chore: bump version to 0.15.0 [skip ci]

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

.github/dco.yml

@@ -0,0 +1,2 @@
+allowRemediationCommits:
+  individual: true

.github/workflows/dco-advisor.yml

@@ -0,0 +1,192 @@
+name: DCO Advisor Bot
+
+on:
+  pull_request_target:
+    types: [opened, reopened, synchronize]
+
+permissions:
+  pull-requests: write
+  issues: write
+
+jobs:
+  dco_advisor:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Handle DCO check result
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const pr = context.payload.pull_request || context.payload.check_run?.pull_requests?.[0];
+            if (!pr) return;
+
+            const prNumber = pr.number;
+            const baseRef = pr.base.ref;
+            const headSha =
+              context.payload.check_run?.head_sha ||
+              pr.head?.sha;
+            const username = pr.user.login;
+
+            console.log("HEAD SHA:", headSha);
+
+            const sleep = ms => new Promise(resolve => setTimeout(resolve, ms));
+
+            // Poll until DCO check has a conclusion (max 6 attempts, 30s)
+            let dcoCheck = null;
+            for (let attempt = 0; attempt < 6; attempt++) {
+              const { data: checks } = await github.rest.checks.listForRef({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                ref: headSha
+              });
+
+              
+              console.log("All check runs:");
+                checks.check_runs.forEach(run => {
+                console.log(`- ${run.name} (${run.status}/${run.conclusion}) @ ${run.head_sha}`);
+              });
+
+              dcoCheck = checks.check_runs.find(run =>
+                run.name.toLowerCase().includes("dco") &&
+              !run.name.toLowerCase().includes("dco_advisor") &&
+                run.head_sha === headSha
+              );
+
+
+              if (dcoCheck?.conclusion) break;
+              console.log(`Waiting for DCO check... (${attempt + 1})`);
+              await sleep(5000); // wait 5 seconds
+            }
+
+            if (!dcoCheck || !dcoCheck.conclusion) {
+              console.log("DCO check did not complete in time.");
+              return;
+            }
+
+            const isFailure = ["failure", "action_required"].includes(dcoCheck.conclusion);
+            console.log(`DCO check conclusion for ${headSha}: ${dcoCheck.conclusion} (treated as ${isFailure ? "failure" : "success"})`);
+
+            // Parse DCO output for commit SHAs and author
+            let badCommits = [];
+            let authorName = "";
+            let authorEmail = "";
+            let moreInfo = `More info: [DCO check report](${dcoCheck?.html_url})`;
+
+            if (isFailure) {
+                const { data: commits } = await github.rest.pulls.listCommits({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    pull_number: prNumber,
+                });
+
+                for (const commit of commits) {
+                    const commitMessage = commit.commit.message;
+                    const signoffMatch = commitMessage.match(/^Signed-off-by:\s+.+<.+>$/m);
+                    if (!signoffMatch) {
+                        console.log(`Bad commit found ${commit.sha}`)
+                        badCommits.push({
+                        sha: commit.sha,
+                        authorName: commit.commit.author.name,
+                        authorEmail: commit.commit.author.email,
+                        });
+                    }
+                }            
+            }
+
+            // If multiple authors are present, you could adapt the message accordingly
+            // For now, we'll just use the first one
+            if (badCommits.length > 0) {
+            authorName = badCommits[0].authorName;
+            authorEmail = badCommits[0].authorEmail;
+            }
+
+            // Generate remediation commit message if needed
+            let remediationSnippet = "";
+            if (badCommits.length && authorEmail) {
+              remediationSnippet = `git commit --allow-empty -s -m "DCO Remediation Commit for ${authorName} <${authorEmail}>\n\n` +
+                badCommits.map(c => `I, ${c.authorName} <${c.authorEmail}>, hereby add my Signed-off-by to this commit: ${c.sha}`).join('\n') +
+                `"`;
+            } else {
+              remediationSnippet = "# Unable to auto-generate remediation message. Please check the DCO check details.";
+            }
+
+            // Build comment
+            const commentHeader = '<!-- dco-advice-bot -->';
+            let body = "";
+
+            if (isFailure) {
+              body = [
+                commentHeader,
+                '❌ **DCO Check Failed**',
+                '',
+                `Hi @${username}, your pull request has failed the Developer Certificate of Origin (DCO) check.`,
+                '',
+                'This repository supports **remediation commits**, so you can fix this without rewriting history — but you must follow the required message format.',
+                '',
+                '---',
+                '',
+                '### 🛠 Quick Fix: Add a remediation commit',
+                'Run this command:',
+                '',
+                '```bash',
+                remediationSnippet,
+                'git push',
+                '```',
+                '',
+                '---',
+                '',
+                '<details>',
+                '<summary>🔧 Advanced: Sign off each commit directly</summary>',
+                '',
+                '**For the latest commit:**',
+                '```bash',
+                'git commit --amend --signoff',
+                'git push --force-with-lease',
+                '```',
+                '',
+                '**For multiple commits:**',
+                '```bash',
+                `git rebase --signoff origin/${baseRef}`,
+                'git push --force-with-lease',
+                '```',
+                '',
+                '</details>',
+                '',
+                moreInfo
+              ].join('\n');
+            } else {
+              body = [
+                commentHeader,
+                '✅ **DCO Check Passed**',
+                '',
+                `Thanks @${username}, all your commits are properly signed off. 🎉`
+              ].join('\n');
+            }
+
+            // Get existing comments on the PR
+            const { data: comments } = await github.rest.issues.listComments({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: prNumber
+            });
+
+            // Look for a previous bot comment
+            const existingComment = comments.find(c =>
+              c.body.includes("<!-- dco-advice-bot -->")
+            );
+
+            if (existingComment) {
+              await github.rest.issues.updateComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: existingComment.id,
+                body: body
+              });
+            } else {
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: prNumber,
+                body: body
+              });
+            }

