Skip to content

Markdown Conversion documentation #20831

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rita3ko merged 11 commits into from
Mar 20, 2025
Merged

Markdown Conversion documentation #20831

Show file tree
Hide file tree
Changes from 10 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
b8bd0d2
toMarkdown
celso Mar 14, 2025
9dd9a4a
Merge branch 'production' into tomarkdown
celso Mar 14, 2025
1c045f6
Markdown conversion
celso Mar 14, 2025
bfe42a5
Merge branch 'tomarkdown' of github.com:cloudflare/cloudflare-docs in…
celso Mar 14, 2025
a279e99
no D1 here
celso Mar 14, 2025
b699267
fixes path
celso Mar 14, 2025
07b9ac0
better wording
celso Mar 14, 2025
4869dc7
toMarkdown changelog
celso Mar 20, 2025
4785385
Merge branch 'production' into tomarkdown
celso Mar 20, 2025
646ce17
changes date
celso Mar 20, 2025
eee2138
better wording
celso Mar 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 60 additions & 0 deletions src/content/changelog/workers-ai/2025-03-20-markdown-conversion.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
---
title: Markdown conversion in Workers AI
description: You can now convert documents in multiple formats to Markdown using the toMarkdown utility method in Workers AI.
date: 2025-03-20T18:00:00Z
---

Document conversion plays an important role when designing and developing AI applications and agents. Workers AI now provides the `toMarkdown` utility method that developers can use from the `env.AI` binding or the [REST API](/api/resources/ai/) for quick, easy, and convenient conversion and summary of documents in multiple formats to Markdown language.

In this example, we fetch a PDF document and an image from R2 and feed them both to `env.AI.toMarkdown`. The result is a list of converted documents. Workers AI models are used automatically to detect and summarize the image.

```typescript
import { Env } from "./env";

export default {
async fetch(request: Request, env: Env, ctx: ExecutionContext) {

// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/somatosensory.pdf
const pdf = await env.R2.get('somatosensory.pdf');

// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/cat.jpeg
const cat = await env.R2.get('cat.jpeg');

return Response.json(
await env.AI.toMarkdown([
{
name: "somatosensory.pdf",
blob: new Blob([await pdf.arrayBuffer()], { type: "application/octet-stream" }),
},
{
name: "cat.jpeg",
blob: new Blob([await cat.arrayBuffer()], { type: "application/octet-stream" }),
},
]),
);
},
};
```

This is the result:

```json
[
{
"name": "somatosensory.pdf",
"mimeType": "application/pdf",
"format": "markdown",
"tokens": 0,
"data": "# somatosensory.pdf\n## Metadata\n- PDFFormatVersion=1.4\n- IsLinearized=false\n- IsAcroFormPresent=false\n- IsXFAPresent=false\n- IsCollectionPresent=false\n- IsSignaturesPresent=false\n- Producer=Prince 20150210 (www.princexml.com)\n- Title=Anatomy of the Somatosensory System\n\n## Contents\n### Page 1\nThis is a sample document to showcase..."
},
{
"name": "cat.jpeg",
"mimeType": "image/jpeg",
"format": "markdown",
"tokens": 0,
"data": "The image is a close-up photograph of Grumpy Cat, a cat with a distinctive grumpy expression and piercing blue eyes. The cat has a brown face with a white stripe down its nose, and its ears are pointed upright. Its fur is light brown and darker around the face, with a pink nose and mouth. The cat's eyes are blue and slanted downward, giving it a perpetually grumpy appearance. The background is blurred, but it appears to be a dark brown color. Overall, the image is a humorous and iconic representation of the popular internet meme character, Grumpy Cat. The cat's facial expression and posture convey a sense of displeasure or annoyance, making it a relatable and entertaining image for many people."
}
]
```

See [Markdown Conversion](/workers-ai/markdown-conversion/) for more information on supported formats, REST API and pricing.
234 changes: 234 additions & 0 deletions src/content/docs/workers-ai/markdown-conversion.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,234 @@
---
title: Markdown Conversion
pcx_content_type: how-to
sidebar:
order: 5
badge:
text: Beta
---

import { Code, Type, MetaInfo, Details } from "~/components";

[Markdown](https://en.wikipedia.org/wiki/Markdown) is essential for text generation and large language models (LLMs) in training and inference because it can provide structured, semantic, human, and machine-readable input. Likewise, Markdown facilitates chunking and structuring input data for better retrieval and synthesis in the context of RAGs, and its simplicity and ease of parsing and rendering make it ideal for AI Agents.

