# Unstructured Transform

> Transform documentation. SDK examples use the Transform SDK package. Links use https://docs.unstructured.io.

- [Parse your first document](https://docs.unstructured.io/transform/first-request): Log in to Transform, upload a document, then Parse its content. Optionally, Extract structured data and use Get Code to build an integration.
- [Upload and reuse a document](https://docs.unstructured.io/transform/upload): Upload a document once and reuse its file ID in Parse or Extract requests. Read the expiry time and upload the original again if needed.
- [Parse a document](https://docs.unstructured.io/transform/parse): Parse a document with one input field and your API key. Read Markdown, request individual elements, or reuse the result for extraction.
- [Parse response format](https://docs.unstructured.io/transform/parse-response): Read Markdown or individual elements from a completed Parse response. Inspect a captured example and follow progress when a request is pending.
- [Extract structured data](https://docs.unstructured.io/transform/extract): Extract structured fields from a document with a JSON Schema, or reuse a completed Parse. Read the returned values and follow pending jobs.
- [Extract response format](https://docs.unstructured.io/transform/extract-response): Read extracted values in the structure defined by your schema. Inspect a captured invoice response and handle missing citation metadata.
- [Define your extraction schema](https://docs.unstructured.io/transform/extract-schema): Define the fields and types to extract with JSON Schema. Add optional instructions, choose the request encoding, and fix rejected schemas.
- [Chain Parse and Extract](https://docs.unstructured.io/transform/chaining): Parse a document once, then pass its ID to Extract with a schema. Follow complete Python, TypeScript, and cURL examples to reuse parsed content.
- [Integrate with Get Code](https://docs.unstructured.io/transform/get-code): Use Get Code after parsing a document or extracting fields in Transform, then configure your API key and carry the flow into your application.
- [Use your API key](https://docs.unstructured.io/transform/authentication): Authenticate Transform API requests with your API key, manage keys in Transform, and resolve access errors for uploads, jobs, and results.
- [Follow request progress](https://docs.unstructured.io/transform/jobs): Follow Transform jobs after HTTP 202, list and filter job history, read status, stream Parse progress, or request cancellation.
- [Python SDK](https://docs.unstructured.io/transform/sdk-python): Install the Python SDK and use your API key to parse documents, extract fields, follow pending extractions, browse jobs, and configure retries.
- [TypeScript SDK](https://docs.unstructured.io/transform/sdk-typescript): Install the TypeScript SDK to parse documents and extract fields. Follow pending extractions, iterate over jobs, and configure request retries.
- [Transform API reference](https://docs.unstructured.io/transform/api-reference): Find Transform endpoints for Parse, Extract, uploads, and jobs. Review required inputs, optional parameters, response fields, and error schemas.
- [Recover from a failed request](https://docs.unstructured.io/transform/recovery): Match Transform error codes to fixes for rejected input, expired results, and access failures. Check existing jobs before retrying a request.
- [Supported files and limits](https://docs.unstructured.io/transform/limits): Check supported file extensions and the documented limits on document size, extraction schemas, and prompts before sending a Transform request.
- [Document retention and expiry](https://docs.unstructured.io/transform/retention): Check when uploaded files expire, recover missing files or expired Parse results, and understand what deleting a file or Parse job removes.
- [Parse API reference](https://docs.unstructured.io/transform/api/parseRun): Parse a document with the Transform API. Review the input field, output and profile options, and the Markdown or elements response schema.
- [Extract fields from a Parse or document](https://docs.unstructured.io/transform/api/extractRun): Extract structured fields from a document or a completed Parse with a schema. Review required inputs, returned values, and pending responses.
- [List parse and extraction jobs](https://docs.unstructured.io/transform/api/jobsList): List Parse and Extract jobs visible to your API key, newest first. Review filters, pagination parameters, and the fields returned for each job.
- [Get the status or result of a job](https://docs.unstructured.io/transform/api/jobsGet): Retrieve a job status and its result when available. Review the result wrapper or request server-sent events to follow progress.
- [Delete a finished job](https://docs.unstructured.io/transform/api/jobsDelete): Remove a terminal job from API listings asynchronously. Review deletion responses and understand how source and output retention differ.
- [Request cancellation of a job](https://docs.unstructured.io/transform/api/jobsCancel): Request cancellation of a queued or processing job. Read the returned job snapshot and keep polling until the job reaches a final status.
- [Upload a file](https://docs.unstructured.io/transform/api/uploadRun): Upload a file for reuse in Parse or Extract requests. Review supported input, the returned file ID and media type, and the file expiry timestamp.
- [Get an uploaded file](https://docs.unstructured.io/transform/api/uploadGet): Retrieve a file you previously uploaded to Transform using its file ID. Review the file response and errors for missing or expired uploads.
- [Delete an uploaded file](https://docs.unstructured.io/transform/api/uploadDelete): Delete an uploaded file before it expires. Review the HTTP 204 response, including when the file ID is already deleted or was never valid.
- [Agents & LLMs overview](https://docs.unstructured.io/transform/agents-llms): Unstructured supports AI agents and LLMs through Unstructured Transform, a dedicated agent guide, and agent-ready Markdown and helper files.
- [Unstructured guide for agents](https://docs.unstructured.io/agent-guide): Key instructions and resources for agents about Unstructured.
- [Unstructured Transform Overview](https://docs.unstructured.io/transform/overview): Unstructured Transform quickly turns any document into structured data that is ready for your apps, databases, vector stores, AI tools, and agents.
- [Supported file types for Transform MCP](https://docs.unstructured.io/transform/supported-file-types): The Transform MCP server supports processing of the following file types.
- [Supported MCP registries for Unstructured Transform](https://docs.unstructured.io/transform/registry): Find and install the Unstructured Transform MCP server through MCP registries and connector directories.
