> ## 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.

# Azure V1

> The Azure V1 connector is used to crawl an Azure instance.

export const schema = {
  "type": "object",
  "title": "Azure",
  "description": "Crawl Azure objects.",
  "required": ["id", "connector", "type", "pipeline", "properties"],
  "properties": {
    "category": {
      "type": "string",
      "title": "Category",
      "default": "Repository",
      "hints": ["hidden", "readonly"]
    },
    "id": {
      "type": "string",
      "title": "Datasource ID",
      "description": "Unique name for this datasource.",
      "minLength": 1,
      "pattern": "^[a-zA-Z0-9_-]+$"
    },
    "connector": {
      "type": "string",
      "title": "Connector Type",
      "description": "Connector Type.",
      "hints": ["hidden"],
      "minLength": 1
    },
    "type": {
      "type": "string",
      "title": "Datasource Type",
      "description": "Datasource type supported by the selected connector type.",
      "hints": ["hidden"],
      "minLength": 1
    },
    "pipeline": {
      "type": "string",
      "title": "Pipeline ID",
      "description": "Name of an existing index pipeline for processing documents.",
      "minLength": 1
    },
    "description": {
      "type": "string",
      "title": "Description",
      "description": "Optional description for this datasource."
    },
    "type_description": {
      "type": "string",
      "title": "Type Description",
      "default": "Crawl Azure objects.",
      "hints": ["hidden", "readonly"]
    },
    "parserId": {
      "type": "string",
      "title": "Parser",
      "description": "Parser used when parsing raw content. For some connectors, a configuration to 'retry' parsing if an error occurs is available as an advanced setting"
    },
    "properties": {
      "type": "object",
      "title": "Properties",
      "description": "Datasource configuration properties",
      "required": ["service_type", "storage_account", "token_secret"],
      "properties": {
        "collection": {
          "type": "string",
          "title": "Collection",
          "description": "Collection documents will be indexed to.",
          "hints": ["hidden"],
          "pattern": "^[a-zA-Z0-9_-]+$"
        },
        "db": {
          "type": "object",
          "title": "Connector DB",
          "description": "Type and properties for a ConnectorDB implementation to use with this datasource.",
          "required": ["type"],
          "properties": {
            "type": {
              "type": "string",
              "title": "Implementation Class Name",
              "description": "Fully qualified class name of ConnectorDb implementation.",
              "default": "com.lucidworks.connectors.db.impl.MapDbConnectorDb",
              "minLength": 1
            },
            "inlinks": {
              "type": "boolean",
              "title": "Process Inlinks?",
              "description": "Keep track of incoming links. This negatively impacts performance and size of DB.",
              "default": false
            },
            "aliases": {
              "type": "boolean",
              "title": "Process Aliases?",
              "description": "Keep track of original URI-s that resolved to the current URI. This negatively impacts performance and size of DB.",
              "default": false
            },
            "inv_aliases": {
              "type": "boolean",
              "title": "Process Inverted Aliases?",
              "description": "Keep track of target URI-s that the current URI resolves to. This negatively impacts performance and size of DB.",
              "default": false
            }
          },
          "hints": ["hidden"]
        },
        "service_type": {
          "type": "string",
          "title": "Azure service type",
          "description": "The Azure service type to crawl, either Blobs or Tables.",
          "enum": ["Azure Table", "Azure Blob"]
        },
        "storage_account": {
          "type": "string",
          "title": "Storage Account",
          "description": "The Azure storage account name.",
          "minLength": 1
        },
        "token_secret": {
          "type": "string",
          "title": "Token Secret",
          "description": "A valid Azure Access Key for authentication.",
          "hints": ["secret"],
          "minLength": 1
        },
        "max_threads": {
          "type": "integer",
          "title": "Maximum number of threads",
          "description": "The maximum number of threads to use for fetching data. Each thread will create a new connection to the repository, which may make overall throughput faster, but will also require more system resources including CPU and memory.",
          "default": 5
        },
        "max_connections": {
          "type": "integer",
          "title": "Maximum number of connections",
          "description": "Maximum number of simultaneous connections to the repository. This value usually does not need to be changed.",
          "default": 5000
        },
        "storage_container": {
          "type": "string",
          "title": "Storage Container",
          "description": "The name of an Azure Blob container.",
          "minLength": 1
        },
        "max_bytes": {
          "type": "integer",
          "title": "Max Bytes",
          "description": "The maximum size, in bytes, of a document to crawl.",
          "default": 10485760
        },
        "tables": {
          "type": "string",
          "title": "Table name",
          "description": "The Azure table to index.",
          "minLength": 1
        },
        "table_filter_statement": {
          "type": "string",
          "title": "Table Filter Statement",
          "description": "A filter to apply to the crawl. Use Azure's syntax for filtering table queries.",
          "hints": ["lengthy"]
        },
        "commit_on_finish": {
          "type": "boolean",
          "title": "Solr commit on finish",
          "description": "Set to true for a request to be sent to Solr after the last batch has been fetched to commit the documents to the index.",
          "default": true,
          "hints": ["advanced"]
        },
        "initial_mapping": {
          "type": "object",
          "title": "Initial field mapping",
          "description": "Provides mapping of fields before documents are sent to an index pipeline.",
          "properties": {
            "skip": {
              "type": "boolean",
              "title": "Skip This Stage",
              "description": "Set to true to skip this stage.",
              "default": false,
              "hints": ["advanced"]
            },
            "label": {
              "type": "string",
              "title": "Label",
              "description": "A unique label for this stage.",
              "hints": ["advanced"],
              "maxLength": 255
