Skip to main content
After you connect your AI tool to the Transform MCP server, to send your files to Transform for processing, you can give your AI tool or agent a simple prompt such as the following, depending on where your files are stored: Somewhere on your local filesystem: Replace <local-paths-to-your-files> in the following prompt with the paths to your target files:
Within a project: For project-based AI sessions, you can use this simple prompt instead:
Attached to a chat: If you have added your target files directly to an AI chat session, you can use this simple prompt instead:
Transform will parse your files by using its default file parsing options, as described in the next section. You can change any or all of these options.

​
Default file parsing options

By default, when the Transform MCP server parses your files: You can change any or all of these options, as described in the next section.

​
Specify file parsing options

To learn how to specify file parsing options, after you connect your AI tool to the Transform MCP server, ask your AI tool the following:

​
Core parsing options

The following core options are available:

​
Output formats

The file metadata Transform includes in output files depends on the output format you choose:
  • json: Transform produces Unstructured document elements and metadata.
  • md and html: Transform includes an HTML comment at the top of the output file that includes file name, file type, and last modified date. For example:
  • txt: Transform does not include file metadata.

​
Chunking options

For chunking, the following options are available. Learn about chunking.

​
Embedding options

For available embedding provider and model options, enter the following prompt:
Learn about embedding.

​
File parsing prompt examples

Additional partitioning strategy prompt examples:
  • Partition using the default auto strategy.
  • Use fast partitioning.
  • Use hi_res parsing.
  • Use vlm parsing.
Additional enrichment prompt examples:
  • Add image descriptions for figures and diagrams.
  • Add table descriptions for the tables.
  • Convert tables to structured HTML.
  • Extract named entities and their relationships.
  • Use generative OCR because the document has handwriting.
Additional chunking strategy prompt examples:
  • Chunk by title, combining any sections under 200 characters into the next one.
  • Split this into chunks of 1000 characters each, with a 100-character overlap between chunks.
  • Chunk this by similarity, starting a new chunk whenever the similarity threshold drops below 0.75.
  • Chunk by character, starting a new chunk after 1500 characters, but cap each chunk at 2000 characters maximum.
Additional embedding prompt examples:
  • Embed this using OpenAI's text-embedding-3-small model.
  • Embed these contracts using Voyage AI's voyage-law-2 model.
  • Chunk this by title, then embed it with IBM's all-minilm-l6-v2 model.
Additional output format prompt examples:
  • Return the parsed results as Markdown.
  • Return the parsed results as JSON.
  • Return the parsed results as HTML.
  • Return the parsed results as plain text.
Complete example prompts:
  • Partition in hi-res mode, optimizing for French and English. Enrich it with table-to-HTML and generative OCR. Chunk it by title, combining sections under 500 characters. Embed it with Voyage AI's voyage-3-large model. Give me the final output as JSON.
  • Use hi-res partitioning on this contract, pages 1 through 5 only. Run named entity recognition to tag parties and dates. Chunk it by character with a max of 1200 characters and a 150-character overlap. Embed using Voyage AI's voyage-law-2 model. Return the result as Markdown.
  • Partition this technical manual with the VLM strategy. Enrich it with image descriptions and table descriptions. Chunk it by page. Embed with OpenAI's text-embedding-3-large model. Output it as HTML.
  • Partition these plain text files using the fast strategy. Skip enrichments. Chunk it by similarity with a threshold of 0.75. Embed it using OpenAI's text-embedding-3-small model. Give me plain text output.
  • Partition these filings in hi-res mode, pages 1 through 30 only. The filings are in German. Enrich with table-to-HTML and table descriptions. Chunk it by title, capping chunks at 1000 characters. Embed it with Voyage AI's voyage-finance-2 model. Return the output as JSON, keeping full Base64 for image elements.

​
Extract structured data

If you want to pull specific fields from your files, instead of converting the files in full, ask for an extraction. To determine what structured data Transform can extract from your files, use a prompt similar to the following:
Your tool parses each file first, then extracts the field values from the parsed element JSON; this is because the Transform MCP extraction tools read a file’s parsed output, rather than the raw file itself. Transform returns results as JSON matching the schema, wrapped with the source filename so you can tell a batch apart. If you know the specific fields you want, include them in your prompt to guide Transform in extracting just the information that’s important to you. For more information, including prompting patterns and performance considerations, see Structured data extraction.

​
Next steps

  • Transform quickstart: 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.
  • Write effective Transform prompts: Get the best results from the Unstructured Transform MCP server in as few requests as possible using these prompting strategies.
  • Control Transform structured data extraction: Control how the Unstructured Transform MCP server extracts and formats structured data from your files.
  • Control Transform generated sample code: Control how the Unstructured Transform MCP server generates sample curl or Python code that demonstrates how to use Transform to partition, enrich, chunk, and embed the data based on your files.