> ## Documentation Index > Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt > Use this file to discover all available pages before exploring further. # Sitecore V2 > The Sitecore V2 connector provides full crawl and incremental crawl support for Sitecore versions 8.x and 9.x. It indexes document content and all metadata. export const schema = { "type": "object", "title": "SiteCore (v2)", "description": "Connector for SiteCore", "required": ["parserId", "id", "properties", "pipeline"], "properties": { "parserId": { "type": "string", "title": "Parser ID", "description": "The Parser to use in the associated IndexPipeline." }, "id": { "type": "string", "title": "Configuration ID", "description": "A unique identifier for this Configuration.", "minLength": 1, "pattern": "^[a-zA-Z0-9_-]+$" }, "pipeline": { "type": "string", "title": "Pipeline ID", "description": "Name of the IndexPipeline used for processing output.", "minLength": 1, "pattern": "^[a-zA-Z0-9_-]+$" }, "description": { "type": "string", "title": "Description", "description": "Optional description", "hints": ["lengthy"], "maxLength": 125 }, "modified": { "type": "string", "title": "Date Modified", "description": "The date at which this Configuration was last modified.", "hints": ["readonly", "hidden"] }, "created": { "type": "string", "title": "Date Created", "description": "The date at which this Configuration was created.", "hints": ["readonly", "hidden"] }, "type": { "type": "string", "title": "Type", "description": "A type ID for this connector.", "hints": ["readonly", "hidden"] }, "collection": { "type": "string", "title": "Collection ID", "description": "The associated content Collection.", "hints": ["readonly", "hidden"], "minLength": 1, "pattern": "^[a-zA-Z0-9_-]+$" }, "diagnosticLogging": { "type": "boolean", "title": "Diagnostic Logging", "description": "[Deprecated] Enables verbose diagnostic logging for troubleshooting. May increase log volume. Disabled by default.", "default": false }, "type_description": { "type": "string", "title": "Type Description", "default": "Connector for SiteCore", "hints": ["hidden", "readonly"] }, "category": { "type": "string", "title": "Category", "default": "Connector for SiteCore", "hints": ["hidden", "readonly"] }, "connector": { "title": "Connector Type", "description": "Connector type.", "minLength": 1, "type": "string", "hints": ["hidden"] }, "properties": { "type": "object", "title": "Plugin Configuration", "description": "Plugin specific properties.", "required": ["sitecoreServerURL", "sitecoreUsername", "itemPaths", "indexMetadata"], "properties": { "sitecoreServerURL": { "type": "string", "title": "SiteCore server URL", "description": "SiteCore server root URL (https://)" }, "sitecoreUsername": { "type": "string", "title": "SiteCore username", "description": "An administrator SiteCore username" }, "sitecorePassword": { "type": "string", "title": "SiteCore password", "description": "The password of the administrator user", "hints": ["secret"] }, "sitecorePasswordVaultLabel": { "type": "string", "title": "SiteCore password from Vault", "description": "The Fusion managed secret to use for SiteCore password.", "hints": ["enumUrl:/apps-manager/vault/labels?type=secret", "vaultref", "vaultvaluetarget:sitecorePassword"] }, "itemPaths": { "type": "array", "title": "Item paths to index", "description": "A list of SiteCore Item paths to be indexed ex. '/sitecore/content/Home' ", "default": ["/sitecore/content/Home"], "items": { "type": "string" } }, "sitecoreDatabase": { "type": "string", "title": "SiteCore context database", "description": "SiteCore context database to use when accessing SiteCore. For example: master, web, core. If you leave this blank, the connector will pick the default database associated with your current user." }, "indexMetadata": { "type": "boolean", "title": "Index item metadata", "description": "If enabled, the item metadata will be added to the indexed document", "default": true, "hints": ["advanced"] }, "fetchRetryProperties": { "type": "object", "title": "Retry Options", "description": "A set of options for configuring retry behavior.", "required": ["delayMs", "maxDelayTimeMs", "delayFactor"], "properties": { "maxRetries": { "type": "number", "title": "Maximum Retries", "description": "The retryer will retry failed operations in the case that they might succeed if attempted again. This parameter states the number of attempts to retry until giving up. This parameter, if specified, will override the \"Stop retrying after time (milliseconds)\" parameter.", "default": 3, "maximum": 100, "exclusiveMaximum": false, "minimum": 0, "exclusiveMinimum": false, "multipleOf": 1 }, "delayFactor": { "type": "number", "title": "Delay Factor", "description": "The retryer will retry failed operations in the case that they might succeed if attempted again. The retryer will sleep an exponential amount of time after the first failed attempt and retry in exponentially incrementing amounts after each failed attempt up to the maximumTime. nextWaitTime = exponentialIncrement * multiplier.", "default": 2, "maximum": 9999, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "delayMs": { "type": "number", "title": "Retry Delay", "description": "Sets the delay between retries, exponentially backing off to the maxDelayTimeMs and multiplying successive delays by the delayFactor", "default": 1000, "maximum": 9223372036854776000, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "maxDelayTimeMs": { "type": "number", "title": "Maximum Delay Time", "description": "The maximum time wait time between successive retries.", "default": 300000, "maximum": 600000, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "maxTimeLimitMs": { "type": "number", "title": "Maximum Time Limit", "description": "This setting is used to limit the maximum amount of time spent on retries. Note: this will be ignored if \"Maximum Retries\" is specified.", "default": 600000, "maximum": 28800000, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "errorExclusions": { "type": "array", "title": "Error Exclusions", "description": "Optional regex list that will be matched against failed attempts exception class and message. If any regex matches, do not retry this request. This is needed to prevent the retryer from retrying non-recoverable errors that were not already ignored by the connector implementation.", "items": { "type": "string", "maxLength": 256, "minLength": 1 } } } }, "connections": { "type": "object", "title": "Http client connection options", "description": "A set of options for configuring the http client behavior.", "required": ["maxConnections"], "properties": { "maxConnections": { "type": "number", "title": "Max connections", "description": "The maximum number of connections", "default": 10, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "ignoreSSLValidationExceptions": { "type": "boolean", "title": "Ignore SSL Validation Exceptions", "description": "Do not attempt to do an SSL Handshake and do not verify the hostname of SSL certificates. Use this when accessing an https url with a self-signed or enterprise certificate authority that you do not want to put in the Java keystore.", "default": false } } }, "timeouts": { "type": "object", "title": "Http timeout options", "description": "A set of options for configuring the http client timeouts.", "required": [], "properties": { "readTimeoutMs": { "type": "number", "title": "", "default": 300000, "maximum": 600000, "exclusiveMaximum": false, "minimum": 0, "exclusiveMinimum": false, "multipleOf": 1 }, "connectTimeoutMs": { "type": "number", "title": "", "default": 60000, "maximum": 300000, "exclusiveMaximum": false, "minimum": 0, "exclusiveMinimum": false, "multipleOf": 1 } } }, "proxyProperties": { "type": "object", "title": "Proxy options", "description": "A set of options for configuring the proxy.", "required": [], "properties": { "url": { "type": "string", "title": "Proxy URL", "description": "The proxy URL", "minLength": 1 }, "username": { "type": "string", "title": "Proxy username", "description": "Proxy username", "minLength": 1 }, "password": { "type": "string", "title": "Proxy password", "description": "Proxy password", "hints": ["secret"], "minLength": 1 }, "passwordVaultLabel": { "type": "string", "title": "Proxy password from Vault", "description": "The Fusion managed secret to use for Proxy password.", "hints": ["vaultvaluetarget:password", "enumUrl:/apps-manager/vault/labels?type=secret", "vaultref"] } } }, "sizeLimitProperties": { "type": "object", "title": "Item Size Limits", "description": "Options for including or excluding items based on size, in bytes.", "required": [], "properties": { "minSizeBytes": { "type": "number", "title": "Minimum", "description": "Used for excluding items when the item size is smaller than the configured value.", "default": 1, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 }, "maxSizeBytes": { "type": "number", "title": "Maximum", "description": "Used for excluding items when the item size is larger than the configured