# Unstructured

## Docs

- [About Unstructured](https://docs.unstructured.io/about.md)
- [Create destination connector](https://docs.unstructured.io/api-reference/api/destination/create-destination.md): Create a new destination connector using the provided configuration.
- [Create destination connection check](https://docs.unstructured.io/api-reference/api/destination/create-destination-connection-check.md): Test a destination connection by creating a connection check for the specified destination connector.
- [Delete destination connector](https://docs.unstructured.io/api-reference/api/destination/delete-destination.md): Delete a specific destination connector by its ID.
- [Destination endpoints](https://docs.unstructured.io/api-reference/api/destination/destination-apis.md)
- [Get destination connector](https://docs.unstructured.io/api-reference/api/destination/get-destination.md): Retrieve detailed information for a specific destination connector.
- [Get destination connection check](https://docs.unstructured.io/api-reference/api/destination/get-destination-connection-check.md): Retrieve the most recent connection check for the destination connector.
- [List destination connectors](https://docs.unstructured.io/api-reference/api/destination/list-destinations.md): Retrieve a list of available destination connectors.
- [Update destination connector](https://docs.unstructured.io/api-reference/api/destination/update-destination.md): Update the configuration of an existing destination connector.
- [Cancel job](https://docs.unstructured.io/api-reference/api/job/cancel-job.md): Cancel the specified job.
- [Create job](https://docs.unstructured.io/api-reference/api/job/create-job.md): Create a job that processes local files, using either a template or a custom directed acyclic graph (DAG).
- [Download job output](https://docs.unstructured.io/api-reference/api/job/download-job-output.md): Download the output of a job from a workflow.
- [Get job](https://docs.unstructured.io/api-reference/api/job/get-job.md): Retrieve basic information for a specific job.
- [Get job details](https://docs.unstructured.io/api-reference/api/job/get-job-details.md): Retrieve current processing details for a specific job.
- [Get job failed files](https://docs.unstructured.io/api-reference/api/job/get-job-failed-files.md): Retrieve the list of any failed files for a specific job, and why those files failed.
- [Job endpoints](https://docs.unstructured.io/api-reference/api/job/job-apis.md)
- [List jobs](https://docs.unstructured.io/api-reference/api/job/list-jobs.md): Retrieve a list of jobs with optional filtering.
- [Create notification channel](https://docs.unstructured.io/api-reference/api/notification/create-notification-channel.md): Create a new delivery channel for receiving platform event notifications.
- [Delete notification channel](https://docs.unstructured.io/api-reference/api/notification/delete-notification-channel.md): Delete workspace-scoped notification channel.
- [Get notification](https://docs.unstructured.io/api-reference/api/notification/get-notification.md): Get a single notification event by ID.
- [Get notification channel](https://docs.unstructured.io/api-reference/api/notification/get-notification-channel.md): Get workspace-scoped notification channel by ID.
- [Get notifications unread count](https://docs.unstructured.io/api-reference/api/notification/get-notifications-unread-count.md): Get count of unread notification events for the current user.
- [List notification channels](https://docs.unstructured.io/api-reference/api/notification/list-notification-channels.md): List workspace-scoped notification channels.
- [List notifications](https://docs.unstructured.io/api-reference/api/notification/list-notifications.md): List notification events for the authenticated user, ordered by creation date with cursor-based pagination.
- [Mark notifications read](https://docs.unstructured.io/api-reference/api/notification/mark-notifications-read.md): Mark notification events as read for the current user.
- [Notification endpoints](https://docs.unstructured.io/api-reference/api/notification/notification-apis.md): Read and manage workspace-level notifications and the delivery channels that route them. Configure email or webhook targets, verify them, and track unread activity across your workflows.
- [Update notification channel](https://docs.unstructured.io/api-reference/api/notification/update-notification-channel.md): Update workspace-scoped notification channel. Only provided fields are updated.
- [Verify notification channel](https://docs.unstructured.io/api-reference/api/notification/verify-notification-channel.md): Verify a notification channel using a verification code.
- [Create source connector](https://docs.unstructured.io/api-reference/api/source/create-source.md): Create a new source connector using the provided configuration.
- [Create source connection check](https://docs.unstructured.io/api-reference/api/source/create-source-connection-check.md): Test a source connection by creating a connection check for the specified source connector.
- [Delete source connector](https://docs.unstructured.io/api-reference/api/source/delete-source.md): Delete a specific source connector identified by its ID.
- [Get source connector](https://docs.unstructured.io/api-reference/api/source/get-source.md): Retrieve detailed information for a specific source connector.
- [Get source connection check](https://docs.unstructured.io/api-reference/api/source/get-source-connection-check.md): Retrieve the most recent connection check for the source connector.
- [List source connectors](https://docs.unstructured.io/api-reference/api/source/list-sources.md): Retrieve a list of available source connectors.
- [Source endpoints](https://docs.unstructured.io/api-reference/api/source/source-apis.md)
- [Update source connector](https://docs.unstructured.io/api-reference/api/source/update-source.md): Update the configuration of an existing source connector.
- [Get template](https://docs.unstructured.io/api-reference/api/template/get-template.md): Retrieve detailed information and DAG for a specific template.
- [List templates](https://docs.unstructured.io/api-reference/api/template/list-templates.md): Retrieve a list of available templates with their metadata.
- [Template endpoints](https://docs.unstructured.io/api-reference/api/template/template-apis.md)
- [Create workflow](https://docs.unstructured.io/api-reference/api/workflow/create-workflow.md): Create a new workflow, either custom or auto, and configure its settings.
- [Create workflow notification channel](https://docs.unstructured.io/api-reference/api/workflow/create-workflow-notification-channel.md): Create a new delivery channel for receiving platform event notifications scoped to the specified workflow.
- [Delete workflow](https://docs.unstructured.io/api-reference/api/workflow/delete-workflow.md): Delete a workflow by its ID.
- [Delete workflow notification channel](https://docs.unstructured.io/api-reference/api/workflow/delete-workflow-notification-channel.md): Delete workflow-scoped notification channel.
- [Get workflow](https://docs.unstructured.io/api-reference/api/workflow/get-workflow.md): Retrieve detailed information for a specific workflow by its ID.
- [Get workflow notification channel](https://docs.unstructured.io/api-reference/api/workflow/get-workflow-notification-channel.md): Get workflow-scoped notification channel by ID.
- [List workflow notification channels](https://docs.unstructured.io/api-reference/api/workflow/list-workflow-notification-channels.md): List workflow-scoped notification channels.
- [List workflows](https://docs.unstructured.io/api-reference/api/workflow/list-workflows.md): Retrieve a list of workflows, optionally filtered by source, destination, state, name, date range, and supports pagination and sorting.
- [Run workflow](https://docs.unstructured.io/api-reference/api/workflow/run-workflow.md): Run a workflow manually, by triggering a new job if none is currently active.
- [Update workflow](https://docs.unstructured.io/api-reference/api/workflow/update-workflow.md): Update an existing workflow's name, connectors, schedule, or workflow type.
- [Update workflow notification channel](https://docs.unstructured.io/api-reference/api/workflow/update-workflow-notification-channel.md): Update workflow-scoped notification channel. Only provided fields are updated.
- [Verify workflow notification channel](https://docs.unstructured.io/api-reference/api/workflow/verify-workflow-notification-channel.md): Verify a workflow-scoped notification channel using a verification code.
- [Workflow endpoints](https://docs.unstructured.io/api-reference/api/workflow/workflow-apis.md)
- [Email Notifications](https://docs.unstructured.io/api-reference/email.md): Learn how to create and verify email notification channels to receive automated emails for Unstructured workflow job events.
- [Unstructured API on AWS](https://docs.unstructured.io/api-reference/legacy-api/aws.md): Follow these steps to deploy the Unstructured API service into your AWS account.
- [Unstructured API on Azure](https://docs.unstructured.io/api-reference/legacy-api/azure.md)
- [Overview](https://docs.unstructured.io/api-reference/legacy-api/overview.md)
- [Partition Endpoint parameters](https://docs.unstructured.io/api-reference/legacy-api/partition/api-parameters.md)
- [Endpoint errors](https://docs.unstructured.io/api-reference/legacy-api/partition/api-validation-errors.md)
- [Chunking strategies](https://docs.unstructured.io/api-reference/legacy-api/partition/chunking.md)
- [Document elements and metadata](https://docs.unstructured.io/api-reference/legacy-api/partition/document-elements.md)
- [Examples](https://docs.unstructured.io/api-reference/legacy-api/partition/examples.md): This page provides some examples of accessing Unstructured Partition Endpoint via different methods.
