup to markdown.
#Navigation improvements
#Enhance documentation structure with new layout
#Enhance CodePanel v2 with a live code editor and syntax highlighting improvements

October 2025

New Documentation

#Enhance Agents with Retry LLM Configuration

API Reference Updates

#Add Agent LLM Retry Configuration to API Reference

Documentation Updates

#UpdatedAdd new tutorial on how to use OpenAI SDK with Vectara Chat Completions API
#UpdatedAdd Conversational AI content to Platform and Agents overviews
#UpdatedUpdate links and formatting in Python SDK Documents

September 2025

New Documentation

#Introduce the tech preview of Vectara Agents Framework
#Introduce new section about Private Deployment options such as on premise

API Reference Updates

#Fix API Reference for Tool and Instruction sections
#Reorganize Agent Sessions in API Reference
#Add Agents APIs to API Reference
#Enhance API Reference with additional improved examples

Documentation Updates

#FixedFix MCP broken link in the agents page
#EnhancedEnhance Agents documentation for Tools and Instructions
#UpdatedRefresh API Reference
#EnhancedEnhance documentation around data I/O, Agents, model selection, and BYO-LLM with additional API Concepts cleanup for accuracy and discoverability

August 2025

New Documentation

#Add documentation for the tech preview of Fuzzy Metadata Search
#Add content about the Vectara Postman Collection
#Add comprehensive documentation for new Vectara Python SDK

API Reference Updates

#Add Metadata Query API to API Reference

Documentation Updates

#UpdatedAdd data egress process content
#UpdatedAdd topic about how to delete an account

July 2025

New Documentation

#Add documentation for the Vectara Admin Center, a centralized interface for managing on-premise and VPC deployments
#New Consistency-Adjusted Index Capability in Open RAG Eval

Documentation Updates

#FixedFix body request render in API Reference
#EnhancedEnhance API Reference usability with automated API key type badges
#UpdatedAdd detailed mapping of endpoints to required API key types
#UpdatedUpdate Query History and Configure Queries sections, enhancing descriptions and screenshots
#EnhancedEnhance chatbot tutorial with production readiness guidance
#UpdatedAdd guidance on using expected value formats with Intelligent Query Rewriting

Docs Platform Updates

#Migrate codeblocks to use the new CodePanel plugin formatting
#Enable syntax highlighting in CodePanel component

June 2025

New Documentation

#Add Query-Aware Hallucination Detection and Correction to the Vectara Hallucination Corrector
#Add new supported languages and enhancements with HHEM 2.3

Documentation Updates

#UpdatedRefresh list of currently available generation presets (prompts)
#UpdatedAdd tutorial about how to build a chatbot with the Chat API
#UpdatedUpdate screenshots for console updates

Example Updates

#Enhance API Documentation with Production-Ready Examples for Query, Upload, Index, and Chat Endpoints

Docs Platform Updates

#Create new CodePanel component for customizable code samples with language selection, annotations, and layout configuration

May 2025

New Documentation

#Add documentation for the List Hallucination Correctors API
#Add documentation for the tech preview of the Vectara Hallucination Corrector
#Add documentation for Table Summarization with Custom Prompts

API Reference Updates

#Update the Correct Hallucinations endpoint in the API Reference
#Add Hallucination Correctors endpoint to the API Reference

Documentation Updates

#EnhancedImprove API Reference description formatting
#UpdatedUpdate the Correct Hallucinations API Definition

Example Updates

#Update Hallucination Corrector model example

Docs Platform Updates

#Update Docusaurus configuration to show last date a topic was updated

April 2025

New Documentation

#Add documentation for the Chat Completions API
#Add documentation for the Evaluate Factual Consistency (HHEM) API
#Add documentation for Mockingbird 2
#Add documentation to define a custom LLM configuration to use models from OpenAI, Anthropic, and Google

API Reference Updates

#Add the Evaluate Factual Consistency API and the Chat Completions API to the API Reference

Documentation Updates

#EnhancedExpand Authentication section with new guides on enterprise access patterns, organizational role scoping, and authorization workflows

Docs Platform Updates

#Refine design of heading styles
#Install Mermaid for creating diagrams
#Update package.json with API documentation build script
#Upgrade Docusaurus Platform from 2.4.3 to 3.7

March 2025

New Documentation

#Add documentation for the tech preview of the Expanded Encoder Management
#Add documentation for the tech preview of the expanded LLM Management APIs
#Add content for new integration between Vectara and Confluent