value.", "default": -1, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 } } }, "extensionConfig": { "type": "object", "title": "File Extension rules", "required": [], "properties": { "includedFileExtensions": { "type": "array", "title": "Included file extensions", "description": "Set of file extensions to be fetched. If specified, all non-matching files will be skipped.", "default": [], "items": { "type": "string", "minLength": 1 } }, "excludedFileExtensions": { "type": "array", "title": "Excluded file extensions", "description": "A set of all file extensions to be skipped from the fetch.", "default": [], "items": { "type": "string", "minLength": 1 } }, "regexCacheSize": { "type": "number", "title": "Regex Cache Size", "description": "The number of regex matches to cache when evaluating regular expressions. For example if you exclude files by filename, each filename's regex result will be cached so that if this same filename came up again, the regex matches would be remembered.", "default": 10000, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 } } }, "regexConfig": { "type": "object", "title": "Regular expression rules", "required": [], "properties": { "inclusiveRegexes": { "type": "array", "title": "Inclusive regexes", "description": "Regular expressions for URI patterns to include. This will limit this datasource to only URIs that match the regular expression.", "default": [], "items": { "type": "string", "minLength": 1 } }, "exclusiveRegexes": { "type": "array", "title": "Exclusive regexes", "description": "Regular expressions for URI patterns to exclude. This will limit this datasource to only URIs that do not match the regular expression.", "default": [], "items": { "type": "string", "minLength": 1 } }, "regexCacheSize": { "type": "number", "title": "Regex Cache Size", "description": "The number of regex matches to cache when evaluating regular expressions. For example if you exclude files by filename, each filename's regex result will be cached so that if this same filename came up again, the regex matches would be remembered.", "default": 10000, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 } } }, "depthLimitConfig": { "type": "object", "title": "Item Depth Limits", "required": [], "properties": { "maxDepth": { "type": "number", "title": "Maximum Item Depth", "description": "Maximum depth level for fetch items. If an item has a depth greater than the configured value, it will not be fetched. The default is \"no limit\" (-1).", "default": -1, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 } } }, "mimeTypeProperties": { "type": "object", "title": "MIME Types", "description": "Options for including or excluding items, based on MIME types.", "required": [], "properties": { "excludedMimeTypes": { "type": "array", "title": "Excluded mime types", "description": "A list of the Mime types to exclude from this crawl. NOTE: This is only used if the \"Mime Type Includes\" field is empty.", "items": { "type": "string" } }, "includedMimeTypes": { "type": "array", "title": "Included mime types", "description": "A list of the Mime types to include in this crawl. Note: If you specify includes, the exclude mime types property will be ignored.", "items": { "type": "string" } } } }, "databaseProperties": { "type": "object", "title": "Database properties", "description": "A set of options for configuring the connection to the database used for incremental crawls.", "required": ["sitecoreDatabaseMaxQuerySize", "sitecoreDatabasePort"], "properties": { "sitecoreDatabaseHost": { "type": "string", "title": "SiteCore database JDBC host", "description": "The SiteCore SQL Server host. Example: 192.168.1.59 Note: This is only needed for faster incremental updates. If not specified, updates will be done with a recrawl strategy." }, "sitecoreDatabasePort": { "type": "number", "title": "SiteCore database JDBC port", "description": "The SiteCore SQL Server port. Typically this is the sql server default of 1433.", "default": 1433, "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 }, "sitecoreDatabaseName": { "type": "string", "title": "SiteCore master database name", "description": "The SiteCore master database's name. Example: sc902_Master" }, "sitecoreDatabaseUsername": { "type": "string", "title": "SiteCore database username", "description": "The SiteCore database username. Only SELECT access is required for this user on the sc*_Master database for these tables: [Items, ArchivedItems, PublishQueue]." }, "sitecoreDatabasePassword": { "type": "string", "title": "SiteCore database