- [Extract images and tables from documents](https://docs.unstructured.io/api-reference/legacy-api/partition/extract-image-block-types.md)
- [Generate a JSON schema for a file](https://docs.unstructured.io/api-reference/legacy-api/partition/generate-schema.md)
- [Get chunked elements](https://docs.unstructured.io/api-reference/legacy-api/partition/get-chunked-elements.md)
- [Get element contents](https://docs.unstructured.io/api-reference/legacy-api/partition/get-elements.md)
- [Overview](https://docs.unstructured.io/api-reference/legacy-api/partition/overview.md)
- [Partitioning strategies](https://docs.unstructured.io/api-reference/legacy-api/partition/partitioning.md)
- [Process an individual file by making a direct POST request](https://docs.unstructured.io/api-reference/legacy-api/partition/post-requests.md)
- [Unstructured API Quickstart](https://docs.unstructured.io/api-reference/legacy-api/partition/quickstart.md)
- [JavaScript/TypeScript SDK](https://docs.unstructured.io/api-reference/legacy-api/partition/sdk-jsts.md)
- [Python SDK](https://docs.unstructured.io/api-reference/legacy-api/partition/sdk-python.md)
- [Speed up processing of large files and batches](https://docs.unstructured.io/api-reference/legacy-api/partition/speed-up-large-files-batches.md)
- [Extract tables as HTML](https://docs.unstructured.io/api-reference/legacy-api/partition/text-as-html.md)
- [Transform a JSON file into a different schema](https://docs.unstructured.io/api-reference/legacy-api/partition/transform-schemas.md)
- [Overview](https://docs.unstructured.io/api-reference/overview.md)
- [Embed quickstart](https://docs.unstructured.io/api-reference/quickstart/embed.md): Create a job to partition, chunk, and embed local files into AI-ready JSON with vector embeddings for semantic search.
- [Enrich quickstart](https://docs.unstructured.io/api-reference/quickstart/enrich.md): Create a job to partition and enrich local files into AI-ready JSON with image descriptions, table HTML, named entities, and generative OCR output.
- [Extract quickstart](https://docs.unstructured.io/api-reference/quickstart/extract.md): Create a job to partition local files and extract specified data as JSON object data records using the Unstructured API.
- [Unstructured API quickstart](https://docs.unstructured.io/api-reference/quickstart/overview.md): Use curl or the Unstructured Python SDK to turn local files into AI-ready JSON.
- [Transform quickstart](https://docs.unstructured.io/api-reference/quickstart/transform.md): Create a job that uses Auto partitioning to transform local files into standard AI-ready JSON.
- [Supported file types](https://docs.unstructured.io/api-reference/supported-file-types.md)
- [Troubleshooting Unstructured API keys and URLs](https://docs.unstructured.io/api-reference/troubleshooting/api-key-url.md)
- [Webhooks](https://docs.unstructured.io/api-reference/webhooks.md)
- [Astra DB](https://docs.unstructured.io/api-reference/workflow/destinations/astradb.md)
- [Azure AI Search](https://docs.unstructured.io/api-reference/workflow/destinations/azure-ai-search.md)
- [Azure Blob Storage](https://docs.unstructured.io/api-reference/workflow/destinations/azure-blob-storage.md)
- [Couchbase](https://docs.unstructured.io/api-reference/workflow/destinations/couchbase.md)
- [Delta Tables in Databricks](https://docs.unstructured.io/api-reference/workflow/destinations/databricks-delta-table.md): Send processed data from Unstructured to a Delta Table in Databricks.
- [Databricks Volumes](https://docs.unstructured.io/api-reference/workflow/destinations/databricks-volumes.md)
- [Delta Tables in Amazon S3](https://docs.unstructured.io/api-reference/workflow/destinations/delta-table.md)
- [Elasticsearch](https://docs.unstructured.io/api-reference/workflow/destinations/elasticsearch.md)
- [IBM FileNet](https://docs.unstructured.io/api-reference/workflow/destinations/filenet.md): Connect Unstructured to IBM FileNet as a destination to send processed document data into your FileNet content repository.
- [Google Cloud Storage](https://docs.unstructured.io/api-reference/workflow/destinations/google-cloud.md)
- [IBM watsonx.data](https://docs.unstructured.io/api-reference/workflow/destinations/ibm-watsonxdata.md)
- [Kafka](https://docs.unstructured.io/api-reference/workflow/destinations/kafka.md)
- [Local](https://docs.unstructured.io/api-reference/workflow/destinations/local.md)
- [Milvus](https://docs.unstructured.io/api-reference/workflow/destinations/milvus.md): Send processed data from Unstructured to Milvus.
- [MongoDB](https://docs.unstructured.io/api-reference/workflow/destinations/mongodb.md)
- [MotherDuck](https://docs.unstructured.io/api-reference/workflow/destinations/motherduck.md)
- [Neo4j](https://docs.unstructured.io/api-reference/workflow/destinations/neo4j.md)
- [OneDrive](https://docs.unstructured.io/api-reference/workflow/destinations/onedrive.md)
- [OpenSearch](https://docs.unstructured.io/api-reference/workflow/destinations/opensearch.md)
- [Overview](https://docs.unstructured.io/api-reference/workflow/destinations/overview.md)
- [Pinecone](https://docs.unstructured.io/api-reference/workflow/destinations/pinecone.md)
- [PostgreSQL](https://docs.unstructured.io/api-reference/workflow/destinations/postgresql.md)
- [Qdrant](https://docs.unstructured.io/api-reference/workflow/destinations/qdrant.md)
- [Redis](https://docs.unstructured.io/api-reference/workflow/destinations/redis.md)
- [S3](https://docs.unstructured.io/api-reference/workflow/destinations/s3.md)
- [Snowflake](https://docs.unstructured.io/api-reference/workflow/destinations/snowflake.md)
- [Teradata Database](https://docs.unstructured.io/api-reference/workflow/destinations/teradata-sql.md)
- [Teradata Vector Store](https://docs.unstructured.io/api-reference/workflow/destinations/teradata-vector-v2.md): Send processed data from Unstructured to Teradata Vector Store.
- [VAST](https://docs.unstructured.io/api-reference/workflow/destinations/vast.md): Send processed data from Unstructured to [VAST](https://www.vastdata.com/).
- [Weaviate](https://docs.unstructured.io/api-reference/workflow/destinations/weaviate.md): Send processed data from Unstructured to Weaviate.
- [Errors](https://docs.unstructured.io/api-reference/workflow/errors.md)
- [Jobs](https://docs.unstructured.io/api-reference/workflow/jobs.md): Manage Unstructured workflow jobs with the Python SDK or REST API. List jobs, monitor processing status, inspect failed files, and cancel running jobs.
- [Migration](https://docs.unstructured.io/api-reference/workflow/migration.md)
- [Available models](https://docs.unstructured.io/api-reference/workflow/models.md): The following models are available for use in Unstructured workflow nodes, organized by model functionality and provider.
- [Contextual chunking node](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/chunker-chunk-by-contextual.md): Add a Contextual Chunker node after your chunker to prepend LLM-generated context to each chunk, improving retrieval quality without changing chunk count or IDs.
- [Chunk by Table Merging strategy](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/chunker-chunk-by-table-merging.md): Use the Chunk by Table Merging strategy to detect and merge split tables spanning adjacent pages into a single coherent element with LLM assistance.
- [Embedder node](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/embedder.md): Configure an Embedder node to convert chunked document elements into vector embeddings using a supported provider and model, enabling similarity search in vector stores.
- [Enhancement nodes](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/enhancement.md): Configure Enhancement nodes to apply AI-powered transformations to partitioned document elements, including enrichments, structured data extraction, and vector embeddings.
- [LLM extraction](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/extract-llm.md): The LLM method uses a language model to extract structured data fields from partitioned documents based on a JSON schema or plain-language extraction guidance.
- [Regex extraction](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/extract-regex.md): The Regex method extracts structured data fields from partitioned documents using named regular-expression patterns, without requiring a language model.