            },
            "condition": {
              "type": "string",
              "title": "Condition",
              "description": "Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.",
              "hints": ["code", "code/javascript", "advanced"]
            },
            "reservedFieldsMappingAllowed": {
              "type": "boolean",
              "title": "Allow System Fields Mapping?",
              "default": false,
              "hints": ["advanced"]
            },
            "retentionMappings": {
              "type": "array",
              "title": "Field Retention",
              "description": "Fields that should be kept or deleted",
              "hints": ["advanced"],
              "items": {
                "type": "object",
                "required": ["field"],
                "properties": {
                  "field": {
                    "type": "string",
                    "title": "Field",
                    "description": "The name of the field to operate on.",
                    "hints": ["advanced"]
                  },
                  "operation": {
                    "type": "string",
                    "title": "Operation",
                    "description": "The type of operation to perform: keep (default) or delete",
                    "enum": ["keep", "delete"],
                    "default": "keep",
                    "hints": ["advanced"]
                  }
                }
              }
            },
            "updateMappings": {
              "type": "array",
              "title": "Field Value Updates",
              "description": "Values that should be added to or set on a field. When a value is added, any values previously on the field will be retained. When a value is set, any values previously on the field will be overwritten.",
              "hints": ["advanced"],
              "items": {
                "type": "object",
                "required": ["field", "value"],
                "properties": {
                  "field": {
                    "type": "string",
                    "title": "Field",
                    "description": "The name of the field to operate on.",
                    "hints": ["advanced"]
                  },
                  "value": {
                    "type": "string",
                    "title": "Value",
                    "description": "The value to add to or set on the field.",
                    "hints": ["advanced"]
                  },
                  "operation": {
                    "type": "string",
                    "title": "Operation",
                    "description": "The type of operation to perform: add (default) or set.",
                    "enum": ["add", "set"],
                    "default": "add",
                    "hints": ["advanced"]
                  }
                }
              }
            },
            "translationMappings": {
              "type": "array",
              "title": "Field Translations",
              "description": "Fields that should be moved or copied to another field. When a field is moved, the values from the source field are moved over to the target field and the source field is removed. When a field is copied, the values from the source field are copied over to the target field and the source field is retained.",
              "hints": ["advanced"],
              "items": {
                "type": "object",
                "required": ["source", "target"],
                "properties": {
                  "source": {
                    "type": "string",
                    "title": "Source Field",
                    "description": "The name of the field to operate on.",
                    "hints": ["advanced"]
                  },
                  "target": {
                    "type": "string",
                    "title": "Target Field",
                    "description": "The name of the target field.",
                    "hints": ["advanced"]
                  },
                  "operation": {
                    "type": "string",
                    "title": "Operation",
                    "description": "The type of operation to perform: copy (default) or move.",
                    "enum": ["copy", "move"],
                    "default": "copy",
                    "hints": ["advanced"]
                  }
                }
              }
            },
            "unmappedRule": {
              "type": "object",
              "title": "Unmapped Fields",
              "description": "Fields not mapped by the above rules. By default, any remaining fields will be kept on the document.",
              "properties": {
                "keep": {
                  "type": "boolean",
                  "title": "Keep",
                  "description": "Keep all unmapped fields",
                  "default": true,
                  "hints": ["advanced"]
                },
                "delete": {
                  "type": "boolean",
                  "title": "Delete",
                  "description": "Delete all unmapped fields",
                  "default": false,
                  "hints": ["advanced"]
                },
                "fieldToMoveValuesTo": {
                  "type": "string",
                  "title": "Move",
                  "description": "Move all unmapped field values to this field",
                  "hints": ["advanced"]
                },
                "fieldToCopyValuesTo": {
                  "type": "string",
                  "title": "Copy",
                  "description": "Copy all unmapped field values to this field",
                  "hints": ["advanced"]
                },
                "valueToAddToUnmappedFields": {
                  "type": "string",
                  "title": "Add",
                  "description": "Add this value to all unmapped fields",
                  "hints": ["advanced"]
                },
                "valueToSetOnUnmappedFields": {
                  "type": "string",
                  "title": "Set",
                  "description": "Set this value on all unmapped fields",
                  "hints": ["advanced"]
                }
              }
            }
          },
          "category": "Field Transformation",
          "categoryPriority": 7,
          "hints": ["advanced"],
          "unsafe": false
        }
      },
      "propertyGroups": [{
        "label": "Azure Table",
        "properties": ["tables", "table_filter_statement"]
      }, {
        "label": "Azure Blob",
        "properties": ["storage_container", "max_bytes"]
      }, {
        "label": "Field Mapping",
        "properties": ["initial_mapping"]
      }, {
        "label": "Crawl Performance",
        "properties": ["max_threads", "max_connections"]
      }]
    }
  },
  "category": "Other",
  "categoryPriority": 1,
  "unsafe": false
};