API Reference Updates

#Add List Table Extractors and Get OAuth Token to the API Reference
#Add the Delete LLM API, Get LLM API, and Create Encoder API and Chunking Strategy to the API Reference

Documentation Updates

#UpdatedUpdate Encoder parameters
#ClarificationClarify that filterable metadata fields are not encrypted
#UpdatedUpdate content and screenshots for the File Upload UI, the Documents UI, and the Query UI
#UpdatedUpdate model_parameters with new llm_name parameter in the advanced summarization options

Example Updates

#Update Encoder examples

February 2025

New Documentation

#Add documentation for the tech preview of Integrating External LLMs
#Add documentation for the tech preview of Document Summarization
#Add documentation for the tech preview of Intelligent Query Rewriting

API Reference Updates

#Add the Summarize Document API, Create LLM API, and Compute Corpus Size API to the API Reference

Documentation Updates

#UpdatedUpdate UI steps on how to reset or delete the corpus

January 2025

New Documentation

#Updated to enable Typescript SDK
#Update HHEM documentation for HHME-2.2
#Add documentation for the new Knee Reranking feature
#Add new HHEM supported languages and some content enhancements

Documentation Updates

#EnhancedImprove Getting Started section layout
#FixedFix broken links in generative prompts
#UpdatedAdd documentation changelog workflow
#FixedFix OAuth2 URL and update screenshot
#UpdatedAdd a dedicated changelog for documentation updates, API enhancements and bug fixes
#UpdatedAdd HHEM 2.2 enhancements to Release Notes

Example Updates

#Fix encoder example with correct value

Deprecations

#Uploading JSON in API v2

Docs Platform Updates

#Update Doc Changelog workflow action

December 2024

New Documentation

#Add documentation for the new Update and Replace Metadata API Definitions
#Add documentation for the querying table data feature
#Add query observability feature to docs
#Add documentation for new chunking strategy parameter

API Reference Updates

#Add API Reference updates for the new tabular data extraction feature

Documentation Updates

#EnhancedImprove information architecture of the Capabilities section and metadata content
#UpdatedUpdate table extract details
#UpdatedUpdate table_extraction_config parameter
#FixedFix link to the table data blog in release notes

Example Updates

#Userfn example supports traditional if statement

Deprecations

#Add API v1 deprecation notices

November 2024

New Documentation

#Add chunking strategy and update descriptions

Documentation Updates

#UpdatedUpdate how metadata structuring is handled in API v2
#UpdatedUpdate descriptions for Pro and Enterprise
#Updatedupdate fern.config.json and generators.yml to use latest version.
#EnhancedEnhance the list of Vectara demos and applications
#ChangedMove Reranking subsection

October 2024

New Documentation

#Reflect product transition to free trial across documentation
#Add new Integrations section that highlights community collaborations and partnerships

API Reference Updates

#updated introduction with proper links
#Get number of documents and document parts
#Add search cutoffs, null handing, and refresh API reference

Documentation Updates

#FixedCorrect udf page misspelling.
#UpdatedUpdate docs for handling filenames with non-ASCII characters in API v2
#UpdatedAdd Release Notes to the docs
#UpdatedUpgrade OpenAPI docs theme.
#UpdatedAdd Video Tutorials section.

Example Updates

#Incorrect syntax in the null score usage chain example
#✨ Add query snippet example
#Update Chain Reranker topic about the array and examples

September 2024

New Documentation

#Add Chain Reranker content

API Reference Updates

#Add request timeouts in docs
#Update corpus API documentation
#Add Generation Presets content to docs

Documentation Updates

#UpdatedUpdate Quick Start
#UpdatedAdd name and description to Update Corpus
#UpdatedUpdate metadata filter topics
#UpdatedUpdate prompt syntax
#UpdatedUpdate custom prompt topics with Query endpoint details and links

Example Updates

#Add more UDF examples

August 2024

New Documentation

#Add User Defined Functions Reranker content

API Reference Updates

#Update query order and labels

Documentation Updates

#UpdatedUpdate introductions to topics in Getting Started and Capabilities

Example Updates

#Improve grpc example for UDF

July 2024

New Documentation

#Add and update topics for Mockingbird
#Add GPT 4o to list of summarizers

API Reference Updates

#Wrap tabs in API reference so they don't get clipped.