- [Generative OCR task](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/prompter-generative-ocr.md): The Generative OCR task uses a vision language model (VLM) to improve the fidelity of text blocks that Unstructured initially processed during partitioning.
- [Image Description task](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/prompter-image-description.md): The Image Description task uses agentic AI or a vision language model (VLM) to generate text-based summaries of detected images in partitioned documents.
- [Named Entity Recognition (NER) task](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/prompter-named-entity-recognition-ner.md): The Named Entity Recognition (NER) task identifies entities and their types — such as people, organizations, and locations — and the relationships between them.
- [Table Description task](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/prompter-table-description.md): The Table Description task uses a vision language model to generate text-based summaries of detected tables in partitioned documents.
- [Table to HTML task](https://docs.unstructured.io/api-reference/workflow/nodes/enhancement/prompter-table-to-html.md): The Table to HTML task converts detected tables into HTML markup using agentic AI or a vision language model  (VLM), improving accuracy and downstream rendering.
- [Custom workflow DAG nodes](https://docs.unstructured.io/api-reference/workflow/nodes/overview.md)
- [Chunk by Character strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/chunker-chunk-by-character.md): The Chunk by Character strategy combines sequential elements to fill each chunk within hard and soft character limits, without using section or page boundaries.
- [Chunk by Page strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/chunker-chunk-by-page.md): The Chunk by Page strategy preserves page boundaries, ensuring no chunk contains content from more than one page.
- [Chunk by Similarity strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/chunker-chunk-by-similarity.md): The Chunk by Similarity strategy uses an embedding model to identify topically similar consecutive elements and combines them into chunks.
- [Chunk by Title strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/chunker-chunk-by-title.md): The Chunk by Title strategy preserves section boundaries by starting a new chunk whenever a Title element is encountered.
- [Auto partition strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/partitioner-auto.md): The Auto strategy dynamically routes each page to the Fast, High Res, or VLM partitioning strategy at runtime, optimizing for the highest quality at the lowest cost.
- [Fast partition strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/partitioner-fast.md): The Fast strategy uses rule-based text extraction optimized for text-only documents, delivering the fastest processing at the lowest cost.
- [High Res partition strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/partitioner-high-res.md): The High Res strategy uses advanced image-to-text processing for all supported file types and supports generation of bounding box coordinates for document elements.
- [VLM partition strategy](https://docs.unstructured.io/api-reference/workflow/nodes/transform/partitioner-vlm.md): The VLM strategy uses a vision language model to deliver the highest-quality partitioning for image-heavy file types including PDFs, images, and scanned documents.
- [Transform nodes](https://docs.unstructured.io/api-reference/workflow/nodes/transform/transform.md): Configure Transform nodes to extract content from raw files and split it into optimally sized elements, using a Partitioner to detect document structure and a Chunker to prepare elements for downstream processing.
- [Overview](https://docs.unstructured.io/api-reference/workflow/overview.md)
- [Retries](https://docs.unstructured.io/api-reference/workflow/retries.md)
- [Azure Blob Storage](https://docs.unstructured.io/api-reference/workflow/sources/azure-blob-storage.md)
- [Box](https://docs.unstructured.io/api-reference/workflow/sources/box.md): Ingest your files into Unstructured from Box.
- [Confluence](https://docs.unstructured.io/api-reference/workflow/sources/confluence.md)
- [Couchbase](https://docs.unstructured.io/api-reference/workflow/sources/couchbase.md)
- [Databricks Volumes](https://docs.unstructured.io/api-reference/workflow/sources/databricks-volumes.md)
- [Dropbox](https://docs.unstructured.io/api-reference/workflow/sources/dropbox.md)
- [Elasticsearch](https://docs.unstructured.io/api-reference/workflow/sources/elasticsearch.md)
- [IBM FileNet](https://docs.unstructured.io/api-reference/workflow/sources/filenet.md): Connect Unstructured to IBM FileNet as a source to ingest documents and content from your FileNet content repository into Unstructured.
- [Google Cloud Storage](https://docs.unstructured.io/api-reference/workflow/sources/google-cloud.md)
- [Google Drive](https://docs.unstructured.io/api-reference/workflow/sources/google-drive.md)
- [Jira](https://docs.unstructured.io/api-reference/workflow/sources/jira.md)
- [Kafka](https://docs.unstructured.io/api-reference/workflow/sources/kafka.md)
- [Local](https://docs.unstructured.io/api-reference/workflow/sources/local.md)
- [MongoDB](https://docs.unstructured.io/api-reference/workflow/sources/mongodb.md)
- [Microsoft OneDrive](https://docs.unstructured.io/api-reference/workflow/sources/onedrive.md): Learn how to Ingest your files into Unstructured from Microsoft OneDrive.
- [OpenSearch](https://docs.unstructured.io/api-reference/workflow/sources/opensearch.md)
- [Outlook](https://docs.unstructured.io/api-reference/workflow/sources/outlook.md)
- [Overview](https://docs.unstructured.io/api-reference/workflow/sources/overview.md)
- [PostgreSQL](https://docs.unstructured.io/api-reference/workflow/sources/postgresql.md)
- [S3](https://docs.unstructured.io/api-reference/workflow/sources/s3.md)
- [Salesforce](https://docs.unstructured.io/api-reference/workflow/sources/salesforce.md)
- [Microsoft SharePoint](https://docs.unstructured.io/api-reference/workflow/sources/sharepoint.md): Ingest your files into Unstructured from SharePoint.
- [Slack](https://docs.unstructured.io/api-reference/workflow/sources/slack.md)
- [Snowflake](https://docs.unstructured.io/api-reference/workflow/sources/snowflake.md)
- [Teradata Database](https://docs.unstructured.io/api-reference/workflow/sources/teradata-sql.md)
- [VAST](https://docs.unstructured.io/api-reference/workflow/sources/vast.md): Ingest your files into Unstructured from [VAST](https://www.vastdata.com/).
- [Zendesk](https://docs.unstructured.io/api-reference/workflow/sources/zendesk.md)
- [Workflows](https://docs.unstructured.io/api-reference/workflow/workflows.md): Build and manage Unstructured workflows with the Python SDK or REST API. Create, update, run, and delete workflows that process and transform documents from source to destination.
- [AI providers](https://docs.unstructured.io/business/ai-providers.md)
- [Connecting to customer-managed services on AWS](https://docs.unstructured.io/business/aws/aws-privatelink/connect-to-customer-managed-services.md)
- [Connecting to AWS-managed services](https://docs.unstructured.io/business/aws/aws-privatelink/connect-to-services.md)
- [Connector support for AWS PrivateLink](https://docs.unstructured.io/business/aws/aws-privatelink/connector-support.md)
- [Configure DNS for AWS PrivateLink](https://docs.unstructured.io/business/aws/aws-privatelink/dns-configuration.md)
- [Onboarding your dedicated instance + AWS PrivateLink](https://docs.unstructured.io/business/aws/aws-privatelink/onboarding-di-pl.md)
- [Enterprise Connect for AWS](https://docs.unstructured.io/business/aws/enterprise-connect.md): Enterprise Connect lets Unstructured access your AWS resources by assuming a customer-configured IAM role with temporary, scoped credentials.
- [Enterprise Connect for Amazon Bedrock](https://docs.unstructured.io/business/aws/enterprise-connect-bedrock.md): Set up an IAM role and trust policy in AWS, then configure Amazon Bedrock in the Unstructured AI Providers UI to enable Enterprise Connect authentication.
- [Enterprise Connect for AWS connectors](https://docs.unstructured.io/business/aws/enterprise-connect-connectors.md): Set up Enterprise Connect authentication for AWS connectors by creating an IAM role and trust policy, then configuring the connector.
- [Onboarding in-VPC on your AWS platform](https://docs.unstructured.io/business/aws/onboarding-in-vpc.md)
- [Unstructured Business on Amazon Web Services (AWS)](https://docs.unstructured.io/business/aws/overview.md)
- [Connecting to customer-managed services on Azure](https://docs.unstructured.io/business/azure/azure-privatelink/connect-to-customer-managed-services.md)
- [Connecting to Azure-managed services](https://docs.unstructured.io/business/azure/azure-privatelink/connect-to-services.md)
- [Connector support for Azure Private Link](https://docs.unstructured.io/business/azure/azure-privatelink/connector-support.md)
- [Configure DNS for Azure Private Link](https://docs.unstructured.io/business/azure/azure-privatelink/dns-privatelink.md)
- [Onboarding Dedicated Instance + Azure Private Link](https://docs.unstructured.io/business/azure/azure-privatelink/onboarding-di-pl.md)
- [Enterprise Connect for Azure](https://docs.unstructured.io/business/azure/enterprise-connect.md): Enterprise Connect lets Unstructured connectors access Azure resources by authenticating as a customer-configured App Registration using short-lived access tokens.