password", "description": "The SiteCore database user password.", "hints": ["secret"] }, "sitecoreDatabasePasswordVaultLabel": { "type": "string", "title": "SiteCore database password from Vault", "description": "The Fusion managed secret to use for SiteCore database password.", "hints": ["enumUrl:/apps-manager/vault/labels?type=secret", "vaultref", "vaultvaluetarget:sitecoreDatabasePassword"] }, "sitecoreDatabaseMaxQuerySize": { "type": "number", "title": "SiteCore database query max page size", "description": "The maximum number of query results that can be returned from SiteCore database at once.", "default": 10000, "hints": ["advanced"], "maximum": 2147483647, "exclusiveMaximum": false, "minimum": -2147483648, "exclusiveMinimum": false, "multipleOf": 1 } } } } }, "coreProperties": { "type": "object", "title": "Core Properties", "description": "Common behavior and performance settings.", "required": [], "properties": { "fetchSettings": { "type": "object", "title": "Fetch Settings", "description": "System level settings for controlling fetch behavior and performance.", "required": [], "properties": { "numFetchThreads": { "type": "number", "title": "Fetch Threads", "description": "Maximum number of fetch threads; defaults to 5.This setting controls the number of threads that call the Connectors fetch method.Higher values can, but not always, help with overall fetch performance.", "default": 5, "maximum": 500, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "indexingThreads": { "type": "number", "title": "Index Subscription Threads", "description": "Maximum number of indexing threads; defaults to 4.This setting controls the number of threads in the indexing service used for processing content documents emitted by this datasource.Higher values can sometimes help with overall fetch performance.", "default": 4, "maximum": 10, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "pluginInstances": { "type": "number", "title": "Number of plugin instances for distributed fetching", "description": "Maximum number of plugin instances for distributed fetching. Only specified number of plugin instanceswill do fetching. This is useful for distributing load between different instances.", "default": 0, "maximum": 500, "exclusiveMaximum": false, "minimum": 0, "exclusiveMinimum": false, "multipleOf": 1 }, "fetchItemQueueSize": { "type": "number", "title": "Fetch Item Queue Size", "description": "Size of the fetch item queue.Larger values result in increased memory usage, but potentially higher performance.Default is 10k.", "default": 10000, "hints": ["hidden"], "maximum": 500000, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "indexMetadata": { "type": "boolean", "title": "Index metadata", "description": "When enabled the metadata of skipped items will be indexed to the content collection.", "default": false }, "fetchRequestCheckInterval": { "type": "number", "title": "Fetch request check interval(ms)", "description": "The amount of time to wait before check if a request is done", "default": 15000, "hints": ["hidden"], "maximum": 500000, "exclusiveMaximum": false, "minimum": 1000, "exclusiveMinimum": false, "multipleOf": 1 }, "fetchResponseScheduledTimeout": { "type": "number", "title": "Fetch response scheduled timeout(ms)", "description": "The maximum amount of time for a response to be scheduled. The task will be canceled if this setting is exceeded.", "default": 300000, "maximum": 500000, "exclusiveMaximum": false, "minimum": 1000, "exclusiveMinimum": false, "multipleOf": 1 }, "fetchResponseCompletedTimeout": { "type": "number", "title": "Fetch response completion timeout(ms)", "description": "The maximum amount of time for a response to be completed. If exceeded, the task will be retried if the job is still running", "default": 300000, "hints": ["hidden"], "maximum": 600000, "exclusiveMaximum": false, "minimum": 1, "exclusiveMinimum": false, "multipleOf": 1 }, "indexingInactivityTimeout": { "type": "number", "title": "Indexing inactivity timeout(seconds)", "description": "The maximum amount of time to wait for indexing results (in seconds). If exceeded, the job will fail with an indexing inactivity timeout.", "default": 86400, "maximum": 691200, "exclusiveMaximum": false, "minimum": 60, "exclusiveMinimum": false, "multipleOf": 1 }, "pluginInactivityTimeout": { "type": "number", "title": "Plugin inactivity timeout(seconds)", "description": "The maximum amount of time to wait for plugin activity (in seconds). If exceeded, the job will fail with a plugin inactivity