- [Get started with the Unstructured Transform MCP server](https://docs.unstructured.io/transform/get-started/overview): Learn how to connect and use the Unstructured Transform MCP server in 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.
- [Get started with Unstructured Transform for Claude Code](https://docs.unstructured.io/transform/get-started/claude-code): 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.
- [Get started with Unstructured Transform for Claude Desktop](https://docs.unstructured.io/transform/get-started/claude-desktop): Learn how to install the Unstructured Transform MCP server into Claude Desktop, then drag and drop files to have Transform produce partitioned, enriched, chunked, and embedded data.
- [Get started with Unstructured Transform for Cline](https://docs.unstructured.io/transform/get-started/cline): 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.
- [Get started with Unstructured Transform for the Codex CLI](https://docs.unstructured.io/transform/get-started/codex-cli): 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.
- [Get started with Unstructured Transform for Codex ChatGPT Desktop](https://docs.unstructured.io/transform/get-started/codex-desktop): Learn how to install the Unstructured Transform MCP server into the ChatGPT desktop app. 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.
- [Get started with Unstructured Transform for CrewAI](https://docs.unstructured.io/transform/get-started/crewai): Learn how to connect your CrewAI agents to the Unstructured Transform MCP server so they can partition and extract data from your files.
- [Get started with Unstructured Transform for the Cursor CLI](https://docs.unstructured.io/transform/get-started/cursor-cli): Learn how to install the Unstructured Transform MCP server into the Cursor CLI, then turn your files into partitioned, enriched, chunked, and embedded data.
- [Get started with Unstructured Transform for the Cursor IDE](https://docs.unstructured.io/transform/get-started/cursor-ide): Learn how to install the Unstructured Transform MCP server into the Cursor IDE, then turn your files into partitioned, enriched, chunked, and embedded data.
- [Get started with Unstructured Transform for Devin (formerly Windsurf)](https://docs.unstructured.io/transform/get-started/devin): Learn how to connect the Unstructured Transform MCP server in the Devin CLI or Devin Desktop, then turn your files into partitioned, enriched, chunked, and embedded data.
- [Get started with Unstructured Transform for DSPy](https://docs.unstructured.io/transform/get-started/dspy): 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.
- [Get started with Unstructured Transform for Dust](https://docs.unstructured.io/transform/get-started/dust): 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.
- [Get started with Unstructured Transform for Firebase Genkit](https://docs.unstructured.io/transform/get-started/genkit): 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.
- [Get started with Unstructured Transform for Google ADK](https://docs.unstructured.io/transform/get-started/google-adk): 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.
- [Get started with Unstructured Transform for Google Antigravity](https://docs.unstructured.io/transform/get-started/antigravity): Learn how to connect the Unstructured Transform MCP server in Google Antigravity, then partition your files into enriched, chunked, and embedded data.
- [Get started with Unstructured Transform for Goose](https://docs.unstructured.io/transform/get-started/goose): 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.
- [Get started with Unstructured Transform for Grok](https://docs.unstructured.io/transform/get-started/grok): 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.
- [Get started with Unstructured Transform for Grok Build](https://docs.unstructured.io/transform/get-started/grok-build): 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.
- [Get started with Unstructured Transform for Gumloop](https://docs.unstructured.io/transform/get-started/gumloop): 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.
- [Get started with Unstructured Transform for the IBM Bob IDE](https://docs.unstructured.io/transform/get-started/ibm-bob-ide): 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.
- [Get started with Unstructured Transform for the IBM Bob Shell](https://docs.unstructured.io/transform/get-started/ibm-bob-shell): 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.
- [Get started with Unstructured Transform for LangChain and LangGraph](https://docs.unstructured.io/transform/get-started/langchain): 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.
- [Get started with Unstructured Transform for Mastra](https://docs.unstructured.io/transform/get-started/mastra): 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.
- [Get started with Unstructured Transform for Microsoft Agent Framework](https://docs.unstructured.io/transform/get-started/microsoft-agent-framework): 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.
- [Get started with Unstructured Transform for NVIDIA NeMo Agent Toolkit](https://docs.unstructured.io/transform/get-started/nemo-agent-toolkit): 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 Unstructured Transform for Postman Desktop Agent](https://docs.unstructured.io/transform/get-started/postman): 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.
- [Get started with Unstructured Transform for PraisonAI](https://docs.unstructured.io/transform/get-started/praisonai): 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.
- [Get started with Unstructured Transform for Pydantic AI](https://docs.unstructured.io/transform/get-started/pydantic-ai): 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.
- [Get started with Unstructured Transform for Sim](https://docs.unstructured.io/transform/get-started/sim): Learn how to connect the Unstructured Transform MCP server to Sim and use agents to convert documents into structured, LLM-ready data.
- [Get started with Unstructured Transform for Vercel AI SDK](https://docs.unstructured.io/transform/get-started/vercel-ai-sdk): 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.
- [Get started with Unstructured Transform for Visual Studio Code](https://docs.unstructured.io/transform/get-started/vs-code): 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 partitioning options](https://docs.unstructured.io/transform/output): Control how the Unstructured Transform MCP server instructs Transform to partition, enrich, chunk, and embed the data based on your files.
- [Unstructured Transform MCP prompting strategies](https://docs.unstructured.io/transform/prompts): 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 structured data extraction](https://docs.unstructured.io/transform/sde): 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.
- [Unstructured Transform MCP sample code generation](https://docs.unstructured.io/transform/code): 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 billing](https://docs.unstructured.io/transform/billing): 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.
- [Read Transform results](https://docs.unstructured.io/transform/results): Read completed Parse and Extract results, find document content inside a retrieved Parse job, and handle warnings or missing citation metadata.