- [Onboarding in-VPC on your Microsoft Azure platform](https://docs.unstructured.io/business/azure/onboarding-in-vpc.md)
- [Unstructured Business on Microsoft Azure (Azure)](https://docs.unstructured.io/business/azure/overview.md)
- [Concepts and architecture](https://docs.unstructured.io/business/dedicated-instances/architecture.md)
- [Before you begin](https://docs.unstructured.io/business/dedicated-instances/before-you-begin.md)
- [Dedicated instance overview](https://docs.unstructured.io/business/dedicated-instances/overview.md)
- [Requirements and limitations](https://docs.unstructured.io/business/dedicated-instances/requirements.md)
- [Security FAQ](https://docs.unstructured.io/business/dedicated-instances/security/security-faq.md)
- [Security model](https://docs.unstructured.io/business/dedicated-instances/security/security-model.md)
- [Shared responsibility model](https://docs.unstructured.io/business/dedicated-instances/security/shared-responsibility-model.md)
- [Onboarding in-VPC on your Google Cloud Platform (GCP)](https://docs.unstructured.io/business/gcp/onboarding-in-vpc.md)
- [Unstructured Business in-VPC on Google Cloud Platform (GCP) - overview](https://docs.unstructured.io/business/gcp/overview.md)
- [Configure an identity provider](https://docs.unstructured.io/business/idp/configuration.md)
- [IdP group mappings](https://docs.unstructured.io/business/idp/group-mappings.md)
- [IdP overview](https://docs.unstructured.io/business/idp/overview.md)
- [Unstructured Business](https://docs.unstructured.io/business/overview.md)
- [Security and compliance overview](https://docs.unstructured.io/business/security-compliance/overview.md)
- [Chunking](https://docs.unstructured.io/concepts/chunking.md)
- [Document elements and metadata](https://docs.unstructured.io/concepts/document-elements.md)
- [Embedding](https://docs.unstructured.io/concepts/embedding.md)
- [Generative OCR optimization](https://docs.unstructured.io/concepts/enriching/generative-ocr.md)
- [Image descriptions](https://docs.unstructured.io/concepts/enriching/image-descriptions.md)
- [Named entity recognition (NER)](https://docs.unstructured.io/concepts/enriching/ner.md)
- [Overview](https://docs.unstructured.io/concepts/enriching/overview.md)
- [Table descriptions](https://docs.unstructured.io/concepts/enriching/table-descriptions.md)
- [Tables to HTML](https://docs.unstructured.io/concepts/enriching/table-to-html.md)
- [More examples](https://docs.unstructured.io/concepts/examples.md)
- [Unstructured concepts overview](https://docs.unstructured.io/concepts/overview.md): Learn how Unstructured processes documents: partitioning, chunking, enriching, embedding, and structured data extraction.
- [Partitioning](https://docs.unstructured.io/concepts/partitioning.md)
- [Additional examples](https://docs.unstructured.io/concepts/structured-data-extractor/additional-examples.md)
- [Choose an extraction method: LLM or Regex](https://docs.unstructured.io/concepts/structured-data-extractor/choose-extraction-method.md)
- [Structured data extraction](https://docs.unstructured.io/concepts/structured-data-extractor/data-extractor.md)
- [Structured Extraction with LLM](https://docs.unstructured.io/concepts/structured-data-extractor/llm-options.md)
- [Structured Extraction with Regex](https://docs.unstructured.io/concepts/structured-data-extractor/regex-options.md)
- [Saving extracted data](https://docs.unstructured.io/concepts/structured-data-extractor/saving-extracted-data.md)
- [Using the structured data extractor](https://docs.unstructured.io/concepts/structured-data-extractor/using-the-structured-data-extractor.md)
- [Query processed PDF with HuggingChat](https://docs.unstructured.io/examplecode/codesamples/api/huggingchat.md)
- [Table extraction from PDF](https://docs.unstructured.io/examplecode/codesamples/apioss/table-extraction-from-pdf.md): This section describes two methods for extracting tables from PDF files.
- [Multi-file API processing](https://docs.unstructured.io/examplecode/codesamples/oss/multi-files-api-processing.md)
- [Delta Table source connector](https://docs.unstructured.io/examplecode/codesamples/oss/table-source-connector.md)
- [Vector database ingestion](https://docs.unstructured.io/examplecode/codesamples/oss/vector-database.md)
- [Notebooks](https://docs.unstructured.io/examplecode/notebooks.md): Notebooks contain complete working sample code for end-to-end solutions.
- [Azure Blob Storage event triggers](https://docs.unstructured.io/examplecode/tools/azure-storage-events.md)
- [Claude Desktop](https://docs.unstructured.io/examplecode/tools/claude.md)
- [CrewAI](https://docs.unstructured.io/examplecode/tools/crewai.md)
- [Databricks Volumes event triggers](https://docs.unstructured.io/examplecode/tools/databricks-volumes-events.md)
- [Firecrawl](https://docs.unstructured.io/examplecode/tools/firecrawl.md)
- [Google Cloud Storage event triggers](https://docs.unstructured.io/examplecode/tools/gcs-events.md)
- [Google Drive event triggers](https://docs.unstructured.io/examplecode/tools/google-drive-events.md)
- [IBM watsonx Orchestrate](https://docs.unstructured.io/examplecode/tools/ibm-orchestrate.md)
- [Query JSON with jq](https://docs.unstructured.io/examplecode/tools/jq.md)
- [Working with Unstructured JSON output](https://docs.unstructured.io/examplecode/tools/json-tools.md)
- [Langflow](https://docs.unstructured.io/examplecode/tools/langflow.md)
- [Model Context Protocol (MCP) Hands-On Walkthrough for the Unstructured Pipeline API](https://docs.unstructured.io/examplecode/tools/mcp.md)
- [Model Context Protocol (MCP) Hands-On Walkthrough for the Unstructured Partition Endpoint](https://docs.unstructured.io/examplecode/tools/mcp-partition.md)
- [Chatbot with Neo4j](https://docs.unstructured.io/examplecode/tools/neo4j-chatbot.md)
- [OneDrive event triggers](https://docs.unstructured.io/examplecode/tools/onedrive-events.md)
- [PII detection](https://docs.unstructured.io/examplecode/tools/pii.md)
- [Amazon S3 event triggers](https://docs.unstructured.io/examplecode/tools/s3-events.md)
- [Amazon S3 Vectors](https://docs.unstructured.io/examplecode/tools/s3-vectors.md)
- [SharePoint event triggers](https://docs.unstructured.io/examplecode/tools/sharepoint-events.md)
- [Streamlit in Snowflake](https://docs.unstructured.io/examplecode/tools/snowflake-streamlit.md)
- [VectorShift](https://docs.unstructured.io/examplecode/tools/vectorshift.md)
- [Frequently asked questions](https://docs.unstructured.io/faq/faq.md)
- [Unstructured Foundation installation for Claude Code](https://docs.unstructured.io/foundation/install/claude-code.md): Learn how to install Unstructured Foundation into Claude Code. You can then use Foundation to give Claude Code persistent access to your organization's knowledge without file uploads.
- [Unstructured Foundation installation for Claude Desktop](https://docs.unstructured.io/foundation/install/claude-desktop.md): Learn how to install Unstructured Foundation into Claude Desktop. You can then use Foundation to give Claude Desktop persistent access to your organization's knowledge without file uploads.
- [Unstructured Foundation installation for the Codex CLI](https://docs.unstructured.io/foundation/install/codex-cli.md): Learn how to install Unstructured Foundation into the Codex CLI. You can then use Foundation to give the Codex CLI persistent access to your organization's knowledge without file uploads.
