📝(docs) fix resource server code snippet

[jmaupetit]

Proposal

One needs to be authenticated while requesting the external API.

[coderabbitai]

Walkthrough

The “Create a document” example in documentation/resource_server.md now passes an explicit headers dictionary to requests.post(...), containing the Bearer access token and Content-Type: application/json.

Estimated code review effort: 1 (Trivial) | ~2 minutes

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is concise and clearly refers to the documentation snippet being fixed.
Description check	✅ Passed	The description matches the change by noting authentication is required for external API requests.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch fix-resource-server-doc

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@documentation/resource_server.md`:
- Line 90: Update the multipart upload request in the documentation example to
remove the explicit Content-Type header while preserving the Authorization
Bearer header, allowing requests to generate the correct multipart/form-data
boundary automatically.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Repository UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 9c2da300-630c-4f62-9dbb-4fc228bc20e0

📥 Commits

Reviewing files that changed from the base of the PR and between 9c3bc8a and 203d9c6.

📒 Files selected for processing (1)

• documentation/resource_server.md

[coderabbitai]

🗄️ Data Integrity & Integration | 🟠 Major | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "== locate file =="
git ls-files | grep 'documentation/resource_server.md' || true

echo "== relevant file section =="
if [ -f documentation/resource_server.md ]; then
  wc -l documentation/resource_server.md
  sed -n '70,105p' documentation/resource_server.md | cat -n
fi

echo "== search multipart/upload endpoint references =="
rg -n "files=|multipart|Content-Type|request\.data|json\(request|file" documentation/resource_server.md . --glob '!**/.git/**' --glob '!**/node_modules/**' | head -200

Repository: suitenumerique/docs

Length of output: 18930

---

🌐 Web query:

Python requests file parameters multipart content-type header boundary Content-Type application/json documentation

💡 Result:

When using the Python requests library, you should generally avoid manually setting the Content-Type header for multipart/form-data requests [1][2][3]. The library automatically calculates the correct Content-Type, including the necessary unique boundary string, whenever you provide the files parameter [1][2][4]. If you manually set the Content-Type header to multipart/form-data without the boundary parameter, or with a custom boundary that does not match the request body, your request will likely fail because the server will be unable to parse the multipart structure [1][5][6]. To send both JSON data and files in a single request, the standard approach is to treat the JSON payload as a file-like object within the files dictionary [7][8]. This allows you to specify its Content-Type as application/json, while the overall request remains multipart-encoded [7]: import requests import json url = 'http://example.com/upload' files = { 'file': ('filename.txt', open('filename.txt', 'rb')), 'metadata': (None, json.dumps({'key': 'value'}), 'application/json') } response = requests.post(url, files=files) In this example, the (None,...) syntax tells requests that the 'metadata' part is not a file, but a data field with an explicit MIME type [7]. If you have a strict requirement to control the boundary manually (e.g., for legacy API compatibility), you should not use the files parameter directly [9][3]. Instead, use the requests-toolbelt library, which provides a MultipartEncoder class designed for this purpose [5][9]. This allows you to generate both the body and the correct Content-Type header (including the boundary) to pass into your requests.post call [5][9].

Citations:

• 1: https://stackoverflow.com/questions/12385179/how-to-send-a-multipart-form-data-with-requests-in-python
• 2: https://bobbyhadz.com/blog/send-multipart-form-data-request-with-requests-in-python
• 3: https://stackoverflow.com/questions/26299889/how-to-post-multipart-list-of-json-xml-files-using-python-requests
• 4: Requests doesn't add boundary when passing Content-Type: multipart/form-data header manually psf/requests#6024
• 5: boundary for custom 'Content-Type: multipart/form-data' header psf/requests#1997
• 6: Custom multipart/form-data Content-Type header silently discards file upload psf/requests#4554
• 7: https://stackoverflow.com/questions/19439961/python-requests-post-json-and-file-in-single-request
• 8: https://stackoverflow.com/questions/70775095/how-to-send-file-and-json-data-with-python-requests-library
• 9: https://stackoverflow.com/questions/36286656/python-set-up-boundary-for-post-using-multipart-form-data-with-requests

---

🌐 Web query:

requests-toolbelt package Python multipart encoding Content-Type header boundary

💡 Result:

The requests-toolbelt package provides the MultipartEncoder class, which automatically handles multipart/form-data encoding and generates the necessary boundary for your request [1][2]. When using MultipartEncoder, you must explicitly set the Content-Type header in your requests.post call using the encoder's content_type property, as the requests library will not automatically set it for you [2][3]. The encoder generates a unique boundary string, which is included in the value returned by the content_type property [1]. To use it, instantiate the MultipartEncoder with your fields and pass the encoder instance to the data parameter of your request, ensuring you set the header as follows: from requests_toolbelt import MultipartEncoder import requests # Create the encoder with your fields m = MultipartEncoder(fields={'field0': 'value', 'field1': 'file_content'}) # Post the request, using m.content_type to set the header r = requests.post('https://httpbin.org/post', data=m, headers={'Content-Type': m.content_type}) The m.content_type property dynamically constructs a string in the format multipart/form-data; boundary=<boundary_value> [1].

Citations:

• 1: https://github.com/requests/toolbelt/blob/master/requests_toolbelt/multipart/encoder.py
• 2: https://toolbelt.readthedocs.io/en/stable/uploading-data.html
• 3: https://toolbelt.readthedocs.io/en/latest/uploading-data.html

---

Do not override the multipart Content-Type header.

This request only uploads a file and lets requests build the multipart body. Passing Content-Type: application/json mislabels the payload; keep the Bearer header and remove the explicit content type so the client can generate the correct multipart/form-data; boundary=... header.

Proposed fix

-            headers={"Authorization": f"Bearer {access_token}", "Content-Type": "application/json"},
+            headers={"Authorization": f"Bearer {access_token}"},

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

	headers={"Authorization": f"Bearer {access_token}", "Content-Type": "application/json"},
	headers={"Authorization": f"Bearer {access_token}"},

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@documentation/resource_server.md` at line 90, Update the multipart upload
request in the documentation example to remove the explicit Content-Type header
while preserving the Authorization Bearer header, allowing requests to generate
the correct multipart/form-data boundary automatically.