CHANGELOG.md

@@ -1,3 +1,29 @@
+## [v0.15.0](https://github.com/docling-project/docling-serve/releases/tag/v0.15.0) - 2025-06-17
+
+### Feature
+
+* Use redocs and scalar as api docs ([#228](https://github.com/docling-project/docling-serve/issues/228)) ([`873d05a`](https://github.com/docling-project/docling-serve/commit/873d05aefe141c63b9c1cf53b23b4fa8c96de05d))
+
+### Fix
+
+* "tesserocr" instead of "tesseract_cli" in usage docs ([#223](https://github.com/docling-project/docling-serve/issues/223)) ([`196c5ce`](https://github.com/docling-project/docling-serve/commit/196c5ce42a04d77234a4212c3d9b9772d2c2073e))
+
+## [v0.14.0](https://github.com/docling-project/docling-serve/releases/tag/v0.14.0) - 2025-06-17
+
+### Feature
+
+* Read supported file extensions from docling ([#214](https://github.com/docling-project/docling-serve/issues/214)) ([`524f6a8`](https://github.com/docling-project/docling-serve/commit/524f6a8997b86d2f869ca491ec8fb40585b42ca4))
+
+### Fix
+
+* Typo in Headline ([#220](https://github.com/docling-project/docling-serve/issues/220)) ([`d5455b7`](https://github.com/docling-project/docling-serve/commit/d5455b7f66de39ea1f8b8927b5968d2baa23ca88))
+
+## [v0.13.0](https://github.com/docling-project/docling-serve/releases/tag/v0.13.0) - 2025-06-04
+
+### Feature
+
+* Upgrade docling to 2.36 ([#212](https://github.com/docling-project/docling-serve/issues/212)) ([`ffea347`](https://github.com/docling-project/docling-serve/commit/ffea34732b24fdd438fabd6df02d3d9ce66b4534))
+
 ## [v0.12.0](https://github.com/docling-project/docling-serve/releases/tag/v0.12.0) - 2025-06-03
 