- [Unstructured Foundation installation for Codex Desktop](https://docs.unstructured.io/foundation/install/codex-desktop.md): Learn how to install Unstructured Foundation into Codex Desktop. You can then use Foundation to give Codex Desktop persistent access to your organization's knowledge without file uploads.
- [Unstructured Foundation installation for the Cursor CLI](https://docs.unstructured.io/foundation/install/cursor-cli.md): Learn how to install Unstructured Foundation into the Cursor CLI. You can then use Foundation to give the Cursor CLI persistent access to your organization's knowledge without file uploads.
- [Unstructured Foundation installation for the Cursor IDE](https://docs.unstructured.io/foundation/install/cursor-ide.md): Learn how to install Unstructured Foundation into the Cursor IDE. You can then use Foundation to give the Cursor IDE persistent access to your organization's knowledge without file uploads.
- [Get started with Unstructured Foundation](https://docs.unstructured.io/foundation/install/overview.md): Learn how to install Unstructured Foundation into various AI tools. You can then use Foundation to give your team and its AI agents persistent access to your organization's knowledge without file uploads.
- [The Unstructured Foundation MCP server](https://docs.unstructured.io/foundation/mcp-server.md): Learn what the Foundation MCP server is; how it uses your AI tools to link Unstructured to your files' sources; and how to set it up and update your configuration.
- [Unstructured Foundation overview](https://docs.unstructured.io/foundation/overview.md): Learn how Unstructured Foundation gives every AI tool your team uses persistent access to your organization's knowledge without file uploads.
- [Get started with Unstructured Foundation](https://docs.unstructured.io/foundation/quickstart.md): Install Unstructured Foundation, connect to your files' sources, and start querying your files from any MCP-compatible AI tool.
- [Unstructured Foundation sources](https://docs.unstructured.io/foundation/sources.md): Learn what Foundation sources are; which sources are available; and how to add, manage, and remove sources from Foundation.
- [Unstructured Foundation storage](https://docs.unstructured.io/foundation/storage.md): Learn what Foundation stores about your files, where that data lives, and how to view or delete stored data.
- [Supported file types](https://docs.unstructured.io/foundation/supported-file-types.md)
- [Troubleshoot Unstructured Foundation](https://docs.unstructured.io/foundation/troubleshooting.md): Solutions for common issues with Unstructured Foundation, including indexing delays, connector authorization errors, and missing query results.
- [Chunking](https://docs.unstructured.io/open-source/best-practices/chunking.md)
- [Embedding](https://docs.unstructured.io/open-source/best-practices/embedding.md)
- [Document elements and metadata](https://docs.unstructured.io/open-source/concepts/document-elements.md)
- [Models](https://docs.unstructured.io/open-source/concepts/models.md): Depending on your need, `Unstructured` provides OCR-based and Transformer-based models to detect elements in the documents. The models are useful to detect the complex layout in the documents and predict the element types.
- [Partitioning strategies](https://docs.unstructured.io/open-source/concepts/partitioning-strategies.md)
- [Chunking](https://docs.unstructured.io/open-source/core-functionality/chunking.md): Chunking functions in `unstructured` use metadata and document elements detected with `partition` functions to post-process elements into more useful "chunks" for uses cases such as retrieval-augmented generation (RAG).
- [Cleaning](https://docs.unstructured.io/open-source/core-functionality/cleaning.md): As part of data preparation for an NLP model, it’s common to need to clean up your data prior to passing it into the model. If there’s unwanted content in your output, for example, it could impact the quality of your NLP model. To help with this, the `unstructured` library includes cleaning function…
- [Embedding](https://docs.unstructured.io/open-source/core-functionality/embedding.md)
- [Extracting](https://docs.unstructured.io/open-source/core-functionality/extracting.md)
- [Core Functionality](https://docs.unstructured.io/open-source/core-functionality/overview.md): The `unstructured` library includes functions to partition, chunk, clean, and stage raw source documents. These functions serve as the primary public interfaces within the library.
- [Partitioning](https://docs.unstructured.io/open-source/core-functionality/partitioning.md): Partitioning functions in `unstructured` allow users to extract structured content from a raw unstructured document. These functions break a document down into elements such as `Title`, `NarrativeText`, and `ListItem`, enabling users to decide what content they’d like to keep for their particular ap…
- [Staging](https://docs.unstructured.io/open-source/core-functionality/staging.md)
- [Set embedding behavior](https://docs.unstructured.io/open-source/how-to/embedding.md)
- [Examples](https://docs.unstructured.io/open-source/how-to/examples.md): This page provides some examples of accessing Unstructured by using the Unstructured Ingest CLI and the Unstructured Ingest Python library.
- [Extract images and tables from documents](https://docs.unstructured.io/open-source/how-to/extract-image-block-types.md)
- [Process a subset of files](https://docs.unstructured.io/open-source/how-to/filter-files.md)
- [Get chunked elements](https://docs.unstructured.io/open-source/how-to/get-chunked-elements.md)
- [Get element contents](https://docs.unstructured.io/open-source/how-to/get-elements.md)
- [Set the OCR agent](https://docs.unstructured.io/open-source/how-to/set-ocr-agent.md)
- [Speed up processing of large files and batches](https://docs.unstructured.io/open-source/how-to/speed-up-large-files-batches.md)
- [Extract tables as HTML](https://docs.unstructured.io/open-source/how-to/text-as-html.md)
- [Astra DB](https://docs.unstructured.io/open-source/ingestion/destination-connectors/astradb.md)
- [Azure](https://docs.unstructured.io/open-source/ingestion/destination-connectors/azure.md)
- [Azure AI Search](https://docs.unstructured.io/open-source/ingestion/destination-connectors/azure-ai-search.md)
- [Box](https://docs.unstructured.io/open-source/ingestion/destination-connectors/box.md)
- [Chroma](https://docs.unstructured.io/open-source/ingestion/destination-connectors/chroma.md)
- [Couchbase](https://docs.unstructured.io/open-source/ingestion/destination-connectors/couchbase.md)
- [Delta Tables in Databricks](https://docs.unstructured.io/open-source/ingestion/destination-connectors/databricks-delta-table.md)
- [Databricks Volumes](https://docs.unstructured.io/open-source/ingestion/destination-connectors/databricks-volumes.md)
- [Delta Tables in Amazon S3](https://docs.unstructured.io/open-source/ingestion/destination-connectors/delta-table.md)
- [Dropbox](https://docs.unstructured.io/open-source/ingestion/destination-connectors/dropbox.md)
- [DuckDB](https://docs.unstructured.io/open-source/ingestion/destination-connectors/duckdb.md)
- [Elasticsearch](https://docs.unstructured.io/open-source/ingestion/destination-connectors/elasticsearch.md)
- [Google Cloud Storage](https://docs.unstructured.io/open-source/ingestion/destination-connectors/google-cloud-service.md)
- [IBM watsonx.data](https://docs.unstructured.io/open-source/ingestion/destination-connectors/ibm-watsonxdata.md)
- [Kafka](https://docs.unstructured.io/open-source/ingestion/destination-connectors/kafka.md)
- [KDB.AI](https://docs.unstructured.io/open-source/ingestion/destination-connectors/kdbai.md)
- [LanceDB](https://docs.unstructured.io/open-source/ingestion/destination-connectors/lancedb.md)
- [Local](https://docs.unstructured.io/open-source/ingestion/destination-connectors/local.md)
- [Milvus](https://docs.unstructured.io/open-source/ingestion/destination-connectors/milvus.md)
- [MongoDB](https://docs.unstructured.io/open-source/ingestion/destination-connectors/mongodb.md)
- [MotherDuck](https://docs.unstructured.io/open-source/ingestion/destination-connectors/motherduck.md)
- [Neo4j](https://docs.unstructured.io/open-source/ingestion/destination-connectors/neo4j.md)
- [OneDrive](https://docs.unstructured.io/open-source/ingestion/destination-connectors/onedrive.md)
- [OpenSearch](https://docs.unstructured.io/open-source/ingestion/destination-connectors/opensearch.md)