timeout.", "default": 600, "maximum": 691200, "exclusiveMaximum": false, "minimum": 60, "exclusiveMinimum": false, "multipleOf": 1 }, "indexContentFields": { "type": "boolean", "title": "Index content fields", "description": "When enabled, content fields will be indexed to the crawl-db collection.", "default": false }, "asyncParsing": { "type": "boolean", "title": "Async Parsing", "description": "When enabled, content will be indexed asynchronously.", "default": false } } }, "strayDeletionSettings": { "type": "object", "title": "Stray Content Deletion Settings", "description": "System level settings for controlling stray content deletion behavior", "required": [], "properties": { "enableStrayDeletion": { "type": "boolean", "title": "Enable Stray Deletion", "description": "When enabled, items not re-encountered in the current crawl are deleted from the content collection. Defaults to true.", "default": true }, "circuitBreakerSettings": { "type": "object", "title": "Circuit Breaker Settings", "description": "Settings that control the circuit breaker, which prevents mass deletion when an unusually high percentage of items are identified as stray in a crawl.", "required": [], "properties": { "percentageThreshold": { "type": "number", "title": "Stray Deletion Threshold (%)", "description": "Maximum percentage of indexed items that may be deleted as stray in a crawl. If the total stray item exceeds this percentage, the circuit breaker blocks the deletion to prevent accidental data loss. Accepts values from 0 to 100. Defaults to 80.", "default": 80, "maximum": 100, "exclusiveMaximum": false, "minimum": 0, "exclusiveMinimum": false, "multipleOf": 1 }, "enableCircuitBreaker": { "type": "boolean", "title": "Enable Circuit Breaker", "description": "When enabled, stray deletion is blocked if the percentage of items to be deleted exceeds the configured threshold. Disable only if unconditional stray deletion is required regardless of volume. Defaults to true.", "default": true } } } } }, "skipConfigValidation": { "type": "boolean", "title": "Skip Validation", "description": "Enable to skip configuration validation when it takes too long and causes timeout issue", "default": false } }, "hints": ["advanced"] } }, "category": "File System", "categoryPriority": 1 }; export const SchemaParamFields = ({schema}) => { const sanitize = str => { if (typeof str !== "string") return str; return str.replace(/^"(.*)"$/s, "$1").replace(/\\/g, "").replace(/"/g, "'"); }; const formatDescription = str => { const s = sanitize(str); return (/[.!?]\)*$/).test(s) ? s : `${s}.`; }; const {description, properties = {}, required: requiredProps = []} = schema; const visibleProps = useMemo(() => Object.entries(properties).filter(([, prop]) => !prop.hints?.includes("hidden")), [properties]); return
{description &&

{formatDescription(description)}

} {visibleProps.map(([name, prop]) => { const isRequired = requiredProps.includes(name); const hasDefault = prop.default !== undefined; const rawDefault = prop.default; const isComplexDefault = hasDefault && (typeof rawDefault === "object" || typeof rawDefault === "string" && (rawDefault.length > 20 || rawDefault.includes('"'))); const fieldProps = { key: name, body: prop.title || name, type: prop.type, ...prop.title && ({ post: [<>API property: {name}] }), ...isRequired && ({ required: true }), ...!isComplexDefault && hasDefault ? { default: sanitize(String(rawDefault)) } : {} }; const isObject = prop.type === "object" && prop.properties; const isArrayOfObjects = prop.type === "array" && prop.items?.type === "object" && prop.items.properties; return {prop.description &&

{formatDescription(prop.description)}

} {isComplexDefault &&

Default: 

                  
                    {JSON.stringify(rawDefault, null, 2)}
} {isArrayOfObjects &&

Object attributes: 

                
                  {'{\n'}
                  {Object.entries(prop.items.properties).map(([iname, iprop]) => <>
                      {`  ${iname}`}
                      {prop.items?.required?.includes(iname) &&  required}
                      {`: {\n    display name: ${sanitize(iprop.title || '')}\n    type: ${iprop.type}\n  }\n`}
                    )}
                  {'}'}
} {isObject && } ; })}
; }; export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => { const [isLoaded, setIsLoaded] = useState(false); useEffect(() => { const timer = setTimeout(() => { setIsLoaded(true); }, 500); return () => clearTimeout(timer); }, []); return
{isLoaded && ` }} />} Powered by Lucidworks Agent Studio