For these reasons, document conversion plays an important role when designing and developing AI applications. Workers AI provides the `toMarkdown` utility method that developers can use from the [`env.AI`](/workers-ai/configuration/bindings/) binding or the REST APIs for quick, easy, and convenient conversion and summary of documents in multiple formats to Markdown language.

## Methods and definitions

### async env.AI.toMarkdown()

Takes a list of documents in different formats and converts them to Markdown.

#### Parameter

- <code>documents</code>: <Type text="array"/>
- An array of `toMarkdownDocument`s.

#### Return values

- <code>results</code>: <Type text="array"/>
- An array of `toMarkdownDocumentResult`s.

### `toMarkdownDocument` definition

- `name` <Type text="string" />

- Name of the document to convert.

- `blob` <Type text="Blob" />

- A new [Blob](https://developer.mozilla.org/en-US/docs/Web/API/Blob/Blob) object with the document content.

### `toMarkdownDocumentResult` definition

- `name` <Type text="string" />

- Name of the converted document. Matches the input name.

- `mimetype` <Type text="string" />

- The detected [mime type](https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/MIME_types/Common_types) of the document.

- `tokens` <Type text="number" />

- The estimated number of tokens of the converted document.

- `data` <Type text="string" />

- The content of the converted document in Markdown format.

## Supported formats

This is the list of support formats. We are constantly adding new formats and updating this table.

<table>
<tbody>
<th colspan="5" rowspan="1" style="width:160px">
Format
</th>
<th colspan="5" rowspan="1">
File extensions
</th>
<th colspan="5" rowspan="1">
Mime Types
</th>
<tr>
<td colspan="5" rowspan="1">
PDF Documents
</td>
<td colspan="5" rowspan="1">
`.pdf`
</td>
<td colspan="5" rowspan="1">
`application/pdf`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
Images <sup>1</sup>
</td>
<td colspan="5" rowspan="1">
`.jpeg`, `.jpg`, `.png`, `.webp`, `.svg`
</td>
<td colspan="5" rowspan="1">
`image/jpeg`, `image/png`, `image/webp`, `image/svg+xml`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
HTML Documents
</td>
<td colspan="5" rowspan="1">
`.html`
</td>
<td colspan="5" rowspan="1">
`text/html`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
XML Documents
</td>
<td colspan="5" rowspan="1">
`.xml`
</td>
<td colspan="5" rowspan="1">
`application/xml`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
Microsoft Office Documents
</td>
<td colspan="5" rowspan="1">
`.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.et`
</td>
<td colspan="5" rowspan="1">
`application/vnd.openxmlformats-officedocument.spreadsheetml.sheet`, `application/vnd.ms-excel.sheet.macroenabled.12`, `application/vnd.ms-excel.sheet.binary.macroenabled.12`, `application/vnd.ms-excel`, `application/vnd.ms-excel`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
Open Document Format
</td>
<td colspan="5" rowspan="1">
`.ods`
</td>
<td colspan="5" rowspan="1">
`application/vnd.oasis.opendocument.spreadsheet`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
CSV
</td>
<td colspan="5" rowspan="1">
`.csv`
</td>
<td colspan="5" rowspan="1">
`text/csv`
</td>
</tr>
<tr>
<td colspan="5" rowspan="1">
Apple Documents
</td>
<td colspan="5" rowspan="1">
`.numbers`
</td>
<td colspan="5" rowspan="1">
`application/vnd.apple.numbers`
</td>
</tr>
</tbody>
</table>

<sup>1</sup> Image conversion uses two Workers AI models for object detection and summarization. See [pricing](/workers-ai/markdown-conversion/#pricing) for more details.