- [Overview](https://docs.unstructured.io/open-source/ingestion/destination-connectors/overview.md)
- [Pinecone](https://docs.unstructured.io/open-source/ingestion/destination-connectors/pinecone.md)
- [PostgreSQL](https://docs.unstructured.io/open-source/ingestion/destination-connectors/postgresql.md)
- [Qdrant](https://docs.unstructured.io/open-source/ingestion/destination-connectors/qdrant.md)
- [Redis](https://docs.unstructured.io/open-source/ingestion/destination-connectors/redis.md)
- [S3](https://docs.unstructured.io/open-source/ingestion/destination-connectors/s3.md)
- [SFTP](https://docs.unstructured.io/open-source/ingestion/destination-connectors/sftp.md)
- [SingleStore](https://docs.unstructured.io/open-source/ingestion/destination-connectors/singlestore.md)
- [Snowflake](https://docs.unstructured.io/open-source/ingestion/destination-connectors/snowflake.md)
- [SQLite](https://docs.unstructured.io/open-source/ingestion/destination-connectors/sqlite.md)
- [Teradata Database](https://docs.unstructured.io/open-source/ingestion/destination-connectors/teradata-sql.md)
- [Vectara](https://docs.unstructured.io/open-source/ingestion/destination-connectors/vectara.md)
- [Weaviate](https://docs.unstructured.io/open-source/ingestion/destination-connectors/weaviate.md)
- [Process files in batches by using the Unstructured Ingest CLI](https://docs.unstructured.io/open-source/ingestion/ingest-cli.md)
- [Chunking configuration](https://docs.unstructured.io/open-source/ingestion/ingest-configuration/chunking-configuration.md)
- [Embedding configuration](https://docs.unstructured.io/open-source/ingestion/ingest-configuration/embedding-configuration.md)
- [Overview](https://docs.unstructured.io/open-source/ingestion/ingest-configuration/overview.md)
- [Partition configuration](https://docs.unstructured.io/open-source/ingestion/ingest-configuration/partition-configuration.md)
- [Processor configuration](https://docs.unstructured.io/open-source/ingestion/ingest-configuration/processor-configuration.md)
- [Ingest dependencies](https://docs.unstructured.io/open-source/ingestion/ingest-dependencies.md)
- [Overview](https://docs.unstructured.io/open-source/ingestion/overview.md)
- [Process files in batches by using the Unstructured Ingest Python library](https://docs.unstructured.io/open-source/ingestion/python-ingest.md)
- [Airtable](https://docs.unstructured.io/open-source/ingestion/source-connectors/airtable.md)
- [Astra DB](https://docs.unstructured.io/open-source/ingestion/source-connectors/astradb.md)
- [Azure](https://docs.unstructured.io/open-source/ingestion/source-connectors/azure.md)
- [Box](https://docs.unstructured.io/open-source/ingestion/source-connectors/box.md)
- [Confluence](https://docs.unstructured.io/open-source/ingestion/source-connectors/confluence.md)
- [Couchbase](https://docs.unstructured.io/open-source/ingestion/source-connectors/couchbase.md)
- [Databricks Volumes](https://docs.unstructured.io/open-source/ingestion/source-connectors/databricks-volumes.md)
- [Delta Table](https://docs.unstructured.io/open-source/ingestion/source-connectors/delta-table.md)
- [Discord](https://docs.unstructured.io/open-source/ingestion/source-connectors/discord.md)
- [Dropbox](https://docs.unstructured.io/open-source/ingestion/source-connectors/dropbox.md)
- [Elasticsearch](https://docs.unstructured.io/open-source/ingestion/source-connectors/elastic-search.md)
- [GitHub](https://docs.unstructured.io/open-source/ingestion/source-connectors/github.md)
- [GitLab](https://docs.unstructured.io/open-source/ingestion/source-connectors/gitlab.md)
- [Google Cloud Storage](https://docs.unstructured.io/open-source/ingestion/source-connectors/google-cloud-storage.md)
- [Google Drive](https://docs.unstructured.io/open-source/ingestion/source-connectors/google-drive.md)
- [Jira](https://docs.unstructured.io/open-source/ingestion/source-connectors/jira.md)
- [Kafka](https://docs.unstructured.io/open-source/ingestion/source-connectors/kafka.md)
- [Local](https://docs.unstructured.io/open-source/ingestion/source-connectors/local.md)
- [MongoDB](https://docs.unstructured.io/open-source/ingestion/source-connectors/mongodb.md)
- [Notion](https://docs.unstructured.io/open-source/ingestion/source-connectors/notion.md)
- [OneDrive](https://docs.unstructured.io/open-source/ingestion/source-connectors/one-drive.md)
- [OpenSearch](https://docs.unstructured.io/open-source/ingestion/source-connectors/opensearch.md)
- [Outlook](https://docs.unstructured.io/open-source/ingestion/source-connectors/outlook.md)
- [Overview](https://docs.unstructured.io/open-source/ingestion/source-connectors/overview.md)
- [PostgreSQL](https://docs.unstructured.io/open-source/ingestion/source-connectors/postgresql.md)
- [S3](https://docs.unstructured.io/open-source/ingestion/source-connectors/s3.md)
- [Salesforce](https://docs.unstructured.io/open-source/ingestion/source-connectors/salesforce.md)
- [SFTP](https://docs.unstructured.io/open-source/ingestion/source-connectors/sftp.md)
- [SharePoint](https://docs.unstructured.io/open-source/ingestion/source-connectors/sharepoint.md)
- [SingleStore](https://docs.unstructured.io/open-source/ingestion/source-connectors/singlestore.md)
- [Slack](https://docs.unstructured.io/open-source/ingestion/source-connectors/slack.md)
- [Snowflake](https://docs.unstructured.io/open-source/ingestion/source-connectors/snowflake.md)
- [SQLite](https://docs.unstructured.io/open-source/ingestion/source-connectors/sqlite.md)
- [Teradata Database](https://docs.unstructured.io/open-source/ingestion/source-connectors/teradata-sql.md)
- [Zendesk](https://docs.unstructured.io/open-source/ingestion/source-connectors/zendesk.md)
- [Supported file types](https://docs.unstructured.io/open-source/ingestion/supported-file-types.md)
- [Docker installation](https://docs.unstructured.io/open-source/installation/docker-installation.md)
- [Full installation](https://docs.unstructured.io/open-source/installation/full-installation.md)
- [Overview](https://docs.unstructured.io/open-source/installation/overview.md): Unstructured open source library offers flexible options for installation.
- [Integrations](https://docs.unstructured.io/open-source/integrations.md): Integrate your model development pipeline with your favorite machine learning frameworks and libraries, and prepare your data for ingestion into downstream systems. Most of our integrations come in the form of [staging functions](/open-source/core-functionality/staging), which take a list of `Elemen…
- [Overview](https://docs.unstructured.io/open-source/introduction/overview.md)
- [Quickstart](https://docs.unstructured.io/open-source/introduction/quick-start.md)
- [Supported file types](https://docs.unstructured.io/open-source/introduction/supported-file-types.md)
- [Account API keys and API URLs](https://docs.unstructured.io/pipelines/account/api-key-url.md)
- [Account billing](https://docs.unstructured.io/pipelines/account/billing.md)
- [Organizational accounts](https://docs.unstructured.io/pipelines/account/organizations.md)
- [Accounts overview](https://docs.unstructured.io/pipelines/account/overview.md)
- [Role-based access control (RBAC)](https://docs.unstructured.io/pipelines/account/roles.md)
- [Account usage](https://docs.unstructured.io/pipelines/account/usage.md)
- [Workspaces](https://docs.unstructured.io/pipelines/account/workspaces.md)
- [Supported connectors](https://docs.unstructured.io/pipelines/connectors.md)
- [Astra DB](https://docs.unstructured.io/pipelines/destinations/astradb.md)
- [Azure AI Search](https://docs.unstructured.io/pipelines/destinations/azure-ai-search.md)
- [Azure Blob Storage](https://docs.unstructured.io/pipelines/destinations/azure-blob-storage.md)
- [Couchbase](https://docs.unstructured.io/pipelines/destinations/couchbase.md)
- [Delta Tables in Databricks](https://docs.unstructured.io/pipelines/destinations/databricks-delta-table.md): Send processed data from Unstructured to a Delta Table in Databricks.
- [Databricks Volumes](https://docs.unstructured.io/pipelines/destinations/databricks-volumes.md)
- [Delta Tables in Amazon S3](https://docs.unstructured.io/pipelines/destinations/delta-table.md)
- [Elasticsearch](https://docs.unstructured.io/pipelines/destinations/elasticsearch.md)
- [IBM FileNet](https://docs.unstructured.io/pipelines/destinations/filenet.md): Connect Unstructured to IBM FileNet as a destination to send processed document data into your FileNet content repository.