; }; [localhost link]: http://localhost:3000/docs/fusion-connectors/connectors/sitecore [mintlify link]: https://doc.lucidworks.com/docs/fusion-connectors/connectors/sitecore [old doc.lw link]: https://doc.lucidworks.com/fusion-connectors/68 * **Latest version:** v3.1.0 * **Compatible with Fusion version:** 4.2.0 and later To configure this connector, you need: * Your Sitecore URL * One or more content paths * A Sitecore administrator username and password ## Remote connectors V2 connectors support [running remotely](/docs/fusion-connectors/developers/remote-v2-connectors) in Fusion versions 5.7.1 and later. If you need to index data from behind a firewall, you can configure a V2 connector to run remotely on-premises using TLS-enabled gRPC. ## Prerequisites Before you can set up an on-prem V2 connector, you must configure the egress from your network to allow HTTP/2 communication into the Fusion cloud. You can use a [forward proxy server](#egress-and-proxy-server-configuration) to act as an intermediary between the connector and Fusion. The following is required to run V2 connectors remotely: * The [plugin zip file and the connector-plugin-standalone JAR](https://plugins.lucidworks.com/). * A configured connector backend gRPC endpoint. * Username and password of a user with a `remote-connectors` or `admin` role. * If the host where the remote connector is running is not configured to trust the server’s TLS certificate, you must configure the file path of the trust certificate collection. If your version of Fusion doesn’t have the `remote-connectors` role by default, you can create one. No API or UI permissions are required for the role. ## Connector compatibility Only V2 connectors are able to run remotely on-premises. You also need the remote connector client JAR file that matches your Fusion version. You can download the latest files at [V2 Connectors Downloads](/docs/fusion-connectors/downloads/v2-connectors-downloads). Whenever you upgrade Fusion, you must also update your remote connectors to match the new version of Fusion. The gRPC connector backend is not supported in Fusion environments deployed on AWS. ## System requirements The following is required for the on-prem host of the remote connector: * (Fusion 5.9.0-5.9.10) JVM version 11 * (Fusion 5.9.11) JVM version 17 * Minimum of 2 CPUs * 4GB Memory Note that memory requirements depend on the number and size of ingested documents. ## Enable backend ingress In your `values.yaml` file, configure this section as needed: ```yaml theme={"dark"} ingress: enabled: false pathtype: "Prefix" path: "/" #host: "ingress.example.com" ingressClassName: "nginx" # Fusion 5.9.6 only tls: enabled: false certificateArn: "" # Enable the annotations field to override the default annotations #annotations: "" ``` * Set `enabled` to `true` to enable the backend ingress. * Set `pathtype` to `Prefix` or `Exact`. * Set `path` to the path where the backend will be available. * Set `host` to the host where the backend will be available. * In Fusion 5.9.6 *only*, you can set `ingressClassName` to one of the following: * `nginx` for Nginx Ingress Controller * `alb` for AWS Application Load Balancer (ALB) * Configure TLS and certificates according to your CA’s procedures and policies. TLS must be enabled in order to use AWS ALB for ingress. ## Connector configuration example ```yaml theme={"dark"} kafka-bridge: target: mynamespace-connectors-backend.lucidworkstest.com:443 # mandatory plain-text: false # optional, false by default. proxy-server: # optional - needed when a forward proxy server is used to provide outbound access to the standalone connector host: host port: some-port user: user # optional password: password # optional trust: # optional - needed when the client's system doesn't trust the server's certificate cert-collection-filepath: path1 proxy: # mandatory fusion-proxy user: admin password: password123 url: https://fusiontest.com/ # needed only when the connector plugin requires blob store access plugin: # mandatory path: ./fs.zip type: #optional - the suffix is added to the connector id suffix: remote ``` ### Minimal example ```yaml theme={"dark"} kafka-bridge: target: mynamespace-connectors-backend.lucidworkstest.com:443 proxy: user: admin password: "password123" plugin: path: ./testplugin.zip ``` ### Logback XML configuration file example ```xml theme={"dark"} %d - %-5p [%t:%C{3.}@%L] - %m{nolookups}%n utf8 ${LOGDIR:-.}/connector.log ${LOGDIR:-.}/connector-%d{yyyy-MM-dd}.%i.log.gz 50MB 10GB %d - %-5p [%t:%C{3.