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 <div>
      {description && <p>{formatDescription(description)}</p>}

      {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: [<><span className="text-stone-400 dark:text-stone-500">API property: </span>{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 <ParamField {...fieldProps}>
            {prop.description && <p>{formatDescription(prop.description)}</p>}

            {isComplexDefault && <div className="flex">
                <p>
                  <strong>Default:</strong>
                </p>
                <pre className="!my-0">
                  <code>
                    {JSON.stringify(rawDefault, null, 2)}
                  </code>
                </pre>
              </div>}

            {isArrayOfObjects && <div className="flex">
              <p>
                <strong>Object attributes:</strong>
              </p>
              <pre className="!my-0">
                <code>
                  {'{\n'}
                  {Object.entries(prop.items.properties).map(([iname, iprop]) => <>
                      {`  ${iname}`}
                      {prop.items?.required?.includes(iname) && <span style={{
      color: 'red'
    }}> required</span>}
                      {`: {\n    display name: ${sanitize(iprop.title || '')}\n    type: ${iprop.type}\n  }\n`}
                    </>)}
                  {'}'}
                </code>
              </pre>
              </div>}

            {isObject && <Expandable title="properties">
                <SchemaParamFields schema={{
      properties: prop.properties,
      required: prop.required
    }} />
              </Expandable>}
          </ParamField>;
  })}
    </div>;
};

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 <div className="lw-template-container">
      <Card title={title} icon={icon}>
        {isLoaded && <span dangerouslySetInnerHTML={{
    __html: `<lw-template id="a029c1a9-28be-427e-b0e1-5d918920246a"></lw-template
            >`
  }} />}
        <Link href={linkHref} className="agent-studio-link text-left text-gray-600 gap-2 dark:text-gray-400 text-sm font-medium flex flex-row items-center hover:text-primary dark:hover:text-primary-light group-hover:text-primary group-hover:dark:text-primary-light">Powered by Lucidworks Agent Studio</Link>
      </Card>
    </div>;
};

[localhost link]: http://localhost:3000/docs/fusion-connectors/connectors/v1/azure

[mintlify link]: https://doc.lucidworks.com/docs/fusion-connectors/connectors/v1/azure

[old doc.lw link]: https://doc.lucidworks.com/fusion-connectors/59

<Callout icon="plug" color="#A4C6F7" iconType="solid">
  **Compatible with Fusion version:** 4.0.0 through 5.12.0
</Callout>

<Tip>
  V1 deprecation and removal notice

  All V1 connectors are deprecated in Fusion 5.18.0 and later. This means they are no longer being actively developed and will be removed in Fusion 6. V1 connectors were also previously deprecated in Fusion 5.12.0 but remained available in all versions between 5.12.0 and 5.18.0, including the Fusion 5.9.x long-term support release line, to support customers on those versions.

  The replacement for this connector is in active development at this time and will be released at a future date.

  If you are using this connector, you must migrate to the replacement connector or a supported alternative before upgrading to Fusion 6. Migrate to the replacement connector as soon as possible to avoid any disruption to your workflows.
</Tip>

<Tip>
  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.
</Tip>

<LwTemplate />

## Configuration

<SchemaParamFields schema={schema} />