 ### Feature

docling_serve/__main__.py

@@ -113,11 +113,13 @@ def _run(
     protocol = "https" if run_ssl else "http"
     url = f"{protocol}://{uvicorn_settings.host}:{uvicorn_settings.port}"
     url_docs = f"{url}/docs"
+    url_scalar = f"{url}/scalar"
     url_ui = f"{url}/ui"
 
     console.print("")
     console.print(f"Server started at [link={url}]{url}[/]")
     console.print(f"Documentation at [link={url_docs}]{url_docs}[/]")
+    console.print(f"Scalar docs at [link={url_docs}]{url_scalar}[/]")
     if docling_serve_settings.enable_ui:
         console.print(f"UI at [link={url_ui}]{url_ui}[/]")
 

docling_serve/app.py

@@ -25,6 +25,7 @@ from fastapi.openapi.docs import (
 )
 from fastapi.responses import RedirectResponse
 from fastapi.staticfiles import StaticFiles
+from scalar_fastapi import get_scalar_api_reference
 
 from docling.datamodel.base_models import DocumentStream
 
@@ -140,8 +141,8 @@ def create_app():  # noqa: C901
 
     app = FastAPI(
         title="Docling Serve",
-        docs_url=None if offline_docs_assets else "/docs",
-        redoc_url=None if offline_docs_assets else "/redocs",
+        docs_url=None if offline_docs_assets else "/swagger",
+        redoc_url=None if offline_docs_assets else "/docs",
         lifespan=lifespan,
         version=version,
     )
@@ -192,7 +193,7 @@ def create_app():  # noqa: C901
             name="static",
         )
 
-        @app.get("/docs", include_in_schema=False)
+        @app.get("/swagger", include_in_schema=False)
         async def custom_swagger_ui_html():
             return get_swagger_ui_html(
                 openapi_url=app.openapi_url,
@@ -206,7 +207,7 @@ def create_app():  # noqa: C901
         async def swagger_ui_redirect():
             return get_swagger_ui_oauth2_redirect_html()
 
-        @app.get("/redoc", include_in_schema=False)
+        @app.get("/docs", include_in_schema=False)
         async def redoc_html():
             return get_redoc_html(
                 openapi_url=app.openapi_url,
@@ -214,6 +215,15 @@ def create_app():  # noqa: C901
                 redoc_js_url="/static/redoc.standalone.js",
             )
 
+    @app.get("/scalar", include_in_schema=False)
+    async def scalar_html():
+        return get_scalar_api_reference(
+            openapi_url=app.openapi_url,
+            title=app.title,
+            scalar_favicon_url="https://raw.githubusercontent.com/docling-project/docling/refs/heads/main/docs/assets/logo.svg",
+            # hide_client_button=True,  # not yet released but in main
+        )
+
     ########################
     # Async / Sync helpers #
     ########################

docling_serve/datamodel/convert.py

@@ -132,7 +132,11 @@ class ConvertDocumentsOptions(BaseModel):
                 f"Allowed values: {', '.join([v.value for v in OutputFormat])}. "
                 "Optional, defaults to Markdown."
             ),
-            examples=[[OutputFormat.MARKDOWN]],
+            examples=[
+                [OutputFormat.MARKDOWN],
+                [OutputFormat.MARKDOWN, OutputFormat.JSON],
+                [v.value for v in OutputFormat],
+            ],
         ),
     ] = [OutputFormat.MARKDOWN]
 
@@ -231,7 +235,7 @@ class ConvertDocumentsOptions(BaseModel):
         PageRange,
         Field(
             description="Only convert a range of pages. The page number starts at 1.",
-            examples=[(1, 4)],
+            examples=[DEFAULT_PAGE_RANGE, (1, 4)],
         ),
     ] = DEFAULT_PAGE_RANGE
 

docling_serve/gradio_ui.py

@@ -1,5 +1,6 @@
 import base64
 import importlib
+import itertools
 import json
 import logging
 import ssl
@@ -12,6 +13,7 @@ import certifi
 import gradio as gr
 import httpx
 