- [Google Cloud Storage](https://docs.unstructured.io/pipelines/destinations/google-cloud.md)
- [IBM watsonx.data](https://docs.unstructured.io/pipelines/destinations/ibm-watsonxdata.md)
- [Kafka](https://docs.unstructured.io/pipelines/destinations/kafka.md)
- [Milvus](https://docs.unstructured.io/pipelines/destinations/milvus.md)
- [MongoDB](https://docs.unstructured.io/pipelines/destinations/mongodb.md)
- [MotherDuck](https://docs.unstructured.io/pipelines/destinations/motherduck.md)
- [Neo4j](https://docs.unstructured.io/pipelines/destinations/neo4j.md)
- [OneDrive](https://docs.unstructured.io/pipelines/destinations/onedrive.md)
- [OpenSearch](https://docs.unstructured.io/pipelines/destinations/opensearch.md)
- [Overview](https://docs.unstructured.io/pipelines/destinations/overview.md)
- [Pinecone](https://docs.unstructured.io/pipelines/destinations/pinecone.md)
- [Pinecone destination connector quickstart](https://docs.unstructured.io/pipelines/destinations/pinecone-destination-quickstart.md)
- [PostgreSQL](https://docs.unstructured.io/pipelines/destinations/postgresql.md)
- [Qdrant](https://docs.unstructured.io/pipelines/destinations/qdrant.md)
- [Redis](https://docs.unstructured.io/pipelines/destinations/redis.md)
- [S3](https://docs.unstructured.io/pipelines/destinations/s3.md)
- [Snowflake](https://docs.unstructured.io/pipelines/destinations/snowflake.md)
- [Teradata Database](https://docs.unstructured.io/pipelines/destinations/teradata-sql.md)
- [Teradata Vector Store](https://docs.unstructured.io/pipelines/destinations/teradata-vector-v2.md): Send processed data from Unstructured to [Teradata Vector Store](https://www.teradata.com/).
- [VAST](https://docs.unstructured.io/pipelines/destinations/vast.md): Send processed data from Unstructured to [VAST](https://www.vastdata.com/).
- [Weaviate](https://docs.unstructured.io/pipelines/destinations/weaviate.md): Send processed data from Unstructured to Weaviate.
- [Jobs](https://docs.unstructured.io/pipelines/jobs.md)
- [Overview](https://docs.unstructured.io/pipelines/overview.md)
- [Unstructured Pipelines quickstarts](https://docs.unstructured.io/pipelines/quickstart.md)
- [Azure Blob Storage](https://docs.unstructured.io/pipelines/sources/azure-blob-storage.md)
- [Box](https://docs.unstructured.io/pipelines/sources/box.md): Ingest your files into Unstructured from Box.
- [Confluence](https://docs.unstructured.io/pipelines/sources/confluence.md)
- [Couchbase](https://docs.unstructured.io/pipelines/sources/couchbase.md)
- [Databricks Volumes](https://docs.unstructured.io/pipelines/sources/databricks-volumes.md)
- [Dropbox](https://docs.unstructured.io/pipelines/sources/dropbox.md)
- [Dropbox source connector quickstart](https://docs.unstructured.io/pipelines/sources/dropbox-source-quickstart.md)
- [Elasticsearch](https://docs.unstructured.io/pipelines/sources/elasticsearch.md)
- [IBM FileNet](https://docs.unstructured.io/pipelines/sources/filenet.md): Connect Unstructured to IBM FileNet as a source to ingest documents and content from your FileNet content repository into Unstructured.
- [Google Cloud Storage](https://docs.unstructured.io/pipelines/sources/google-cloud.md)
- [Google Drive](https://docs.unstructured.io/pipelines/sources/google-drive.md)
- [Jira](https://docs.unstructured.io/pipelines/sources/jira.md)
- [Kafka](https://docs.unstructured.io/pipelines/sources/kafka.md)
- [MongoDB](https://docs.unstructured.io/pipelines/sources/mongodb.md)
- [Microsoft OneDrive](https://docs.unstructured.io/pipelines/sources/onedrive.md): Learn how to Ingest your files into Unstructured from Microsoft OneDrive.
- [OpenSearch](https://docs.unstructured.io/pipelines/sources/opensearch.md)
- [Outlook](https://docs.unstructured.io/pipelines/sources/outlook.md)
- [Overview](https://docs.unstructured.io/pipelines/sources/overview.md)
- [PostgreSQL](https://docs.unstructured.io/pipelines/sources/postgresql.md)
- [S3](https://docs.unstructured.io/pipelines/sources/s3.md)
- [Salesforce](https://docs.unstructured.io/pipelines/sources/salesforce.md)
- [Microsoft SharePoint](https://docs.unstructured.io/pipelines/sources/sharepoint.md): Ingest your files into Unstructured from SharePoint.
- [Slack](https://docs.unstructured.io/pipelines/sources/slack.md)
- [Snowflake](https://docs.unstructured.io/pipelines/sources/snowflake.md)
- [Teradata Database](https://docs.unstructured.io/pipelines/sources/teradata-sql.md)
- [VAST](https://docs.unstructured.io/pipelines/sources/vast.md): Ingest your files into Unstructured from [VAST](https://www.vastdata.com/).
- [Zendesk](https://docs.unstructured.io/pipelines/sources/zendesk.md)
- [Supported file types](https://docs.unstructured.io/pipelines/supported-file-types.md)
- [Unstructured Pipelines walkthrough](https://docs.unstructured.io/pipelines/walkthrough.md)
- [Webhooks](https://docs.unstructured.io/pipelines/webhooks.md)
- [Workflows](https://docs.unstructured.io/pipelines/workflows.md)
- [Access to services](https://docs.unstructured.io/support/access.md)
- [Delete or export personal data stored by Unstructured](https://docs.unstructured.io/support/how-to/data-privacy.md)
- [Raise an invoice issue or request a refund](https://docs.unstructured.io/support/how-to/invoice-issue.md)
- [Overview](https://docs.unstructured.io/support/how-to/overview.md)
- [Google Drive source connectors cannot be created by using the API](https://docs.unstructured.io/support/issues/api-connector-secrets.md)
- [Authorization and permissions issues](https://docs.unstructured.io/support/issues/authorization-permissions.md)
- [S3 destination connector - Unable to locate credentials](https://docs.unstructured.io/support/issues/cannot-locate-credentials.md)
- [Configuration and resource issues](https://docs.unstructured.io/support/issues/configuration-resource.md)
- [Data format, schema, and validation issues](https://docs.unstructured.io/support/issues/data-format-schema-validation.md)
- [Document processing issues](https://docs.unstructured.io/support/issues/document-processing.md)
- [Unable to sign up with personal email address](https://docs.unstructured.io/support/issues/email-addresses.md)
- [Get authenticated user error](https://docs.unstructured.io/support/issues/get-authenticated-user-error.md)
- [Google Drive schema validation failure](https://docs.unstructured.io/support/issues/google-drive-schema-validation.md)
- [Internal issues](https://docs.unstructured.io/support/issues/internal-file-handling.md)
- [Network, connection, and timeout issues](https://docs.unstructured.io/support/issues/network-connection-timeout.md)
- [The Fast strategy is not available for image files](https://docs.unstructured.io/support/issues/no-fast-partitioning-for-images.md)
- [Overview](https://docs.unstructured.io/support/issues/overview.md)
- [Quota, billing, and rate limiting issues](https://docs.unstructured.io/support/issues/quota-billing-rate-limiting.md)
- [Workflow already has a job scheduled or in progress](https://docs.unstructured.io/support/issues/workflow-job-in-progress.md)
- [Requesting support](https://docs.unstructured.io/support/request.md)
- [Shared Responsibility Model](https://docs.unstructured.io/support/shared-responsibility.md)
- [Check service status](https://docs.unstructured.io/support/status.md)
- [Unstructured Transform billing](https://docs.unstructured.io/transform/billing.md): Learn how to get information about how Unstructured calculates your usage and billing for Transform, how to upgrade to a Pay-As-You-Go plan, and other related usage and billing information.