## Example

In this example, we fetch a PDF document and an image from R2 and feed them both to `env.AI.toMarkdown`. The result is a list of converted documents. Workers AI models are used automatically to detect and summarize the image.

```typescript
import { Env } from "./env";

export default {
async fetch(request: Request, env: Env, ctx: ExecutionContext) {

// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/somatosensory.pdf
const pdf = await env.R2.get('somatosensory.pdf');

// https://pub-979cb28270cc461d94bc8a169d8f389d.r2.dev/cat.jpeg
const cat = await env.R2.get('cat.jpeg');

return Response.json(
await env.AI.toMarkdown([
{
name: "somatosensory.pdf",
blob: new Blob([await pdf.arrayBuffer()], { type: "application/octet-stream" }),
},
{
name: "cat.jpeg",
blob: new Blob([await cat.arrayBuffer()], { type: "application/octet-stream" }),
},
]),
);
},
};
```

This is the result:

```json
[
{
"name": "somatosensory.pdf",
"mimeType": "application/pdf",
"format": "markdown",
"tokens": 0,
"data": "# somatosensory.pdf\n## Metadata\n- PDFFormatVersion=1.4\n- IsLinearized=false\n- IsAcroFormPresent=false\n- IsXFAPresent=false\n- IsCollectionPresent=false\n- IsSignaturesPresent=false\n- Producer=Prince 20150210 (www.princexml.com)\n- Title=Anatomy of the Somatosensory System\n\n## Contents\n### Page 1\nThis is a sample document to showcase..."
},
{
"name": "cat.jpeg",
"mimeType": "image/jpeg",
"format": "markdown",
"tokens": 0,
"data": "The image is a close-up photograph of Grumpy Cat, a cat with a distinctive grumpy expression and piercing blue eyes. The cat has a brown face with a white stripe down its nose, and its ears are pointed upright. Its fur is light brown and darker around the face, with a pink nose and mouth. The cat's eyes are blue and slanted downward, giving it a perpetually grumpy appearance. The background is blurred, but it appears to be a dark brown color. Overall, the image is a humorous and iconic representation of the popular internet meme character, Grumpy Cat. The cat's facial expression and posture convey a sense of displeasure or annoyance, making it a relatable and entertaining image for many people."
}
]
```

## REST API

In addition to the Workers AI [binding](/workers-ai/configuration/bindings/), you can use the [REST API](/workers-ai/get-started/rest-api/):

```bash
curl https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/tomarkdown \
-H 'Authorization: Bearer {API_TOKEN}' \
-F "[email protected]" \
-F "[email protected]"
```

## Pricing

`toMarkdown` is free for most format conversions. In some cases, like image conversion, it can use Workers AI models for object detection and summarization, which may incur additional costs if it exceeds the Workers AI free allocation limits. See the [pricing page](/workers-ai/platform/pricing/) for more details.
52 changes: 43 additions & 9 deletions src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,9 +33,26 @@
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 131072,
"description": "The input text prompt for the model to generate a response."
},
"lora": {
"type": "string",
"description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."
},
"response_format": {
"title": "JSON Mode",
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"json_object",
"json_schema"
]
},
"json_schema": {}
}
},
"raw": {
"type": "boolean",
"default": false,
Expand Down Expand Up @@ -93,10 +110,6 @@
"minimum": 0,
"maximum": 2,
"description": "Increases the likelihood of the model introducing new topics."
},
"lora": {
"type": "string",
"description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."
}
},
"required": [
Expand All @@ -118,7 +131,6 @@
},
"content": {
"type": "string",
"maxLength": 131072,
"description": "The content of the message as a string."
}
},
Expand Down Expand Up @@ -287,10 +299,29 @@
]
}
},
"response_format": {
"title": "JSON Mode",
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"json_object",
"json_schema"
]
},
"json_schema": {}
}
},
"raw": {
"type": "boolean",
"default": false,
"description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting."
},
"stream": {
"type": "boolean",
"default": false,
"description": "If true, the response will be streamed back incrementally."
"description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events."
},
"max_tokens": {
"type": "integer",
Expand All @@ -308,7 +339,7 @@
"type": "number",
"minimum": 0,
"maximum": 2,
"description": "Controls the creativity of the AI's responses by adjusting how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."
"description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."
},
"top_k": {
"type": "integer",
Expand Down Expand Up @@ -395,7 +426,10 @@
}
}
}
}
},
"required": [
"response"
]
},
{
"type": "string",
Expand Down
Loading
Loading