}@%L] - %m{nolookups}%n utf8 ``` ## Run the remote connector ```java theme={"dark"} java [-Dlogging.config=[LOGBACK_XML_FILE]] \ -jar connector-plugin-client-standalone.jar [YAML_CONFIG_FILE] ``` The `logging.config` property is optional. If not set, logging messages are sent to the console. ## Test communication You can run the connector in communication testing mode. This mode tests the communication with the backend without running the plugin, reports the result, and exits. ```java theme={"dark"} java -Dstandalone.connector.connectivity.test=true -jar connector-plugin-client-standalone.jar [YAML_CONFIG_FILE] ``` ## Encryption In a deployment, communication to the connector’s backend server is encrypted using TLS. You should only run this configuration without TLS in a testing scenario. To disable TLS, set `plain-text` to `true`. ## Egress and proxy server configuration One of the methods you can use to allow outbound communication from behind a firewall is a proxy server. You can configure a proxy server to allow certain communication traffic while blocking unauthorized communication. If you use a proxy server at the site where the connector is running, you must configure the following properties: * **Host.** The hosts where the proxy server is running. * **Port.** The port the proxy server is listening to for communication requests. * **Credentials.** Optional proxy server user and password. When you configure egress, it is important to disable any connection or activity timeouts because the connector uses long running gRPC calls. ## Password encryption If you use a login name and password in your configuration, run the following utility to encrypt the password: 1. Enter a user name and password in the [connector configuration YAML](#configuration). 2. Run the standalone JAR with this property: ```java theme={"dark"} -Dstandalone.connector.encrypt.password=true ``` 3. Retrieve the encrypted passwords from the log that is created. 4. Replace the clear password in the configuration YAML with the encrypted password. ## Connector restart (5.7 and earlier) The connector will shut down automatically whenever the connection to the server is disrupted, to prevent it from getting into a bad state. Communication disruption can happen, for example, when the server running in the `connectors-backend` pod shuts down and is replaced by a new pod. Once the connector shuts down, connector configuration and job execution are disabled. To prevent that from happening, you should restart the connector as soon as possible. You can use Linux scripts and utilities to restart the connector automatically, such as [Monit](https://mmonit.com/monit/). ## Recoverable bridge (5.8 and later) If communication to the remote connector is disrupted, the connector will try to recover communication and gRPC calls. By default, six attempts will be made to recover each gRPC call. The number of attempts can be configured with the `max-grpc-retries` bridge parameters. ## Job expiration duration (5.9.5 only) The timeout value for irresponsive backend jobs can be configured with the `job-expiration-duration-seconds` parameter. The default value is `120` seconds. ## Use the remote connector Once the connector is running, it is available in the Datasources dropdown. If the standalone connector terminates, it disappears from the list of available connectors. Once it is re-run, it is available again and configured connector instances will not get lost. ## Enable asynchronous parsing (5.9 and later) To separate document crawling from document parsing, enable Tika Asynchronous Parsing on remote V2 connectors. Below is an example configuration showing how to specify the file system to index under the `connector-plugins` entry in your `values.yaml` file: ```yaml wrap theme={"dark"} additionalVolumes: - name: fusion-data1-pvc persistentVolumeClaim: claimName: fusion-data1-pvc - name: fusion-data2-pvc persistentVolumeClaim: claimName: fusion-data2-pvc additionalVolumeMounts: - name: fusion-data1-pvc mountPath: "/connector/data1" - name: fusion-data2-pvc mountPath: "/connector/data2" ``` You may also need to specify the user that is authorized to access the file system, as in this example: ```yaml wrap theme={"dark"} securityContext: fsGroup: 1002100000 runAsUser: 1002100000 ``` ## Configuration When entering configuration values in the UI, use *unescaped* characters, such as `\t` for the tab character. When entering configuration values in the API, use *escaped* characters, such as `\\t` for the tab character.