Documentation Updates

#UpdatedAdd note about original BM25
#UpdatedUpdate corpus key and file upload content
#FixedFix typos and update screenshots

Example Updates

#Update part.is_title field description

June 2024

New Documentation

#Add new REST API v2 specifications to the documentation

API Reference Updates

#Rename API Playground references to API Reference.
#Update API v2 migration guide
#Put generation_end into the reference.
#Re-enable accordion transition in API playground, to fix bug in which content height wasn't updated correctly

Documentation Updates

#UpdatedUpdate API v2 download URL
#FixedFix typos in spec.
#ChangedChange nav from API Playground -> API Reference.
#FixedFix tips in query endpoint
#FixedFix link to Reranking blog

Example Updates

#Fix oauth examples.

May 2024

New Documentation

#Update Reranker topic with the new Vectara Multilingual Reranker v1
#Add citation summary feature content

Documentation Updates

#FixedFix query body request
#ClarificationPoint ReactSearch to updated reranker
#UpdatedUpdate citation section
#FixedFix reranking link
#UpdatedAdd examples for functions and operations
#UpdatedAdd summarized search
#UpdatedUpdate Information Architecture with new sections for Capabilities and Use Cases

April 2024

New Documentation

#Add docs for stream concatenation, React-Chatbot, and Stream-Query-Client
#Add Stream Query to the API Playground
#Add new Stream Query API Definition content

API Reference Updates

#Improve List Conversations API parameter descriptions
#Improve prompt examples in query, and update the enable api key and file upload endpoints
#Update prompts to use single-quote in examples
#Update Create Corpus default example
#Fix values in the query body endpoint

Example Updates

#Add context configuration to Query and Highlighting topics

March 2024

New Documentation

#Update the API Playground with Factual Consistency Score
#Add content about the new Factual Consistency Score

API Reference Updates

#Update Playground example for FCS
#Update API References examples for Query, Indexing, and API Keys
#Update Query example in API Playground
#Update API Reference examples for consistency

Documentation Updates

#UpdatedUpdate Chat APIs overview
#UpdatedUpdate API Reference section with improved structure and flow

Example Updates

#Update file formats and document structuring
#Add Content-Disposition header to set the Document ID

February 2024

New Documentation

#Add Generative Prompts section
#Add documentation for the new Vectara Chat
#Add documentation for the Personal API Key, Index, and Query Keys

API Reference Updates

#Add custom prompts to Query
#Update the API Playground for Chat APIs
#Update API Playground for the Personal API Keys

Documentation Updates

#UpdatedUpdate console and corpus content around account and corpus creation

January 2024

New Documentation

#Add Create-UI and refine copy and layout of Build Apps landing page
#Add Get Usage Metrics to API Playground
#Add List Documents content to Console and API Reference
#Add Account and Corpus Management APIs to Playground
#Add Read Corpus and Update Corpus Enablement topics

API Reference Updates

#Update File Upload API specs
#Add List Documents to API Playground

Documentation Updates

#UpdatedAdd Build Applications section
#UpdatedUpdate banner with Airbyte partnership information
#FixedFix reranker URL and update search topic with new formatting
#EnhancedImprove the Index API Definition content

Example Updates

#Update List Documents response example

December 2023

New Documentation

#Add Manager User and List Users to API Playground
#Add List Users and Manage Users topics
#create, delete, enable, list API keys

Documentation Updates

#FixedFix Q&A redirect
#Indexing documentation is out of date.
#ChangedMigrate from data store term to corpus.
#UpdatedAdd API Keys topics to API Reference
#UpdatedAdd MMR to the Reranking topic
#UpdatedAdd content about Data Ingestion
#UpdatedAdd content about the Index Request Headers
#UpdatedUpdated content about the English and MMR rerankers

Example Updates

#Improve Information Architecture and update several examples

Docs Platform Updates

#Support deep-linking to a search.
#Support search on narrower screens (e.g. mobile)

November 2023

New Documentation

#Add update filter attributes and list jobs to the OpenAPI spec

Documentation Updates

#UpdatedUpdate banner for the new metadata filtering capability
#UpdatedAdd content about structuring document data
#UpdatedUpdate Quick Start with steps, field names, and screenshots
#UpdatedAdd the grpc-timeout option in header to several topics

Example Updates

#Update Code Samples with specific category for Query Operations

Docs Platform Updates

#Customize Not Found page.
#Make search more prominent.
#Add a console button to the navigation bar
#Update search with Ctrl-K shortcut.
#Ensure rendering a single instance of search
#Fix rendering of API Playground code in dark mode.
#Add TopicButton, Grid, and Spacer components.