+from docling.datamodel.base_models import FormatToExtensions
 from docling.datamodel.pipeline_options import (
     PdfBackend,
     PdfPipeline,
@@ -545,19 +547,10 @@ with gr.Blocks(
                     elem_id="file_input_zone",
                     label="Upload File",
                     file_types=[
-                        ".pdf",
-                        ".docx",
-                        ".pptx",
-                        ".html",
-                        ".xlsx",
-                        ".json",
-                        ".asciidoc",
-                        ".txt",
-                        ".md",
-                        ".jpg",
-                        ".jpeg",
-                        ".png",
-                        ".gif",
+                        f".{v}"
+                        for v in itertools.chain.from_iterable(
+                            FormatToExtensions.values()
+                        )
                     ],
                     file_count="multiple",
                     scale=4,

docling_serve/helper_functions.py

@@ -36,7 +36,7 @@ def FormDepends(cls: type[BaseModel]):
         annotation = model_field.annotation
         description = model_field.description
         default = (
-            Form(..., description=description)
+            Form(..., description=description, examples=model_field.examples)
             if model_field.is_required()
             else Form(
                 model_field.default,

docs/README.md

@@ -1,4 +1,4 @@
-# Dolcing Serve documentation
+# Docling Serve documentation
 
 This documentation pages explore the webserver configurations, runtime options, deployment examples as well as development best practices.
 

docs/usage.md

@@ -13,7 +13,7 @@ On top of the source of file (see below), both endpoints support the same parame
 - `do_ocr` (bool): If enabled, the bitmap content will be processed using OCR. Defaults to `True`.
 - `image_export_mode`: Image export mode for the document (only in case of JSON, Markdown or HTML). Allowed values: embedded, placeholder, referenced. Optional, defaults to `embedded`.
 - `force_ocr` (bool): If enabled, replace any existing text with OCR-generated text over the full content. Defaults to `False`.
-- `ocr_engine` (str): OCR engine to use. Allowed values: `easyocr`, `tesseract_cli`, `tesseract`, `rapidocr`, `ocrmac`. Defaults to `easyocr`.
+- `ocr_engine` (str): OCR engine to use. Allowed values: `easyocr`, `tesserocr`, `tesseract`, `rapidocr`, `ocrmac`. Defaults to `easyocr`. To use the `tesserocr` engine, `tesserocr` must be installed where docling-serve is running: `pip install tesserocr`
 - `ocr_lang` (List[str]): List of languages used by the OCR engine. Note that each OCR engine has different values for the language names. Defaults to empty.
 - `pdf_backend` (str): PDF backend to use. Allowed values: `pypdfium2`, `dlparse_v1`, `dlparse_v2`, `dlparse_v4`. Defaults to `dlparse_v4`.
 - `table_mode` (str): Table mode to use. Allowed values: `fast`, `accurate`. Defaults to `fast`.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling-serve"
-version = "0.12.0"  # DO NOT EDIT, updated automatically
+version = "0.15.0"  # DO NOT EDIT, updated automatically
 description = "Running Docling as a service"
 license = {text = "MIT"}
 authors = [
@@ -42,6 +42,7 @@ dependencies = [
     "typer~=0.12",
     "uvicorn[standard]>=0.29.0,<1.0.0",
     "websockets~=14.0",
+    "scalar-fastapi>=1.0.3",
 ]
 
 [project.optional-dependencies]
@@ -213,6 +214,7 @@ module = [
     "kfp.*",
     "kfp_server_api.*",
     "mlx_vlm.*",
+    "scalar_fastapi.*",
 ]
 ignore_missing_imports = true