- [Unstructured Transform MCP sample code generation](https://docs.unstructured.io/transform/code.md): Control how the Unstructured Transform MCP server generates curl or Python code that shows how to use Transform to partition, enrich, chunk, and embed the data based on your files.
- [Unstructured Transform MCP server installation for the Google Antigravity CLI](https://docs.unstructured.io/transform/install/antigravity-cli.md): Learn how to install the Unstructured Transform MCP server into the Google Antigravity CLI. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Google Antigravity Desktop](https://docs.unstructured.io/transform/install/antigravity-desktop.md): Learn how to install the Unstructured Transform MCP server into Google Antigravity Desktop. You can then drag and drop your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Claude Code](https://docs.unstructured.io/transform/install/claude-code.md): Learn how to install the Unstructured Transform MCP server into Claude Code. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Claude Desktop](https://docs.unstructured.io/transform/install/claude-desktop.md): Learn how to install the Unstructured Transform MCP server into Claude Desktop. You can then drag and drop files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Cline](https://docs.unstructured.io/transform/install/cline.md): Learn how to install the Unstructured Transform MCP server into Cline. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for the Codex CLI](https://docs.unstructured.io/transform/install/codex-cli.md): Learn how to install the Unstructured Transform MCP server into the Codex CLI. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Codex Desktop](https://docs.unstructured.io/transform/install/codex-desktop.md): Learn how to install the Unstructured Transform MCP server into Codex Desktop. You can then drag and drop files and have Unstructured start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for CrewAI](https://docs.unstructured.io/transform/install/crewai.md): Learn how to connect your CrewAI agents to the Unstructured Transform MCP server so they can parse and extract data from your files.
- [Unstructured Transform MCP server installation for the Cursor CLI](https://docs.unstructured.io/transform/install/cursor-cli.md): Learn how to install the Unstructured Transform MCP server into the Cursor CLI. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for the Cursor IDE](https://docs.unstructured.io/transform/install/cursor-ide.md): Learn how to install the Unstructured Transform MCP server into the Cursor IDE. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for the Devin CLI (formerly the Windsurf CLI)](https://docs.unstructured.io/transform/install/devin-cli.md): Learn how to install the Unstructured Transform MCP server into the Devin CLI (formerly the Windsurf CLI). You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Devin Desktop (formerly the Windsurf IDE)](https://docs.unstructured.io/transform/install/devin-desktop.md): Learn how to install the Unstructured Transform MCP server into Devin Desktop (formerly the Windsurf IDE). You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for DSPy](https://docs.unstructured.io/transform/install/dspy.md): Learn how to connect the Unstructured Transform MCP server to DSPy agents. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Dust](https://docs.unstructured.io/transform/install/dust.md): Learn how to add the Unstructured Transform MCP server to Dust as a remote MCP server. Your Dust agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Firebase Genkit](https://docs.unstructured.io/transform/install/genkit.md): Learn how to connect the Unstructured Transform MCP server to a Firebase Genkit application. Your flows and agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Google ADK](https://docs.unstructured.io/transform/install/google-adk.md): Learn how to connect the Unstructured Transform MCP server to a Google Agent Development Kit (ADK) agent. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Goose](https://docs.unstructured.io/transform/install/goose.md): Learn how to install the Unstructured Transform MCP server into Goose. You can then point Goose to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Grok](https://docs.unstructured.io/transform/install/grok.md): Learn how to connect the Unstructured Transform MCP server to Grok on grok.com. You can then drag and drop files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Grok Build](https://docs.unstructured.io/transform/install/grok-build.md): Learn how to connect the Unstructured Transform MCP server to Grok Build. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Gumloop](https://docs.unstructured.io/transform/install/gumloop.md): Learn how to connect the Unstructured Transform MCP server to Gumloop. Your Gumloop agents and workflows can then turn your files into partitioned, enriched, chunked, and embedded data in minutes.
- [Unstructured Transform MCP server installation for the IBM Bob IDE](https://docs.unstructured.io/transform/install/ibm-bob-ide.md): Learn how to install the Unstructured Transform MCP server into the IBM Bob IDE. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for the IBM Bob Shell](https://docs.unstructured.io/transform/install/ibm-bob-shell.md): Learn how to install the Unstructured Transform MCP server into the IBM Bob Shell. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for LangChain and LangGraph](https://docs.unstructured.io/transform/install/langchain.md): Learn how to connect the Unstructured Transform MCP server to LangChain and LangGraph agents. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Mastra](https://docs.unstructured.io/transform/install/mastra.md): Learn how to connect the Unstructured Transform MCP server to Mastra agents. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Microsoft Agent Framework](https://docs.unstructured.io/transform/install/microsoft-agent-framework.md): Learn how to connect the Unstructured Transform MCP server to Microsoft Agent Framework agents. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for NVIDIA NeMo Agent Toolkit](https://docs.unstructured.io/transform/install/nemo-agent-toolkit.md): Learn how to connect the Unstructured Transform MCP server to an NVIDIA NeMo Agent Toolkit workflow. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Get started with the Unstructured Transform MCP server](https://docs.unstructured.io/transform/install/overview.md): Learn how to install the Unstructured Transform MCP server into various AI tools. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Postman Desktop Agent](https://docs.unstructured.io/transform/install/postman.md): Learn how to install the Unstructured Transform MCP server into the Postman Desktop Agent. You can then drag and drop files and have Unstructured start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for PraisonAI](https://docs.unstructured.io/transform/install/praisonai.md): Learn how to connect the Unstructured Transform MCP server to a PraisonAI agent. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Pydantic AI](https://docs.unstructured.io/transform/install/pydantic-ai.md): Learn how to connect the Unstructured Transform MCP server to Pydantic AI agents. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Vercel AI SDK](https://docs.unstructured.io/transform/install/vercel-ai-sdk.md): Learn how to connect the Unstructured Transform MCP server to the Vercel AI SDK. Your agents can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP server installation for Visual Studio Code](https://docs.unstructured.io/transform/install/vs-code.md): Learn how to install the Unstructured Transform MCP server into Visual Studio Code. You can then point to your files and have Transform start producing partitioned, enriched, chunked, and embedded data based on your files in minutes.
- [Unstructured Transform MCP file parsing options](https://docs.unstructured.io/transform/output.md): Control how the Unstructured Transform MCP server instructs Transform to partition, enrich, chunk, and embed the data based on your files.
- [Unstructured Transform Overview](https://docs.unstructured.io/transform/overview.md): Unstructured Transform quickly turns any document into structured data that is ready for your apps, databases, vector stores, AI tools, and agents.
- [Unstructured Transform MCP prompting strategies](https://docs.unstructured.io/transform/prompts.md): Use these strategies to help get the best results in as few requests as possible when prompting the Unstructured Transform MCP server.
- [Unstructured Transform MCP server quickstart](https://docs.unstructured.io/transform/quickstart.md): Install the Unstructured Transform MCP server, drag and drop files, and have Transform start producing partitioned and enriched data based on your files in minutes.
- [Supported MCP registries for Unstructured Transform](https://docs.unstructured.io/transform/registry.md): Find and install the Unstructured Transform MCP server through MCP registries and connector directories.
- [Unstructured Transform MCP structured data extraction](https://docs.unstructured.io/transform/sde.md): Unstructured Transform includes the ability for you to designate target data from your files, and then extract and convert that data reliably into a structured format of your choosing.
- [Supported file types for Unstructured Transform](https://docs.unstructured.io/transform/supported-file-types.md): Unstructured Transform supports processing of the following file types.
- [Welcome to Unstructured!](https://docs.unstructured.io/welcome.md)

## Optional

- [Get support](https://docs.unstructured.io/support/request)
- [Service status](https://unstructuredio.trust.pagerduty.com/posts/dashboard)
- [Feedback](https://docs.google.com/forms/d/e/1FAIpQLSciKwrJD4m_9ObcTveWMb9yK63FWd7gLxIknovc3kLw_0qUrg/viewform?usp=sf_link)
- [Blog](https://unstructured.io/blog)
- [Product info](https://unstructured.io/)
- [Trust portal](https://trust.unstructured.io/)
- [Contact Sales (e-mail)](mailto:sales@unstructured.io)
- [Meta-prompt (titles)](https://docs.unstructured.io/llms.txt)
- [Meta-prompt (full)](https://docs.unstructured.io/llms-full.txt)